@globalfishingwatch/i18n-labels 1.2.194 → 1.2.196

package/en/datasets.json

@@ -618,6 +618,13 @@
       "bearing": "bearing"
     }
   },
+  "proto-global-encounters-events-30min": {
+    "name": "PROTOTYPE - Encounter Events of 30min. (AIS)",
+    "description": "The dataset contains encounter events of 30min for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]",
+    "schema": {
+      "duration": "duration"
+    }
+  },
   "proto-global-encounters-events": {
     "name": "Encounter Events. (AIS)",
     "description": "The dataset contains encounter events with authorizations for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]"
@@ -1051,6 +1058,31 @@
       "structure_start_date": "Start date"
     }
   },
+  "public-fixed-infrastructure-filtered": {
+    "name": "Offshore Fixed Infrastructure (SAR, Optical)",
+    "description": "<h2>Overview</h2> <p>Offshore fixed infrastructure is a global dataset that uses AI and machine learning to detect and classify structures throughout the world’s oceans.</p> <p>Classification labels (oil, wind, and unknown) are provided, as well as confidence levels (high, medium, or low) reflecting our certainty in the assigned label. Detections can be filtered and colored on the map using both label and confidence level.<em></em>The data is updated on a monthly basis, and new classified detections are added at the beginning of every month. Viewing change using the timebar is simple, and allows anyone to recognize the rapid industrialization of the world’s oceans. For example, you can easily observe the expansion of wind farms in the North and East China Seas, or changes in oil infrastructure in the Gulf of Mexico or Persian Gulf.</p> <p>By overlaying the existing map layers, you can explore how vessels interact with oil and wind structures, visualise the density of synthetic aperture radar (SAR) and Visible Infrared Imaging Radiometer Suite (VIIRS) vessel detections around infrastructure, or determine which marine protected areas (MPAs) contain wind, oil, or other infrastructure types. These are only examples of the types of questions we can now ask. Offshore fixed infrastructure is a first of its kind dataset that not only brings to light the extensive industrialization of our oceans, but enables users across industries to use this information in research, monitoring and management.</p> <h2>Use cases</h2> <ul> <li>Maritime domain awareness</li> <ul> <li>Infrastructure locations can support maritime domain awareness, and understanding of other activities occurring at sea.</li> <li>Infrastructure data supports assessments of ocean industrialization, facilitating monitoring of areas experiencing build-up or new development</li> </ul> <li>Monitoring vessels</li> <ul> <li>Infrastructure locations can be used to analyse the behaviour of vessels associated with infrastructure, including grouping vessels based on their interaction with oil and wind structures.</li> <li>Interactions between vessels and infrastructure can help quantify the resources required to support offshore industrial activity</li> <li>The impacts of infrastructure on fishing, including attracting or deterring fishing, can be analysed.</li> </ul> <li>Marine protected areas (MPAs) and marine spatial planning</li> <ul> <li>During the planning stage in the designation of new protected areas, knowing the location of existing infrastructure will be vital to understand which stakeholders shall be included in the consultation process, to understand potential conflicts, and identify easy wins.</li> </ul> <li>Environmental impacts</li> <ul> <li>Infrastructure locations can be used to help detect marine pollution events, and to differentiate between types of pollution events (e.g. pollution from vessels versus pollution from platforms)</li> </ul> </ul> <h2>Caveats</h2> <ul> <li><strong>Sentinel-1 and Sentinel-2 satellites do not sample most of the open ocean.</strong></li> <ul> <li>Most industrial activity happens relatively close to shore.</li> <li>The extent and frequency of SAR acquisitions is determined by the mission priorities.</li> <li>For more info see: https://www.nature.com/articles/s41586-023-06825-8/figures/5</li> </ul> <li><strong>We do not provide detections of infrastructure within 1 km of shore</strong></li> <ul> <li>We do not classify objects within 1 km of shore because it is difficult to map where the shoreline begins, and ambiguous coastlines and rocks cause false positives.</li> <li>The bulk of industrial activities, including offshore development with medium-to-large oil rigs and wind farms, occur several kilometers from shore.</li> </ul> <li> <strong>False positives can be produced from noise artifacts.</strong> </li> <ul> <li>Rocks, small islands, sea ice, radar ambiguities (radar echoes), and image artifacts can cause false positives</li> <li>Detections in some areas including Southern Chile, the Arctic, and the Norwegian Sea have been filtered to remove noise.</li> </ul> <li><strong>Spatial coverage varies over time, which can produce different detections results year on year - <a target=\"_blank\" href=\"https://share.cleanshot.com/yG0qfF\"> <span style=\"color:rgb(0, 0, 0);\">Example</span> </a></strong> </li> <ul> <li>Infrastructure detentions from 2017-01-01 to near real time are available, and updated on a monthly basis.</li> </ul> <li> <strong>Labels can change over time</strong> </li> <ul> <li>The label assigned to a structure is the greatest predicted label averaged across time. As we get more data, the label may change, and more accurately predict the true infrastructure type.</li> </ul> <li><strong>Global datasets aren’t perfect</strong></li> <ul> <li>We’ve done our best to create the most accurate product possible, but there will be infrastructure that isn’t detected, or has been classified incorrectly. This will be most evident when working at the project level.</li> <li>We strongly encourage users to provide feedback to the research team so that we may improve future versions of the model. All feedback is greatly appreciated.</li> </ul> </ul> <h2>Methods</h2> <h3>SAR imagery</h3> <p>We use SAR imagery from the Copernicus Sentinel-1 mission of the European Space Agency (ESA) [1]. The images are sourced from two satellites (S1A and S1B up until December 2021 when S1B stopped operating, and S1A only from 2022 onward) that orbit 180 degrees out of phase with each other in a polar, sun-synchronous orbit. Each satellite has a repeat-cycle of 12 days, so that together they provide a global mapping of coastal waters around the world approximately every six days for the period that both were operating. The number of images per location, however, varies greatly depending on mission priorities, latitude, and degree of overlap between adjacent satellite passes. Spatial coverage also varies over time [2]. Our data consist of dual-polarization images (VH and VV) from the Interferometric Wide (IW) swath mode, with a resolution of about 20 m.</p> <p>[1] <a target=\"_blank\" href=\"https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf\"> <span style=\"color:rgb(0, 0, 0);\">https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf</span> </a> </p> <p>[2]<a target=\"_blank\" href=\"https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario\"> <span style=\"color:rgb(0, 0, 0);\"></span> <span style=\"color:rgb(0, 0, 0);\">https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario</span> </a> </p> <h3>Infrastructure detection by SAR</h3> <p>Detecting infrastructure with SAR is based on the widely used Constant False Alarm Rate (CFAR) algorithm, an anomaly detection method conceived for detecting ships in synthetic aperture radar images, that has been modified to remove non-stationary objects. This algorithm is designed to search for pixel values that are unusually bright (the targets) compared to those in the surrounding area (the sea clutter). This method sets a threshold based on the pixel values of the local background (within a window), scanning the whole image pixel-by-pixel. Pixel values above the threshold constitute an anomaly and are likely to be samples from a target.</p> <h3>Infrastructure classification</h3> <p>To classify every detected offshore infrastructure, we used deep learning and designed a ConvNet based on the ConvNeXt architecture. A novel aspect of our deep learning classification approach is the combination of SAR imagery from Sentinel-1 with optical imagery from Sentinel-2. From six-month composites of dual-band SAR (VH and VV) and four-band optical (RGB and NIR) images, we extracted small tiles for every detected fixed infrastructure, with the respective objects at the center of the tile. A single model output includes the probabilities for the specified classes: wind, oil, unknown, lake maracaibo, and noise.</p> <h3>Filtering</h3> <p>GFW post-processed the classified SAR detections to reduce noise (false positives), remove vessels, exclude areas with sea ice at high latitudes, and incorporate expert feedback. We used a clustering approach to identify detections across time (within a 50 m radius) that were likely the same structure but their coordinates differed slightly, and assigned them the greatest average predicted label of the cluster. We also filled in gaps for fixed structures that were missing in one timestep but detected in the previous and following timesteps, and dropped detections appearing in a single timestep. Finally, the dataset underwent extensive manual review and editing by researchers and industry experts in order to refine the final product, and provide the most accurate dataset possible.</p> <h3>Data field descriptions</h3> <p>Each detection has a unique individual identifier (<em>detection_id</em>). A six-month image composite is used in the classification, therefore the <em>detection_date</em> represents the middle of the six month period. This helps to remove non-stationary objects (i.e. vessels), and avoid confusion in the model if a structure is being built, or there isn’t adequate imagery available. <em>structure_id</em> allows you to track a structure through time. There are therefore many <em>detection_id</em> (one for each month the structure is detected) for each <em>structure_id</em>. Labels of <em>wind</em> and <em>oil </em>represent any wind or oil related structure respectively. <em>Unknown</em> represents a structure that is not oil or wind related, such as bridges or navigational buoys. </p> <p>Label confidence levels of ‘High’. ‘Medium’ and ‘Low’ are assigned to each structure, and are conditional on where the detections fell in relation to the boundaries of manually developed wind and oil polygons, and whether the label has changed from the previous month. The <em>label_confidence</em> field can be used to filter analysis. </p> <h2>Resources, code and other notes</h2> <p>Two repos are used in the automation process, both of which are private, and should not be shared publicly.</p> <p>Detection and classification: https://github.com/GlobalFishingWatch/sentinel-1-ee/tree/master</p> <p>Clustering and reclassification: https://github.com/GlobalFishingWatch/infrastructure-post-processing</p> <p>All code developed for the paper, Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity.</p> <h2>Sources data and citations</h2> <p>Copernicus Sentinel data 2017-current</p> <p>Lujala, Päivi; Jan Ketil Rød &amp; Nadia Thieme, 2007. 'Fighting over Oil: Introducing A New Dataset', Conflict Management and Peace Science 24(3), 239-256</p> <p>Sabbatino, M., Romeo, L., Baker, V., Bauer, J., Barkhurst, A., Bean, A., DiGiulio, J., Jones, K., Jones, T.J., Justman, D., Miller III, R., Rose, K., and Tong., A., Global Oil &amp; Gas Infrastructure Features Database Geocube Collection, 2019-03-25, https://edx.netl.doe.gov/dataset/global-oil-gas-infrastructure-features-database-geocube-collection, DOI: 10.18141/1502839</p> <h2>License</h2> <p>Non-Commercial Use Only. The Site and the Services are provided for Non-Commercial use only in accordance with the CC BY-NC 4.0 license. If you would like to use the Site and/or the Services for commercial purposes, please contact us.</p> <h2>Global Fishing Watch metadata</h2> <p>Infrastructure development methods should reference the paper:</p> <p>Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8</p> <p>All code developed for the paper, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity. All the data generated and used by these scripts can reference the following data repos:</p> <p>Analysis and Figures: https://doi.org/10.6084/m9.figshare.24309475</p> <p>Training and Evaluation: https://doi.org/10.6084/m9.figshare.24309469</p>",
+    "schema": {
+      "label": {
+        "keyword": "label",
+        "enum": {
+          "oil": "oil",
+          "wind": "wind",
+          "unknown": "unknown"
+        }
+      },
+      "structure_id": "structure_id",
+      "label_confidence": {
+        "keyword": "label_confidence",
+        "enum": {
+          "high": "high",
+          "low": "low",
+          "medium": "medium"
+        }
+      },
+      "structure_end_date": "structure_end_date",
+      "structure_start_date": "structure_start_date"
+    }
+  },
   "public-global-all-tracks": {
     "name": "Tracks",
     "description": "The dataset contains the tracks from all vessels (AIS) - Version 20231026"
@@ -1090,18 +1122,15 @@
     "name": "Encounter Events (AIS)",
     "description": "Identified from AIS data as locations where two vessels, a carrier and fishing vessel, were within 500 meters for at least 2 hours and traveling at a median speed under 2 knots, while at least 10 km from a coastal anchorage.",
     "schema": {
-      "duration": {
-        "keyword": "Duration",
-        "enum": {
-          "120": "120",
-          "4320": "4320"
-        }
-      }
+      "duration": "duration"
     }
   },
   "public-global-fishing-effort": {
     "name": "AIS",
-    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as known or possible commercial fishing vessels, and applies a fishing presence algorithm to determine “apparent fishing activity” based on changes in vessel speed and direction. The algorithm classifies each AIS broadcast data point for these vessels as either apparently fishing or not fishing and shows the former on the Global Fishing Watch fishing activity heat map. AIS data as broadcast may vary in completeness, accuracy and quality. Also, data collection by satellite or terrestrial receivers may introduce errors through missing or inaccurate data. Global Fishing Watch’s fishing presence algorithm is a best effort mathematically to identify “apparent fishing activity.” As a result, it is possible that some fishing activity is not identified as such by Global Fishing Watch; conversely, Global Fishing Watch may show apparent fishing activity where fishing is not actually taking place. For these reasons, Global Fishing Watch qualifies designations of vessel fishing activity, including synonyms of the term “fishing activity,” such as “fishing” or “fishing effort,” as “apparent,” rather than certain. Any/all Global Fishing Watch information about “apparent fishing activity” should be considered an estimate and must be relied upon solely at your own risk. Global Fishing Watch is taking steps to make sure fishing activity designations are as accurate as possible. Global Fishing Watch fishing presence algorithms are developed and tested using actual fishing event data collected by observers, combined with expert analysis of vessel movement data resulting in the manual classification of thousands of known fishing events. Global Fishing Watch also collaborates extensively with academic researchers through our research program to share fishing activity classification data and automated classification techniques."
+    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as known or possible commercial fishing vessels, and applies a fishing presence algorithm to determine “apparent fishing activity” based on changes in vessel speed and direction. The algorithm classifies each AIS broadcast data point for these vessels as either apparently fishing or not fishing and shows the former on the Global Fishing Watch fishing activity heat map. AIS data as broadcast may vary in completeness, accuracy and quality. Also, data collection by satellite or terrestrial receivers may introduce errors through missing or inaccurate data. Global Fishing Watch’s fishing presence algorithm is a best effort mathematically to identify “apparent fishing activity.” As a result, it is possible that some fishing activity is not identified as such by Global Fishing Watch; conversely, Global Fishing Watch may show apparent fishing activity where fishing is not actually taking place. For these reasons, Global Fishing Watch qualifies designations of vessel fishing activity, including synonyms of the term “fishing activity,” such as “fishing” or “fishing effort,” as “apparent,” rather than certain. Any/all Global Fishing Watch information about “apparent fishing activity” should be considered an estimate and must be relied upon solely at your own risk. Global Fishing Watch is taking steps to make sure fishing activity designations are as accurate as possible. Global Fishing Watch fishing presence algorithms are developed and tested using actual fishing event data collected by observers, combined with expert analysis of vessel movement data resulting in the manual classification of thousands of known fishing events. Global Fishing Watch also collaborates extensively with academic researchers through our research program to share fishing activity classification data and automated classification techniques.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-fishing-vessels": {
     "name": "AIS (Fishing Vessels)",
@@ -1147,7 +1176,10 @@
   },
   "public-global-presence": {
     "name": "AIS",
-    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. The activity layer displays a heatmap of vessel presence. The presence is determined by taking one position per hour per vessel from the positions transmitted by the vessel's AIS."
+    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. The activity layer displays a heatmap of vessel presence. The presence is determined by taking one position per hour per vessel from the positions transmitted by the vessel's AIS.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-salinity": {
     "name": "Salinity",
@@ -1229,6 +1261,10 @@
     "name": "Wave height",
     "description": "<h2>Overview</h2>\n<ul>\n<li>Wave height is the vertical distance from the trough (bottom) to the crest (top) of a wave on the sea surface. This dataset uses the significant wave height, which is the average of the highest one-third of all wave heights over a given sample period.</li>\n<ul>\n<h2>Source</h2>\n<ul>\n <a href='https://www.pacioos.hawaii.edu/metadata/ww3_global.html'>Cheung, K.F. 2010, updated 2021. WaveWatch III (WW3) Global Wave Model. Distributed by the Pacific Islands Ocean Observing System (PacIOOS), which is a part of the U.S. Integrated Ocean Observing System (IOOS®), funded in part by National Oceanic and Atmospheric Administration (NOAA) Awards #NA16NOS0120024 and #NA21NOS0120091.</a></li>"
   },
+  "public-global-tracks": {
+    "name": "Tracks",
+    "description": "The dataset contains the tracks from all vessels (AIS) - Version 3.0"
+  },
   "public-global-vessel-identity": {
     "name": "AIS (all vessel types)",
     "description": "Vessel Identity (all shiptypes)"
@@ -1241,11 +1277,28 @@
     "name": "Night light detections (VIIRS)",
     "description": "The night lights vessel detections layer, known as visible infrared imaging radiometer suite or VIIRS, shows vessels at sea that satellites have detected by the light they emit at night. Though not exclusively associated with fishing vessels, this activity layer is likely to show vessels associated with activities like squid fishing, which use bright lights and fish at night.<br/>\n<br/>\nBased on the Suomi NPP satellite, the VIIRS sensor makes a pass across the entire planet at least once every night, detecting lights to provide at least one daily observation globally. Due to the orbit design of polar orbiting satellites, regions closer to polar will have more over-passes per day, while equatorial regions have only one over-pass daily.<br/> \n<br/>\nBecause the vessels are detected solely based on light emission, we can detect individual vessels and even entire fishing fleets that may not broadcast identity information and so may not be represented elsewhere on the Global Fishing Watch map. Global Fishing Watch ingests boat detections processed from low light imaging data collected by the U.S. National Oceanic and Atmospheric Administration (NOAA) VIIRS. The boat detections are processed in near-real time by the <a href='https://eogdata.mines.edu/products/vbd/' target='_blank' rel=noopener'>Earth Observation Group</a> at the Colorado School of Mines. The data, known as VIIRS boat detections, picks up the presence of vessels, including those fishing using lights to attract catch or to conduct operations at night.Lights from fixed offshore infrastructure and other non-vessel sources are excluded. Read more about VIIRS night light vessel detections, and download the <a href='https://eogdata.mines.edu/products/vbd/' target='_blank' rel=noopener'>data</a>.<br/>\n<br/>\nGlobal Fishing Watch has developed a sophisticated system to match available automatic identification system (AIS) data to respective night light vessel detections. This matching is done using a probabilistic model that determines AIS-message/VIIRS-detection pairs based on all available AIS records right before and right after the time the satellite VIIRS image was taken, as well as the probability of pairing a specific AIS message to any of the vessels appearing on that image. Using this information, Global Fishing Watch has added the experimental ability to filter detections based on vessel type and gear type within the VIIRS activity layer.<br/>\n<br/>\nMore than 85% of the detections are from vessels that lack AIS or publicly shared vessel monitoring system (VMS) transponders. The global addition of the VIIRS layer enables you to rapidly filter the night light detections that either were matched or not with AIS where vessel identification is available.<br/>\n<br/>\nRadiance indicates the brightness of the light source received by the VIIRS sensor. Radiance is impacted by the moon, clouds, and the angle of the vessel from the satellite. Two vessels with the same brightness, or light intensity, may have different radiance levels depending on the conditions. In general, vessels that are not actively fishing using light may have lower radiance levels. Exceptions should be considered when vessels are approaching a coastline. To further explore how vessel lights at night emit different radiance levels, the VIIRS activity layer can be filtered to specific ranges of interest associated with different human behaviours.<br/>\n<br/>\nThose using night light detections data should consider the South Atlantic Anomaly (SAA), an area where the Earth's inner Van Allen radiation belt is at its lowest altitude, allowing more energetic particles from space to penetrate. When such particles hit the sensors on a satellite, this can create a false signal which might cause the algorithm to recognize it as a boat detection. A filtration algorithm has been applied but there may still be some mis-identification",
     "schema": {
+      "bearing": "bearing",
+      "matched": {
+        "keyword": "matched",
+        "enum": {
+          "true": "true",
+          "false": "false"
+        }
+      },
       "radiance": {
         "keyword": "Radiance",
         "enum": {
-          "1": "1",
-          "1000": "1000"
+          "0": "0",
+          "10000": "10000"
+        }
+      },
+      "shiptype": {
+        "keyword": "shiptype",
+        "enum": {
+          "unknown": "unknown",
+          "fishing": "fishing",
+          "carrier": "carrier",
+          "support": "support"
         }
       },
       "qf_detect": {

package/es/datasets.json

@@ -618,6 +618,13 @@
       "bearing": "bearing"
     }
   },
+  "proto-global-encounters-events-30min": {
+    "name": "PROTOTYPE - Encounter Events of 30min. (AIS)",
+    "description": "The dataset contains encounter events of 30min for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]",
+    "schema": {
+      "duration": "duration"
+    }
+  },
   "proto-global-encounters-events": {
     "name": "Encounter Events. (AIS)",
     "description": "The dataset contains encounter events with authorizations for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]"
@@ -1051,6 +1058,31 @@
       "structure_start_date": "structure_start_date"
     }
   },
+  "public-fixed-infrastructure-filtered": {
+    "name": "Offshore Fixed Infrastructure (SAR, Optical)",
+    "description": "<h2>Overview</h2> <p>Offshore fixed infrastructure is a global dataset that uses AI and machine learning to detect and classify structures throughout the world’s oceans.</p> <p>Classification labels (oil, wind, and unknown) are provided, as well as confidence levels (high, medium, or low) reflecting our certainty in the assigned label. Detections can be filtered and colored on the map using both label and confidence level.<em></em>The data is updated on a monthly basis, and new classified detections are added at the beginning of every month. Viewing change using the timebar is simple, and allows anyone to recognize the rapid industrialization of the world’s oceans. For example, you can easily observe the expansion of wind farms in the North and East China Seas, or changes in oil infrastructure in the Gulf of Mexico or Persian Gulf.</p> <p>By overlaying the existing map layers, you can explore how vessels interact with oil and wind structures, visualise the density of synthetic aperture radar (SAR) and Visible Infrared Imaging Radiometer Suite (VIIRS) vessel detections around infrastructure, or determine which marine protected areas (MPAs) contain wind, oil, or other infrastructure types. These are only examples of the types of questions we can now ask. Offshore fixed infrastructure is a first of its kind dataset that not only brings to light the extensive industrialization of our oceans, but enables users across industries to use this information in research, monitoring and management.</p> <h2>Use cases</h2> <ul> <li>Maritime domain awareness</li> <ul> <li>Infrastructure locations can support maritime domain awareness, and understanding of other activities occurring at sea.</li> <li>Infrastructure data supports assessments of ocean industrialization, facilitating monitoring of areas experiencing build-up or new development</li> </ul> <li>Monitoring vessels</li> <ul> <li>Infrastructure locations can be used to analyse the behaviour of vessels associated with infrastructure, including grouping vessels based on their interaction with oil and wind structures.</li> <li>Interactions between vessels and infrastructure can help quantify the resources required to support offshore industrial activity</li> <li>The impacts of infrastructure on fishing, including attracting or deterring fishing, can be analysed.</li> </ul> <li>Marine protected areas (MPAs) and marine spatial planning</li> <ul> <li>During the planning stage in the designation of new protected areas, knowing the location of existing infrastructure will be vital to understand which stakeholders shall be included in the consultation process, to understand potential conflicts, and identify easy wins.</li> </ul> <li>Environmental impacts</li> <ul> <li>Infrastructure locations can be used to help detect marine pollution events, and to differentiate between types of pollution events (e.g. pollution from vessels versus pollution from platforms)</li> </ul> </ul> <h2>Caveats</h2> <ul> <li><strong>Sentinel-1 and Sentinel-2 satellites do not sample most of the open ocean.</strong></li> <ul> <li>Most industrial activity happens relatively close to shore.</li> <li>The extent and frequency of SAR acquisitions is determined by the mission priorities.</li> <li>For more info see: https://www.nature.com/articles/s41586-023-06825-8/figures/5</li> </ul> <li><strong>We do not provide detections of infrastructure within 1 km of shore</strong></li> <ul> <li>We do not classify objects within 1 km of shore because it is difficult to map where the shoreline begins, and ambiguous coastlines and rocks cause false positives.</li> <li>The bulk of industrial activities, including offshore development with medium-to-large oil rigs and wind farms, occur several kilometers from shore.</li> </ul> <li> <strong>False positives can be produced from noise artifacts.</strong> </li> <ul> <li>Rocks, small islands, sea ice, radar ambiguities (radar echoes), and image artifacts can cause false positives</li> <li>Detections in some areas including Southern Chile, the Arctic, and the Norwegian Sea have been filtered to remove noise.</li> </ul> <li><strong>Spatial coverage varies over time, which can produce different detections results year on year - <a target=\"_blank\" href=\"https://share.cleanshot.com/yG0qfF\"> <span style=\"color:rgb(0, 0, 0);\">Example</span> </a></strong> </li> <ul> <li>Infrastructure detentions from 2017-01-01 to near real time are available, and updated on a monthly basis.</li> </ul> <li> <strong>Labels can change over time</strong> </li> <ul> <li>The label assigned to a structure is the greatest predicted label averaged across time. As we get more data, the label may change, and more accurately predict the true infrastructure type.</li> </ul> <li><strong>Global datasets aren’t perfect</strong></li> <ul> <li>We’ve done our best to create the most accurate product possible, but there will be infrastructure that isn’t detected, or has been classified incorrectly. This will be most evident when working at the project level.</li> <li>We strongly encourage users to provide feedback to the research team so that we may improve future versions of the model. All feedback is greatly appreciated.</li> </ul> </ul> <h2>Methods</h2> <h3>SAR imagery</h3> <p>We use SAR imagery from the Copernicus Sentinel-1 mission of the European Space Agency (ESA) [1]. The images are sourced from two satellites (S1A and S1B up until December 2021 when S1B stopped operating, and S1A only from 2022 onward) that orbit 180 degrees out of phase with each other in a polar, sun-synchronous orbit. Each satellite has a repeat-cycle of 12 days, so that together they provide a global mapping of coastal waters around the world approximately every six days for the period that both were operating. The number of images per location, however, varies greatly depending on mission priorities, latitude, and degree of overlap between adjacent satellite passes. Spatial coverage also varies over time [2]. Our data consist of dual-polarization images (VH and VV) from the Interferometric Wide (IW) swath mode, with a resolution of about 20 m.</p> <p>[1] <a target=\"_blank\" href=\"https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf\"> <span style=\"color:rgb(0, 0, 0);\">https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf</span> </a> </p> <p>[2]<a target=\"_blank\" href=\"https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario\"> <span style=\"color:rgb(0, 0, 0);\"></span> <span style=\"color:rgb(0, 0, 0);\">https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario</span> </a> </p> <h3>Infrastructure detection by SAR</h3> <p>Detecting infrastructure with SAR is based on the widely used Constant False Alarm Rate (CFAR) algorithm, an anomaly detection method conceived for detecting ships in synthetic aperture radar images, that has been modified to remove non-stationary objects. This algorithm is designed to search for pixel values that are unusually bright (the targets) compared to those in the surrounding area (the sea clutter). This method sets a threshold based on the pixel values of the local background (within a window), scanning the whole image pixel-by-pixel. Pixel values above the threshold constitute an anomaly and are likely to be samples from a target.</p> <h3>Infrastructure classification</h3> <p>To classify every detected offshore infrastructure, we used deep learning and designed a ConvNet based on the ConvNeXt architecture. A novel aspect of our deep learning classification approach is the combination of SAR imagery from Sentinel-1 with optical imagery from Sentinel-2. From six-month composites of dual-band SAR (VH and VV) and four-band optical (RGB and NIR) images, we extracted small tiles for every detected fixed infrastructure, with the respective objects at the center of the tile. A single model output includes the probabilities for the specified classes: wind, oil, unknown, lake maracaibo, and noise.</p> <h3>Filtering</h3> <p>GFW post-processed the classified SAR detections to reduce noise (false positives), remove vessels, exclude areas with sea ice at high latitudes, and incorporate expert feedback. We used a clustering approach to identify detections across time (within a 50 m radius) that were likely the same structure but their coordinates differed slightly, and assigned them the greatest average predicted label of the cluster. We also filled in gaps for fixed structures that were missing in one timestep but detected in the previous and following timesteps, and dropped detections appearing in a single timestep. Finally, the dataset underwent extensive manual review and editing by researchers and industry experts in order to refine the final product, and provide the most accurate dataset possible.</p> <h3>Data field descriptions</h3> <p>Each detection has a unique individual identifier (<em>detection_id</em>). A six-month image composite is used in the classification, therefore the <em>detection_date</em> represents the middle of the six month period. This helps to remove non-stationary objects (i.e. vessels), and avoid confusion in the model if a structure is being built, or there isn’t adequate imagery available. <em>structure_id</em> allows you to track a structure through time. There are therefore many <em>detection_id</em> (one for each month the structure is detected) for each <em>structure_id</em>. Labels of <em>wind</em> and <em>oil </em>represent any wind or oil related structure respectively. <em>Unknown</em> represents a structure that is not oil or wind related, such as bridges or navigational buoys. </p> <p>Label confidence levels of ‘High’. ‘Medium’ and ‘Low’ are assigned to each structure, and are conditional on where the detections fell in relation to the boundaries of manually developed wind and oil polygons, and whether the label has changed from the previous month. The <em>label_confidence</em> field can be used to filter analysis. </p> <h2>Resources, code and other notes</h2> <p>Two repos are used in the automation process, both of which are private, and should not be shared publicly.</p> <p>Detection and classification: https://github.com/GlobalFishingWatch/sentinel-1-ee/tree/master</p> <p>Clustering and reclassification: https://github.com/GlobalFishingWatch/infrastructure-post-processing</p> <p>All code developed for the paper, Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity.</p> <h2>Sources data and citations</h2> <p>Copernicus Sentinel data 2017-current</p> <p>Lujala, Päivi; Jan Ketil Rød &amp; Nadia Thieme, 2007. 'Fighting over Oil: Introducing A New Dataset', Conflict Management and Peace Science 24(3), 239-256</p> <p>Sabbatino, M., Romeo, L., Baker, V., Bauer, J., Barkhurst, A., Bean, A., DiGiulio, J., Jones, K., Jones, T.J., Justman, D., Miller III, R., Rose, K., and Tong., A., Global Oil &amp; Gas Infrastructure Features Database Geocube Collection, 2019-03-25, https://edx.netl.doe.gov/dataset/global-oil-gas-infrastructure-features-database-geocube-collection, DOI: 10.18141/1502839</p> <h2>License</h2> <p>Non-Commercial Use Only. The Site and the Services are provided for Non-Commercial use only in accordance with the CC BY-NC 4.0 license. If you would like to use the Site and/or the Services for commercial purposes, please contact us.</p> <h2>Global Fishing Watch metadata</h2> <p>Infrastructure development methods should reference the paper:</p> <p>Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8</p> <p>All code developed for the paper, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity. All the data generated and used by these scripts can reference the following data repos:</p> <p>Analysis and Figures: https://doi.org/10.6084/m9.figshare.24309475</p> <p>Training and Evaluation: https://doi.org/10.6084/m9.figshare.24309469</p>",
+    "schema": {
+      "label": {
+        "keyword": "label",
+        "enum": {
+          "oil": "oil",
+          "wind": "wind",
+          "unknown": "unknown"
+        }
+      },
+      "structure_id": "structure_id",
+      "label_confidence": {
+        "keyword": "label_confidence",
+        "enum": {
+          "high": "high",
+          "low": "low",
+          "medium": "medium"
+        }
+      },
+      "structure_end_date": "structure_end_date",
+      "structure_start_date": "structure_start_date"
+    }
+  },
   "public-global-all-tracks": {
     "name": "Trayectorias",
     "description": "The dataset contains the tracks from all vessels (AIS) - Version 20231026"
@@ -1088,20 +1120,17 @@
   },
   "public-global-encounters-events": {
     "name": "Encounter Events. (AIS)",
-    "description": "Identificado de los datos AIS como lugares donde dos buques, un transportador y uno pesquero; estuvieron a 500 metros durante al menos 2 horas y viajando a una velocidad media de &lt;2 nudos, y a menos de 10 km de la costa.",
+    "description": "Identified from AIS data as locations where two vessels, a carrier and fishing vessel, were within 500 meters for at least 2 hours and traveling at a median speed under 2 knots, while at least 10 km from a coastal anchorage.",
     "schema": {
-      "duration": {
-        "keyword": "duración",
-        "enum": {
-          "120": "120",
-          "4320": "4320"
-        }
-      }
+      "duration": "duration"
     }
   },
   "public-global-fishing-effort": {
     "name": "AIS",
-    "description": "Global Fishing Watch utiliza datos sobre la identidad, el tipo, la ubicación, la velocidad, y otros datos que son emitidos a través del Sistema de Identificación Automática (AIS) y recolectados a través de satélites y receptores terrestres. El AIS fue desarrollado para la prevención de colisión/esquivación. Global Fishing Watch analiza los datos AIS recopilados de los buques que nuestra investigación ha identificado como conocidos o posibles buques pesqueros comerciales, y aplica un algoritmo de detección de pesca para determinar una “aparente actividad pesquera” basado en cambios en la velocidad y dirección de los buques. El algoritmo clasifica cada punto de datos para estos buques como pesca aparente o sin actividad pesquera y muestra el primero en el mapa de calor de la actividad pesquera de Global Fishing Watch. Los datos AIS pueden variar en integridad, precisión y calidad. Además, la recolección de datos por parte de receptores satelitales o terrestres, puede introducir errores a través de datos faltantes o inexactos. El algoritmo de detección de pesca de Global Fishing Watch representa un esfuerzo matemático para identificar una “aparente actividad pesquera”. Como resultado, es posible que algunas actividades pesqueras no sean identificadas como tales por Global Fishing Watch. Por el contrario, Global Fishing Watch puede mostrar una actividad pesquera aparente en la que la pesca no se está llevando a cabo. Por estas razones, Global Fishing Watch califica “actividad pesquera”,“pesca” o “esfuerzo pesquero” como “aparente”, en lugar de brindar certeza sobre la actividad. En todo o en parte, la información de Global Fishing Watch sobre “aparente actividad de pesca” debe ser considerada una estimación y debe ser confiada únicamente bajo su propio riesgo. Global Fishing Watch está tomando medidas para asegurar que la identificación del comportamiento de la actividad pesquera sea lo más exacta posible. Los algoritmos de detección de pesca de Global Fishing Watch son desarrollados y probados usando datos reales de eventos de pesca recopilados por observadores, combinado con el análisis experto de los datos del movimiento de buques que dan lugar a la clasificación manual de miles de eventos de pesca conocidos. Global Fishing Watch también colabora ampliamente con investigadores académicos a través de nuestro programa de investigación para compartir datos de clasificación de actividades pesqueras y técnicas de clasificación automatizadas."
+    "description": "Global Fishing Watch utiliza datos sobre la identidad, el tipo, la ubicación, la velocidad, y otros datos que son emitidos a través del Sistema de Identificación Automática (AIS) y recolectados a través de satélites y receptores terrestres. El AIS fue desarrollado para la prevención de colisión/esquivación. Global Fishing Watch analiza los datos AIS recopilados de los buques que nuestra investigación ha identificado como conocidos o posibles buques pesqueros comerciales, y aplica un algoritmo de detección de pesca para determinar una “aparente actividad pesquera” basado en cambios en la velocidad y dirección de los buques. El algoritmo clasifica cada punto de datos para estos buques como pesca aparente o sin actividad pesquera y muestra el primero en el mapa de calor de la actividad pesquera de Global Fishing Watch. Los datos AIS pueden variar en integridad, precisión y calidad. Además, la recolección de datos por parte de receptores satelitales o terrestres, puede introducir errores a través de datos faltantes o inexactos. El algoritmo de detección de pesca de Global Fishing Watch representa un esfuerzo matemático para identificar una “aparente actividad pesquera”. Como resultado, es posible que algunas actividades pesqueras no sean identificadas como tales por Global Fishing Watch. Por el contrario, Global Fishing Watch puede mostrar una actividad pesquera aparente en la que la pesca no se está llevando a cabo. Por estas razones, Global Fishing Watch califica “actividad pesquera”,“pesca” o “esfuerzo pesquero” como “aparente”, en lugar de brindar certeza sobre la actividad. En todo o en parte, la información de Global Fishing Watch sobre “aparente actividad de pesca” debe ser considerada una estimación y debe ser confiada únicamente bajo su propio riesgo. Global Fishing Watch está tomando medidas para asegurar que la identificación del comportamiento de la actividad pesquera sea lo más exacta posible. Los algoritmos de detección de pesca de Global Fishing Watch son desarrollados y probados usando datos reales de eventos de pesca recopilados por observadores, combinado con el análisis experto de los datos del movimiento de buques que dan lugar a la clasificación manual de miles de eventos de pesca conocidos. Global Fishing Watch también colabora ampliamente con investigadores académicos a través de nuestro programa de investigación para compartir datos de clasificación de actividades pesqueras y técnicas de clasificación automatizadas.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-fishing-vessels": {
     "name": "AIS (Buques de pesca)",
@@ -1147,7 +1176,10 @@
   },
   "public-global-presence": {
     "name": "AIS",
-    "description": "Global Fishing Watch utiliza datos sobre la identidad, el tipo, la ubicación, la velocidad, y otros datos que son emitidos a través del Sistema de Identificación Automática (AIS) y recolectados a través de satélites y receptores terrestres. El AIS fue desarrollado para la prevención de colisión/esquivación. La capa de actividad muestra un mapa de calor de la presencia de buques. La presencia se determina tomando una posición al hora por buque a partir de las posiciones transmitidas por el AIS de la buque."
+    "description": "Global Fishing Watch utiliza datos sobre la identidad, el tipo, la ubicación, la velocidad, y otros datos que son emitidos a través del Sistema de Identificación Automática (AIS) y recolectados a través de satélites y receptores terrestres. El AIS fue desarrollado para la prevención de colisión/esquivación. La capa de actividad muestra un mapa de calor de la presencia de buques. La presencia se determina tomando una posición al hora por buque a partir de las posiciones transmitidas por el AIS de la buque.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-salinity": {
     "name": "Salinidad",
@@ -1229,6 +1261,10 @@
     "name": "Altura de ola",
     "description": "<h2>Resumen</h2>\n<ul>\n<li>La altura de ola es la distancia vertical desde el valle (abajo) hasta la cresta (arriba) de una ola sobre la superficie del mar. Este conjunto de datos utiliza la altura de ola significante, la cual es el promedio del tercio más alto de todas las alturas de ola durante un período de muestra determinado.</li>\n<ul>\n<h2>Fuente</h2>\n<ul>\n <a href='https://www.pacioos.hawaii.edu/metadata/ww3_global.html'>Cheung, K.F. 2010, updated 2021. WaveWatch III (WW3) Global Wave Model. Distributed by the Pacific Islands Ocean Observing System (PacIOOS), which is a part of the U.S. Integrated Ocean Observing System (IOOS®), funded in part by National Oceanic and Atmospheric Administration (NOAA) Awards #NA16NOS0120024 and #NA21NOS0120091.</a></li>"
   },
+  "public-global-tracks": {
+    "name": "Tracks",
+    "description": "The dataset contains the tracks from all vessels (AIS) - Version 3.0"
+  },
   "public-global-vessel-identity": {
     "name": "AIS (all vessel types)",
     "description": "Vessel Identity (all shiptypes)"
@@ -1238,14 +1274,31 @@
     "description": "Vessel Insights from AIS"
   },
   "public-global-viirs-presence": {
-    "name": "Detecciones de luz nocturna (VIIRS)",
+    "name": "Night light detections (VIIRS)",
     "description": "La capa de detección nocturna de barcos, conocida como conjunto de radiómetros de imágenes infrarrojas visibles (VIIRS, por sus siglas en ingles), muestra las embarcaciones en el mar que los satélites han detectado por la luz que emiten durante la noche. Aunque no se asocia exclusivamente con embarcaciones pesqueras, es probable que esta capa de actividad muestre embarcaciones asociadas con actividades como la pesca de calamar, que utilizan luces brillantes y pescan de noche.<br/>\n<br/>\nBasado en el satélite Suomi NPP, el sensor VIIRS pasa por todo el planeta al menos una vez cada noche, detectando luces para proporcionar al menos una observación diaria a nivel mundial. Debido al diseño de la órbita de los satélites de órbita polar, las regiones más cercanas a los polos tendrán más sobrepasos por día, mientras que las regiones ecuatoriales solo tienen un sobrepaso por día.<br/>\n<br/>\nDebido a que las embarcaciones se detectan únicamente en función a la emisión de luz, podemos detectar embarcaciones individuales e incluso flotas pesqueras completas que pueden no transmitir información de su identidad y, por lo tanto, pueden no estar representadas en otra parte del mapa de Global Fishing Watch. Global Fishing Watch incluye las detecciones de embarcaciones procesadas a partir de datos de las imágenes satelitales nocturnas recopilados por la Administración Nacional Oceánica y Atmosférica de los EE. UU. (NOAA por sus siglas en inglés) VIIRS. Las detecciones de embarcaciones son procesadas casi en tiempo real por el <a href='https://eogdata.mines.edu/products/vbd/' target='_blank' rel=noopener'>Earth Observation Group</a> en la Colorado School of Mines. Los datos, conocidos como detecciones de embarcaciones VIIRS, detectan la presencia de embarcaciones, incluidas aquellas que pescan con luces para atraer a su recurso objetivo o para realizar operaciones nocturnas. Se excluyen las luces de las infraestructuras fijas en el mar y otras fuentes ajenas a las embarcaciones. Obtenga más información sobre las detecciones nocturnas de embarcaciones VIIRS y descargue los <a href='https://eogdata.mines.edu/products/vbd/' target='_blank' rel=noopener'>datos</a>.<br/>\n<br/>\nGlobal Fishing Watch ha desarrollado un sistema sofisticado para hacer coincidir los datos disponibles del sistema de identificación automática (AIS, por sus siglas en inglés) con las respectivas detecciones nocturnas de embarcaciones. Esta coincidencia se realiza mediante un modelo probabilístico que determina los mensajes AIS/detección VIIRS que coinciden en función de todos los registros AIS disponibles justo antes y después de la hora en que se tomó la imagen satelital VIIRS, así como la probabilidad de emparejar un mensaje específico de AIS para cualquiera de las embarcaciones que aparecen en esa imagen satelital. Con esta información, Global Fishing Watch agregó la capacidad de filtrar las detecciones según el tipo de embarcación y el tipo de arte de pesca dentro de la capa de actividad VIIRS.<br/>\n<br/>\nMás del 85% de las detecciones son de embarcaciones que carecen de transpondedores AIS o del sistema de monitoreo de embarcaciones (VMS, por sus siglas en inglés). La adición global de la capa VIIRS le permite rápidamente filtrar las detecciones nocturnas que coincidieron o no con AIS, donde la identificación de la embarcación está disponible.<br/>\n<br/>\nEl resplandor indica el brillo de la fuente de luz recibida por el sensor VIIRS. El resplandor se ve afectado por la luna, las nubes y el ángulo de la embarcación identificada desde el satélite. Dos embarcaciones con el mismo brillo o intensidad de luz pueden tener diferentes niveles de resplandor dependiendo de las condiciones. En general, las embarcaciones que no están pescando activamente con luz pueden tener niveles de resplandor más bajos. Deben considerarse excepciones cuando los barcos se acercan a la costa. Para explorar más a fondo cómo las luces de las embarcaciones emiten diferentes niveles de resplandor durante la noche, la capa de actividad VIIRS puede ser filtrada por rangos específicos de interés asociados con diferentes comportamientos humanos.<br/>\n<br/>\nAquellos que utilizan datos de detecciones nocturnas deben considerar la Anomalía del Atlántico Sur (SAA, siglas en inglés), un área donde el cinturón interno de resplandor de Van Allen de la Tierra se encuentra en su altitud más baja, lo que permite que penetren más partículas energéticas del espacio. Cuando tales partículas golpean los sensores en un satélite, esto puede crear una señal falsa que podría hacer que el algoritmo lo reconozca como una detección de embarcación. Se ha aplicado un algoritmo de filtración, pero aún puede haber algún error de identificación ",
     "schema": {
+      "bearing": "bearing",
+      "matched": {
+        "keyword": "matched",
+        "enum": {
+          "true": "true",
+          "false": "false"
+        }
+      },
       "radiance": {
         "keyword": "Resplandor",
         "enum": {
-          "1": "1",
-          "1000": "1000"
+          "0": "0",
+          "10000": "10000"
+        }
+      },
+      "shiptype": {
+        "keyword": "shiptype",
+        "enum": {
+          "unknown": "unknown",
+          "fishing": "fishing",
+          "carrier": "carrier",
+          "support": "support"
         }
       },
       "qf_detect": {

package/fr/datasets.json

@@ -618,6 +618,13 @@
       "bearing": "bearing"
     }
   },
+  "proto-global-encounters-events-30min": {
+    "name": "PROTOTYPE - Encounter Events of 30min. (AIS)",
+    "description": "The dataset contains encounter events of 30min for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]",
+    "schema": {
+      "duration": "duration"
+    }
+  },
   "proto-global-encounters-events": {
     "name": "Événements de rencontre (AIS)",
     "description": "The dataset contains encounter events with authorizations for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]"
@@ -1051,6 +1058,31 @@
       "structure_start_date": "structure_start_date"
     }
   },
+  "public-fixed-infrastructure-filtered": {
+    "name": "Offshore Fixed Infrastructure (SAR, Optical)",
+    "description": "<h2>Overview</h2> <p>Offshore fixed infrastructure is a global dataset that uses AI and machine learning to detect and classify structures throughout the world’s oceans.</p> <p>Classification labels (oil, wind, and unknown) are provided, as well as confidence levels (high, medium, or low) reflecting our certainty in the assigned label. Detections can be filtered and colored on the map using both label and confidence level.<em></em>The data is updated on a monthly basis, and new classified detections are added at the beginning of every month. Viewing change using the timebar is simple, and allows anyone to recognize the rapid industrialization of the world’s oceans. For example, you can easily observe the expansion of wind farms in the North and East China Seas, or changes in oil infrastructure in the Gulf of Mexico or Persian Gulf.</p> <p>By overlaying the existing map layers, you can explore how vessels interact with oil and wind structures, visualise the density of synthetic aperture radar (SAR) and Visible Infrared Imaging Radiometer Suite (VIIRS) vessel detections around infrastructure, or determine which marine protected areas (MPAs) contain wind, oil, or other infrastructure types. These are only examples of the types of questions we can now ask. Offshore fixed infrastructure is a first of its kind dataset that not only brings to light the extensive industrialization of our oceans, but enables users across industries to use this information in research, monitoring and management.</p> <h2>Use cases</h2> <ul> <li>Maritime domain awareness</li> <ul> <li>Infrastructure locations can support maritime domain awareness, and understanding of other activities occurring at sea.</li> <li>Infrastructure data supports assessments of ocean industrialization, facilitating monitoring of areas experiencing build-up or new development</li> </ul> <li>Monitoring vessels</li> <ul> <li>Infrastructure locations can be used to analyse the behaviour of vessels associated with infrastructure, including grouping vessels based on their interaction with oil and wind structures.</li> <li>Interactions between vessels and infrastructure can help quantify the resources required to support offshore industrial activity</li> <li>The impacts of infrastructure on fishing, including attracting or deterring fishing, can be analysed.</li> </ul> <li>Marine protected areas (MPAs) and marine spatial planning</li> <ul> <li>During the planning stage in the designation of new protected areas, knowing the location of existing infrastructure will be vital to understand which stakeholders shall be included in the consultation process, to understand potential conflicts, and identify easy wins.</li> </ul> <li>Environmental impacts</li> <ul> <li>Infrastructure locations can be used to help detect marine pollution events, and to differentiate between types of pollution events (e.g. pollution from vessels versus pollution from platforms)</li> </ul> </ul> <h2>Caveats</h2> <ul> <li><strong>Sentinel-1 and Sentinel-2 satellites do not sample most of the open ocean.</strong></li> <ul> <li>Most industrial activity happens relatively close to shore.</li> <li>The extent and frequency of SAR acquisitions is determined by the mission priorities.</li> <li>For more info see: https://www.nature.com/articles/s41586-023-06825-8/figures/5</li> </ul> <li><strong>We do not provide detections of infrastructure within 1 km of shore</strong></li> <ul> <li>We do not classify objects within 1 km of shore because it is difficult to map where the shoreline begins, and ambiguous coastlines and rocks cause false positives.</li> <li>The bulk of industrial activities, including offshore development with medium-to-large oil rigs and wind farms, occur several kilometers from shore.</li> </ul> <li> <strong>False positives can be produced from noise artifacts.</strong> </li> <ul> <li>Rocks, small islands, sea ice, radar ambiguities (radar echoes), and image artifacts can cause false positives</li> <li>Detections in some areas including Southern Chile, the Arctic, and the Norwegian Sea have been filtered to remove noise.</li> </ul> <li><strong>Spatial coverage varies over time, which can produce different detections results year on year - <a target=\"_blank\" href=\"https://share.cleanshot.com/yG0qfF\"> <span style=\"color:rgb(0, 0, 0);\">Example</span> </a></strong> </li> <ul> <li>Infrastructure detentions from 2017-01-01 to near real time are available, and updated on a monthly basis.</li> </ul> <li> <strong>Labels can change over time</strong> </li> <ul> <li>The label assigned to a structure is the greatest predicted label averaged across time. As we get more data, the label may change, and more accurately predict the true infrastructure type.</li> </ul> <li><strong>Global datasets aren’t perfect</strong></li> <ul> <li>We’ve done our best to create the most accurate product possible, but there will be infrastructure that isn’t detected, or has been classified incorrectly. This will be most evident when working at the project level.</li> <li>We strongly encourage users to provide feedback to the research team so that we may improve future versions of the model. All feedback is greatly appreciated.</li> </ul> </ul> <h2>Methods</h2> <h3>SAR imagery</h3> <p>We use SAR imagery from the Copernicus Sentinel-1 mission of the European Space Agency (ESA) [1]. The images are sourced from two satellites (S1A and S1B up until December 2021 when S1B stopped operating, and S1A only from 2022 onward) that orbit 180 degrees out of phase with each other in a polar, sun-synchronous orbit. Each satellite has a repeat-cycle of 12 days, so that together they provide a global mapping of coastal waters around the world approximately every six days for the period that both were operating. The number of images per location, however, varies greatly depending on mission priorities, latitude, and degree of overlap between adjacent satellite passes. Spatial coverage also varies over time [2]. Our data consist of dual-polarization images (VH and VV) from the Interferometric Wide (IW) swath mode, with a resolution of about 20 m.</p> <p>[1] <a target=\"_blank\" href=\"https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf\"> <span style=\"color:rgb(0, 0, 0);\">https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf</span> </a> </p> <p>[2]<a target=\"_blank\" href=\"https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario\"> <span style=\"color:rgb(0, 0, 0);\"></span> <span style=\"color:rgb(0, 0, 0);\">https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario</span> </a> </p> <h3>Infrastructure detection by SAR</h3> <p>Detecting infrastructure with SAR is based on the widely used Constant False Alarm Rate (CFAR) algorithm, an anomaly detection method conceived for detecting ships in synthetic aperture radar images, that has been modified to remove non-stationary objects. This algorithm is designed to search for pixel values that are unusually bright (the targets) compared to those in the surrounding area (the sea clutter). This method sets a threshold based on the pixel values of the local background (within a window), scanning the whole image pixel-by-pixel. Pixel values above the threshold constitute an anomaly and are likely to be samples from a target.</p> <h3>Infrastructure classification</h3> <p>To classify every detected offshore infrastructure, we used deep learning and designed a ConvNet based on the ConvNeXt architecture. A novel aspect of our deep learning classification approach is the combination of SAR imagery from Sentinel-1 with optical imagery from Sentinel-2. From six-month composites of dual-band SAR (VH and VV) and four-band optical (RGB and NIR) images, we extracted small tiles for every detected fixed infrastructure, with the respective objects at the center of the tile. A single model output includes the probabilities for the specified classes: wind, oil, unknown, lake maracaibo, and noise.</p> <h3>Filtering</h3> <p>GFW post-processed the classified SAR detections to reduce noise (false positives), remove vessels, exclude areas with sea ice at high latitudes, and incorporate expert feedback. We used a clustering approach to identify detections across time (within a 50 m radius) that were likely the same structure but their coordinates differed slightly, and assigned them the greatest average predicted label of the cluster. We also filled in gaps for fixed structures that were missing in one timestep but detected in the previous and following timesteps, and dropped detections appearing in a single timestep. Finally, the dataset underwent extensive manual review and editing by researchers and industry experts in order to refine the final product, and provide the most accurate dataset possible.</p> <h3>Data field descriptions</h3> <p>Each detection has a unique individual identifier (<em>detection_id</em>). A six-month image composite is used in the classification, therefore the <em>detection_date</em> represents the middle of the six month period. This helps to remove non-stationary objects (i.e. vessels), and avoid confusion in the model if a structure is being built, or there isn’t adequate imagery available. <em>structure_id</em> allows you to track a structure through time. There are therefore many <em>detection_id</em> (one for each month the structure is detected) for each <em>structure_id</em>. Labels of <em>wind</em> and <em>oil </em>represent any wind or oil related structure respectively. <em>Unknown</em> represents a structure that is not oil or wind related, such as bridges or navigational buoys. </p> <p>Label confidence levels of ‘High’. ‘Medium’ and ‘Low’ are assigned to each structure, and are conditional on where the detections fell in relation to the boundaries of manually developed wind and oil polygons, and whether the label has changed from the previous month. The <em>label_confidence</em> field can be used to filter analysis. </p> <h2>Resources, code and other notes</h2> <p>Two repos are used in the automation process, both of which are private, and should not be shared publicly.</p> <p>Detection and classification: https://github.com/GlobalFishingWatch/sentinel-1-ee/tree/master</p> <p>Clustering and reclassification: https://github.com/GlobalFishingWatch/infrastructure-post-processing</p> <p>All code developed for the paper, Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity.</p> <h2>Sources data and citations</h2> <p>Copernicus Sentinel data 2017-current</p> <p>Lujala, Päivi; Jan Ketil Rød &amp; Nadia Thieme, 2007. 'Fighting over Oil: Introducing A New Dataset', Conflict Management and Peace Science 24(3), 239-256</p> <p>Sabbatino, M., Romeo, L., Baker, V., Bauer, J., Barkhurst, A., Bean, A., DiGiulio, J., Jones, K., Jones, T.J., Justman, D., Miller III, R., Rose, K., and Tong., A., Global Oil &amp; Gas Infrastructure Features Database Geocube Collection, 2019-03-25, https://edx.netl.doe.gov/dataset/global-oil-gas-infrastructure-features-database-geocube-collection, DOI: 10.18141/1502839</p> <h2>License</h2> <p>Non-Commercial Use Only. The Site and the Services are provided for Non-Commercial use only in accordance with the CC BY-NC 4.0 license. If you would like to use the Site and/or the Services for commercial purposes, please contact us.</p> <h2>Global Fishing Watch metadata</h2> <p>Infrastructure development methods should reference the paper:</p> <p>Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8</p> <p>All code developed for the paper, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity. All the data generated and used by these scripts can reference the following data repos:</p> <p>Analysis and Figures: https://doi.org/10.6084/m9.figshare.24309475</p> <p>Training and Evaluation: https://doi.org/10.6084/m9.figshare.24309469</p>",
+    "schema": {
+      "label": {
+        "keyword": "label",
+        "enum": {
+          "oil": "oil",
+          "wind": "wind",
+          "unknown": "unknown"
+        }
+      },
+      "structure_id": "structure_id",
+      "label_confidence": {
+        "keyword": "label_confidence",
+        "enum": {
+          "high": "high",
+          "low": "low",
+          "medium": "medium"
+        }
+      },
+      "structure_end_date": "structure_end_date",
+      "structure_start_date": "structure_start_date"
+    }
+  },
   "public-global-all-tracks": {
     "name": "Trajectoires",
     "description": "The dataset contains the tracks from all vessels (AIS) - Version 20231026"
@@ -1088,20 +1120,17 @@
   },
   "public-global-encounters-events": {
     "name": "Événements de rencontre (AIS)",
-    "description": "The dataset contains encounter events for AIS.",
+    "description": "Identified from AIS data as locations where two vessels, a carrier and fishing vessel, were within 500 meters for at least 2 hours and traveling at a median speed under 2 knots, while at least 10 km from a coastal anchorage.",
     "schema": {
-      "duration": {
-        "keyword": "durée",
-        "enum": {
-          "120": "120",
-          "4320": "4320"
-        }
-      }
+      "duration": "duration"
     }
   },
   "public-global-fishing-effort": {
     "name": "AIS",
-    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as known or possible commercial fishing vessels, and applies a fishing presence algorithm to determine “apparent fishing activity” based on changes in vessel speed and direction. The algorithm classifies each AIS broadcast data point for these vessels as either apparently fishing or not fishing and shows the former on the Global Fishing Watch fishing activity heat map. AIS data as broadcast may vary in completeness, accuracy and quality. Also, data collection by satellite or terrestrial receivers may introduce errors through missing or inaccurate data. Global Fishing Watch’s fishing presence algorithm is a best effort mathematically to identify “apparent fishing activity.” As a result, it is possible that some fishing activity is not identified as such by Global Fishing Watch; conversely, Global Fishing Watch may show apparent fishing activity where fishing is not actually taking place. For these reasons, Global Fishing Watch qualifies designations of vessel fishing activity, including synonyms of the term “fishing activity,” such as “fishing” or “fishing effort,” as “apparent,” rather than certain. Any/all Global Fishing Watch information about “apparent fishing activity” should be considered an estimate and must be relied upon solely at your own risk. Global Fishing Watch is taking steps to make sure fishing activity designations are as accurate as possible. Global Fishing Watch fishing presence algorithms are developed and tested using actual fishing event data collected by observers, combined with expert analysis of vessel movement data resulting in the manual classification of thousands of known fishing events. Global Fishing Watch also collaborates extensively with academic researchers through our research program to share fishing activity classification data and automated classification techniques."
+    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as known or possible commercial fishing vessels, and applies a fishing presence algorithm to determine “apparent fishing activity” based on changes in vessel speed and direction. The algorithm classifies each AIS broadcast data point for these vessels as either apparently fishing or not fishing and shows the former on the Global Fishing Watch fishing activity heat map. AIS data as broadcast may vary in completeness, accuracy and quality. Also, data collection by satellite or terrestrial receivers may introduce errors through missing or inaccurate data. Global Fishing Watch’s fishing presence algorithm is a best effort mathematically to identify “apparent fishing activity.” As a result, it is possible that some fishing activity is not identified as such by Global Fishing Watch; conversely, Global Fishing Watch may show apparent fishing activity where fishing is not actually taking place. For these reasons, Global Fishing Watch qualifies designations of vessel fishing activity, including synonyms of the term “fishing activity,” such as “fishing” or “fishing effort,” as “apparent,” rather than certain. Any/all Global Fishing Watch information about “apparent fishing activity” should be considered an estimate and must be relied upon solely at your own risk. Global Fishing Watch is taking steps to make sure fishing activity designations are as accurate as possible. Global Fishing Watch fishing presence algorithms are developed and tested using actual fishing event data collected by observers, combined with expert analysis of vessel movement data resulting in the manual classification of thousands of known fishing events. Global Fishing Watch also collaborates extensively with academic researchers through our research program to share fishing activity classification data and automated classification techniques.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-fishing-vessels": {
     "name": "AIS (Fishing Vessels)",
@@ -1147,7 +1176,10 @@
   },
   "public-global-presence": {
     "name": "AIS",
-    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as carriers. The activity layer displays a heatmap of vessel presence. The presence is determined by taking one position per day per vessel from the positions transmitted by the vessel's AIS."
+    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as carriers. The activity layer displays a heatmap of vessel presence. The presence is determined by taking one position per day per vessel from the positions transmitted by the vessel's AIS.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-salinity": {
     "name": "Salinité",
@@ -1229,6 +1261,10 @@
     "name": "Hauteur de houle",
     "description": "<h2>Sommaire</h2>\n<ul>\n<li>La hauteur de houle est la distance verticale entre le creux (bas) et la crête (haut) d'une vague à la surface de la mer. Ce jeu de données utilise la hauteur de houle significative, qui est la moyenne du tiers le plus élevé de toutes les hauteurs de houle sur une période d'échantillonnage donnée.</li>\n<ul>\n<h2>La Source</h2>\n<ul>\n <a href='https://www.pacioos.hawaii.edu/metadata/ww3_global.html'>Cheung, K.F. 2010, updated 2021. WaveWatch III (WW3) Global Wave Model. Distributed by the Pacific Islands Ocean Observing System (PacIOOS), which is a part of the U.S. Integrated Ocean Observing System (IOOS®), funded in part by National Oceanic and Atmospheric Administration (NOAA) Awards #NA16NOS0120024 and #NA21NOS0120091.</a></li>"
   },
+  "public-global-tracks": {
+    "name": "Tracks",
+    "description": "The dataset contains the tracks from all vessels (AIS) - Version 3.0"
+  },
   "public-global-vessel-identity": {
     "name": "AIS (all vessel types)",
     "description": "Vessel Identity (all shiptypes)"
@@ -1238,14 +1274,31 @@
     "description": "Vessel Insights from AIS"
   },
   "public-global-viirs-presence": {
-    "name": "VIIRS",
+    "name": "Night light detections (VIIRS)",
     "description": "The night lights vessel detections layer, known as visible infrared imaging radiometer suite or VIIRS, shows vessels at sea that satellites have detected by the light they emit at night. Though not exclusively associated with fishing vessels, this activity layer is likely to show vessels associated with activities like squid fishing, which use bright lights and fish at night.The satellite makes a single over-pass across the entire planet every night, detecting lights not obscured by clouds and designed to give at least one observation globally every day. Because the vessels are detected solely based on light emission, we can detect individual vessels and even entire fishing fleets that are not broadcasting automatic identification system (AIS) and so are not represented in the AIS apparent fishing effort layer. Lights from fixed offshore infrastructure and other non-vessel sources are excluded. Global Fishing Watch ingests boat detections processed from low light imaging data collected by the U.S. National Oceanic and Atmospheric Administration (NOAA) VIIRS. The boat detections are processed in near-real time by NOAA’s Earth Observation Group, located in Boulder, Colorado. The data, known as VIIRS boat detections, picks up the presence of fishing vessels using lights to attract catch or to conduct operations at night. More than 85% of the detections are from vessels that lack AIS or Vessel Monitoring System (VMS) transponders. Due to the orbit design of polar orbiting satellites, regions closer to polar will have more over-passes per day, while equatorial regions have only one over-pass daily. Read more about this product, and download the data <a href=\"https://ngdc.noaa.gov/eog/viirs/download_boat.html\" target=\"_blank\" rel=\"noopener\">here</a>.Those using night light detections data should acknowledge the South Atlantic Anomaly (SAA), an area where the Earth's inner Van Allen radiation belt is at its lowest altitude, allowing more energetic particles from space to penetrate. When such particles hit the sensors on a satellite, this can create a false signal which might cause the algorithm to recognize it as a boat presence. A filtration algorithm has been applied but there may still be some mis-identification. The GFW layer includes quality flags (QF), including a filter to show only detections which NOAA has classified as vessels (QF1)",
     "schema": {
+      "bearing": "bearing",
+      "matched": {
+        "keyword": "matched",
+        "enum": {
+          "true": "true",
+          "false": "false"
+        }
+      },
       "radiance": {
         "keyword": "radiance",
         "enum": {
-          "1": "1",
-          "1000": "1000"
+          "0": "0",
+          "10000": "10000"
+        }
+      },
+      "shiptype": {
+        "keyword": "shiptype",
+        "enum": {
+          "unknown": "unknown",
+          "fishing": "fishing",
+          "carrier": "carrier",
+          "support": "support"
         }
       },
       "qf_detect": {

package/id/datasets.json

@@ -618,6 +618,13 @@
       "bearing": "bearing"
     }
   },
+  "proto-global-encounters-events-30min": {
+    "name": "PROTOTYPE - Encounter Events of 30min. (AIS)",
+    "description": "The dataset contains encounter events of 30min for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]",
+    "schema": {
+      "duration": "duration"
+    }
+  },
   "proto-global-encounters-events": {
     "name": "Encounter Events. (AIS)",
     "description": "The dataset contains encounter events with authorizations for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]"
@@ -1051,6 +1058,31 @@
       "structure_start_date": "structure_start_date"
     }
   },
+  "public-fixed-infrastructure-filtered": {
+    "name": "Offshore Fixed Infrastructure (SAR, Optical)",
+    "description": "<h2>Overview</h2> <p>Offshore fixed infrastructure is a global dataset that uses AI and machine learning to detect and classify structures throughout the world’s oceans.</p> <p>Classification labels (oil, wind, and unknown) are provided, as well as confidence levels (high, medium, or low) reflecting our certainty in the assigned label. Detections can be filtered and colored on the map using both label and confidence level.<em></em>The data is updated on a monthly basis, and new classified detections are added at the beginning of every month. Viewing change using the timebar is simple, and allows anyone to recognize the rapid industrialization of the world’s oceans. For example, you can easily observe the expansion of wind farms in the North and East China Seas, or changes in oil infrastructure in the Gulf of Mexico or Persian Gulf.</p> <p>By overlaying the existing map layers, you can explore how vessels interact with oil and wind structures, visualise the density of synthetic aperture radar (SAR) and Visible Infrared Imaging Radiometer Suite (VIIRS) vessel detections around infrastructure, or determine which marine protected areas (MPAs) contain wind, oil, or other infrastructure types. These are only examples of the types of questions we can now ask. Offshore fixed infrastructure is a first of its kind dataset that not only brings to light the extensive industrialization of our oceans, but enables users across industries to use this information in research, monitoring and management.</p> <h2>Use cases</h2> <ul> <li>Maritime domain awareness</li> <ul> <li>Infrastructure locations can support maritime domain awareness, and understanding of other activities occurring at sea.</li> <li>Infrastructure data supports assessments of ocean industrialization, facilitating monitoring of areas experiencing build-up or new development</li> </ul> <li>Monitoring vessels</li> <ul> <li>Infrastructure locations can be used to analyse the behaviour of vessels associated with infrastructure, including grouping vessels based on their interaction with oil and wind structures.</li> <li>Interactions between vessels and infrastructure can help quantify the resources required to support offshore industrial activity</li> <li>The impacts of infrastructure on fishing, including attracting or deterring fishing, can be analysed.</li> </ul> <li>Marine protected areas (MPAs) and marine spatial planning</li> <ul> <li>During the planning stage in the designation of new protected areas, knowing the location of existing infrastructure will be vital to understand which stakeholders shall be included in the consultation process, to understand potential conflicts, and identify easy wins.</li> </ul> <li>Environmental impacts</li> <ul> <li>Infrastructure locations can be used to help detect marine pollution events, and to differentiate between types of pollution events (e.g. pollution from vessels versus pollution from platforms)</li> </ul> </ul> <h2>Caveats</h2> <ul> <li><strong>Sentinel-1 and Sentinel-2 satellites do not sample most of the open ocean.</strong></li> <ul> <li>Most industrial activity happens relatively close to shore.</li> <li>The extent and frequency of SAR acquisitions is determined by the mission priorities.</li> <li>For more info see: https://www.nature.com/articles/s41586-023-06825-8/figures/5</li> </ul> <li><strong>We do not provide detections of infrastructure within 1 km of shore</strong></li> <ul> <li>We do not classify objects within 1 km of shore because it is difficult to map where the shoreline begins, and ambiguous coastlines and rocks cause false positives.</li> <li>The bulk of industrial activities, including offshore development with medium-to-large oil rigs and wind farms, occur several kilometers from shore.</li> </ul> <li> <strong>False positives can be produced from noise artifacts.</strong> </li> <ul> <li>Rocks, small islands, sea ice, radar ambiguities (radar echoes), and image artifacts can cause false positives</li> <li>Detections in some areas including Southern Chile, the Arctic, and the Norwegian Sea have been filtered to remove noise.</li> </ul> <li><strong>Spatial coverage varies over time, which can produce different detections results year on year - <a target=\"_blank\" href=\"https://share.cleanshot.com/yG0qfF\"> <span style=\"color:rgb(0, 0, 0);\">Example</span> </a></strong> </li> <ul> <li>Infrastructure detentions from 2017-01-01 to near real time are available, and updated on a monthly basis.</li> </ul> <li> <strong>Labels can change over time</strong> </li> <ul> <li>The label assigned to a structure is the greatest predicted label averaged across time. As we get more data, the label may change, and more accurately predict the true infrastructure type.</li> </ul> <li><strong>Global datasets aren’t perfect</strong></li> <ul> <li>We’ve done our best to create the most accurate product possible, but there will be infrastructure that isn’t detected, or has been classified incorrectly. This will be most evident when working at the project level.</li> <li>We strongly encourage users to provide feedback to the research team so that we may improve future versions of the model. All feedback is greatly appreciated.</li> </ul> </ul> <h2>Methods</h2> <h3>SAR imagery</h3> <p>We use SAR imagery from the Copernicus Sentinel-1 mission of the European Space Agency (ESA) [1]. The images are sourced from two satellites (S1A and S1B up until December 2021 when S1B stopped operating, and S1A only from 2022 onward) that orbit 180 degrees out of phase with each other in a polar, sun-synchronous orbit. Each satellite has a repeat-cycle of 12 days, so that together they provide a global mapping of coastal waters around the world approximately every six days for the period that both were operating. The number of images per location, however, varies greatly depending on mission priorities, latitude, and degree of overlap between adjacent satellite passes. Spatial coverage also varies over time [2]. Our data consist of dual-polarization images (VH and VV) from the Interferometric Wide (IW) swath mode, with a resolution of about 20 m.</p> <p>[1] <a target=\"_blank\" href=\"https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf\"> <span style=\"color:rgb(0, 0, 0);\">https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf</span> </a> </p> <p>[2]<a target=\"_blank\" href=\"https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario\"> <span style=\"color:rgb(0, 0, 0);\"></span> <span style=\"color:rgb(0, 0, 0);\">https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario</span> </a> </p> <h3>Infrastructure detection by SAR</h3> <p>Detecting infrastructure with SAR is based on the widely used Constant False Alarm Rate (CFAR) algorithm, an anomaly detection method conceived for detecting ships in synthetic aperture radar images, that has been modified to remove non-stationary objects. This algorithm is designed to search for pixel values that are unusually bright (the targets) compared to those in the surrounding area (the sea clutter). This method sets a threshold based on the pixel values of the local background (within a window), scanning the whole image pixel-by-pixel. Pixel values above the threshold constitute an anomaly and are likely to be samples from a target.</p> <h3>Infrastructure classification</h3> <p>To classify every detected offshore infrastructure, we used deep learning and designed a ConvNet based on the ConvNeXt architecture. A novel aspect of our deep learning classification approach is the combination of SAR imagery from Sentinel-1 with optical imagery from Sentinel-2. From six-month composites of dual-band SAR (VH and VV) and four-band optical (RGB and NIR) images, we extracted small tiles for every detected fixed infrastructure, with the respective objects at the center of the tile. A single model output includes the probabilities for the specified classes: wind, oil, unknown, lake maracaibo, and noise.</p> <h3>Filtering</h3> <p>GFW post-processed the classified SAR detections to reduce noise (false positives), remove vessels, exclude areas with sea ice at high latitudes, and incorporate expert feedback. We used a clustering approach to identify detections across time (within a 50 m radius) that were likely the same structure but their coordinates differed slightly, and assigned them the greatest average predicted label of the cluster. We also filled in gaps for fixed structures that were missing in one timestep but detected in the previous and following timesteps, and dropped detections appearing in a single timestep. Finally, the dataset underwent extensive manual review and editing by researchers and industry experts in order to refine the final product, and provide the most accurate dataset possible.</p> <h3>Data field descriptions</h3> <p>Each detection has a unique individual identifier (<em>detection_id</em>). A six-month image composite is used in the classification, therefore the <em>detection_date</em> represents the middle of the six month period. This helps to remove non-stationary objects (i.e. vessels), and avoid confusion in the model if a structure is being built, or there isn’t adequate imagery available. <em>structure_id</em> allows you to track a structure through time. There are therefore many <em>detection_id</em> (one for each month the structure is detected) for each <em>structure_id</em>. Labels of <em>wind</em> and <em>oil </em>represent any wind or oil related structure respectively. <em>Unknown</em> represents a structure that is not oil or wind related, such as bridges or navigational buoys. </p> <p>Label confidence levels of ‘High’. ‘Medium’ and ‘Low’ are assigned to each structure, and are conditional on where the detections fell in relation to the boundaries of manually developed wind and oil polygons, and whether the label has changed from the previous month. The <em>label_confidence</em> field can be used to filter analysis. </p> <h2>Resources, code and other notes</h2> <p>Two repos are used in the automation process, both of which are private, and should not be shared publicly.</p> <p>Detection and classification: https://github.com/GlobalFishingWatch/sentinel-1-ee/tree/master</p> <p>Clustering and reclassification: https://github.com/GlobalFishingWatch/infrastructure-post-processing</p> <p>All code developed for the paper, Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity.</p> <h2>Sources data and citations</h2> <p>Copernicus Sentinel data 2017-current</p> <p>Lujala, Päivi; Jan Ketil Rød &amp; Nadia Thieme, 2007. 'Fighting over Oil: Introducing A New Dataset', Conflict Management and Peace Science 24(3), 239-256</p> <p>Sabbatino, M., Romeo, L., Baker, V., Bauer, J., Barkhurst, A., Bean, A., DiGiulio, J., Jones, K., Jones, T.J., Justman, D., Miller III, R., Rose, K., and Tong., A., Global Oil &amp; Gas Infrastructure Features Database Geocube Collection, 2019-03-25, https://edx.netl.doe.gov/dataset/global-oil-gas-infrastructure-features-database-geocube-collection, DOI: 10.18141/1502839</p> <h2>License</h2> <p>Non-Commercial Use Only. The Site and the Services are provided for Non-Commercial use only in accordance with the CC BY-NC 4.0 license. If you would like to use the Site and/or the Services for commercial purposes, please contact us.</p> <h2>Global Fishing Watch metadata</h2> <p>Infrastructure development methods should reference the paper:</p> <p>Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8</p> <p>All code developed for the paper, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity. All the data generated and used by these scripts can reference the following data repos:</p> <p>Analysis and Figures: https://doi.org/10.6084/m9.figshare.24309475</p> <p>Training and Evaluation: https://doi.org/10.6084/m9.figshare.24309469</p>",
+    "schema": {
+      "label": {
+        "keyword": "label",
+        "enum": {
+          "oil": "oil",
+          "wind": "wind",
+          "unknown": "unknown"
+        }
+      },
+      "structure_id": "structure_id",
+      "label_confidence": {
+        "keyword": "label_confidence",
+        "enum": {
+          "high": "high",
+          "low": "low",
+          "medium": "medium"
+        }
+      },
+      "structure_end_date": "structure_end_date",
+      "structure_start_date": "structure_start_date"
+    }
+  },
   "public-global-all-tracks": {
     "name": "Lintasan",
     "description": "The dataset contains the tracks from all vessels (AIS) - Version 20231026"
@@ -1088,20 +1120,17 @@
   },
   "public-global-encounters-events": {
     "name": "Encounter Events. (AIS)",
-    "description": "The dataset contains encounter events for AIS.",
+    "description": "Identified from AIS data as locations where two vessels, a carrier and fishing vessel, were within 500 meters for at least 2 hours and traveling at a median speed under 2 knots, while at least 10 km from a coastal anchorage.",
     "schema": {
-      "duration": {
-        "keyword": "durasi",
-        "enum": {
-          "120": "120",
-          "4320": "4320"
-        }
-      }
+      "duration": "duration"
     }
   },
   "public-global-fishing-effort": {
     "name": "AIS",
-    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as known or possible commercial fishing vessels, and applies a fishing presence algorithm to determine “apparent fishing activity” based on changes in vessel speed and direction. The algorithm classifies each AIS broadcast data point for these vessels as either apparently fishing or not fishing and shows the former on the Global Fishing Watch fishing activity heat map. AIS data as broadcast may vary in completeness, accuracy and quality. Also, data collection by satellite or terrestrial receivers may introduce errors through missing or inaccurate data. Global Fishing Watch’s fishing presence algorithm is a best effort mathematically to identify “apparent fishing activity.” As a result, it is possible that some fishing activity is not identified as such by Global Fishing Watch; conversely, Global Fishing Watch may show apparent fishing activity where fishing is not actually taking place. For these reasons, Global Fishing Watch qualifies designations of vessel fishing activity, including synonyms of the term “fishing activity,” such as “fishing” or “fishing effort,” as “apparent,” rather than certain. Any/all Global Fishing Watch information about “apparent fishing activity” should be considered an estimate and must be relied upon solely at your own risk. Global Fishing Watch is taking steps to make sure fishing activity designations are as accurate as possible. Global Fishing Watch fishing presence algorithms are developed and tested using actual fishing event data collected by observers, combined with expert analysis of vessel movement data resulting in the manual classification of thousands of known fishing events. Global Fishing Watch also collaborates extensively with academic researchers through our research program to share fishing activity classification data and automated classification techniques."
+    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as known or possible commercial fishing vessels, and applies a fishing presence algorithm to determine “apparent fishing activity” based on changes in vessel speed and direction. The algorithm classifies each AIS broadcast data point for these vessels as either apparently fishing or not fishing and shows the former on the Global Fishing Watch fishing activity heat map. AIS data as broadcast may vary in completeness, accuracy and quality. Also, data collection by satellite or terrestrial receivers may introduce errors through missing or inaccurate data. Global Fishing Watch’s fishing presence algorithm is a best effort mathematically to identify “apparent fishing activity.” As a result, it is possible that some fishing activity is not identified as such by Global Fishing Watch; conversely, Global Fishing Watch may show apparent fishing activity where fishing is not actually taking place. For these reasons, Global Fishing Watch qualifies designations of vessel fishing activity, including synonyms of the term “fishing activity,” such as “fishing” or “fishing effort,” as “apparent,” rather than certain. Any/all Global Fishing Watch information about “apparent fishing activity” should be considered an estimate and must be relied upon solely at your own risk. Global Fishing Watch is taking steps to make sure fishing activity designations are as accurate as possible. Global Fishing Watch fishing presence algorithms are developed and tested using actual fishing event data collected by observers, combined with expert analysis of vessel movement data resulting in the manual classification of thousands of known fishing events. Global Fishing Watch also collaborates extensively with academic researchers through our research program to share fishing activity classification data and automated classification techniques.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-fishing-vessels": {
     "name": "AIS (Fishing Vessels)",
@@ -1147,7 +1176,10 @@
   },
   "public-global-presence": {
     "name": "AIS",
-    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as carriers. The activity layer displays a heatmap of vessel presence. The presence is determined by taking one position per day per vessel from the positions transmitted by the vessel's AIS."
+    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as carriers. The activity layer displays a heatmap of vessel presence. The presence is determined by taking one position per day per vessel from the positions transmitted by the vessel's AIS.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-salinity": {
     "name": "Kadar garam",
@@ -1229,6 +1261,10 @@
     "name": "Tinggi gelombang",
     "description": "<h2>Overview</h2>\n<ul>\n<li>Wave height is the vertical distance from the trough (bottom) to the crest (top) of a wave on the sea surface. This dataset uses the significant wave height, which is the average of the highest one-third of all wave heights over a given sample period.</li>\n<ul>\n<h2>Source</h2>\n<ul>\n <a href='https://www.pacioos.hawaii.edu/metadata/ww3_global.html'>Cheung, K.F. 2010, updated 2021. WaveWatch III (WW3) Global Wave Model. Distributed by the Pacific Islands Ocean Observing System (PacIOOS), which is a part of the U.S. Integrated Ocean Observing System (IOOS®), funded in part by National Oceanic and Atmospheric Administration (NOAA) Awards #NA16NOS0120024 and #NA21NOS0120091.</a></li>"
   },
+  "public-global-tracks": {
+    "name": "Tracks",
+    "description": "The dataset contains the tracks from all vessels (AIS) - Version 3.0"
+  },
   "public-global-vessel-identity": {
     "name": "AIS (all vessel types)",
     "description": "Vessel Identity (all shiptypes)"
@@ -1238,14 +1274,31 @@
     "description": "Vessel Insights from AIS"
   },
   "public-global-viirs-presence": {
-    "name": "VIIRS",
+    "name": "Night light detections (VIIRS)",
     "description": "The night lights vessel detections layer, known as visible infrared imaging radiometer suite or VIIRS, shows vessels at sea that satellites have detected by the light they emit at night. Though not exclusively associated with fishing vessels, this activity layer is likely to show vessels associated with activities like squid fishing, which use bright lights and fish at night.The satellite makes a single over-pass across the entire planet every night, detecting lights not obscured by clouds and designed to give at least one observation globally every day. Because the vessels are detected solely based on light emission, we can detect individual vessels and even entire fishing fleets that are not broadcasting automatic identification system (AIS) and so are not represented in the AIS apparent fishing effort layer. Lights from fixed offshore infrastructure and other non-vessel sources are excluded. Global Fishing Watch ingests boat detections processed from low light imaging data collected by the U.S. National Oceanic and Atmospheric Administration (NOAA) VIIRS. The boat detections are processed in near-real time by NOAA’s Earth Observation Group, located in Boulder, Colorado. The data, known as VIIRS boat detections, picks up the presence of fishing vessels using lights to attract catch or to conduct operations at night. More than 85% of the detections are from vessels that lack AIS or Vessel Monitoring System (VMS) transponders. Due to the orbit design of polar orbiting satellites, regions closer to polar will have more over-passes per day, while equatorial regions have only one over-pass daily. Read more about this product, and download the data <a href=\"https://ngdc.noaa.gov/eog/viirs/download_boat.html\" target=\"_blank\" rel=\"noopener\">here</a>.Those using night light detections data should acknowledge the South Atlantic Anomaly (SAA), an area where the Earth's inner Van Allen radiation belt is at its lowest altitude, allowing more energetic particles from space to penetrate. When such particles hit the sensors on a satellite, this can create a false signal which might cause the algorithm to recognize it as a boat presence. A filtration algorithm has been applied but there may still be some mis-identification. The GFW layer includes quality flags (QF), including a filter to show only detections which NOAA has classified as vessels (QF1)",
     "schema": {
+      "bearing": "bearing",
+      "matched": {
+        "keyword": "matched",
+        "enum": {
+          "true": "true",
+          "false": "false"
+        }
+      },
       "radiance": {
         "keyword": "radiance",
         "enum": {
-          "1": "1",
-          "1000": "1000"
+          "0": "0",
+          "10000": "10000"
+        }
+      },
+      "shiptype": {
+        "keyword": "shiptype",
+        "enum": {
+          "unknown": "unknown",
+          "fishing": "fishing",
+          "carrier": "carrier",
+          "support": "support"
         }
       },
       "qf_detect": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@globalfishingwatch/i18n-labels",
-  "version": "1.2.194",
+  "version": "1.2.196",
   "main": "./index.cjs.js",
   "module": "./index.mjs",
   "typings": "./index.d.ts",

package/pt/datasets.json

@@ -618,6 +618,13 @@
       "bearing": "bearing"
     }
   },
+  "proto-global-encounters-events-30min": {
+    "name": "PROTOTYPE - Encounter Events of 30min. (AIS)",
+    "description": "The dataset contains encounter events of 30min for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]",
+    "schema": {
+      "duration": "duration"
+    }
+  },
   "proto-global-encounters-events": {
     "name": "Encounter Events. (AIS)",
     "description": "The dataset contains encounter events with authorizations for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]"
@@ -1051,6 +1058,31 @@
       "structure_start_date": "structure_start_date"
     }
   },
+  "public-fixed-infrastructure-filtered": {
+    "name": "Offshore Fixed Infrastructure (SAR, Optical)",
+    "description": "<h2>Overview</h2> <p>Offshore fixed infrastructure is a global dataset that uses AI and machine learning to detect and classify structures throughout the world’s oceans.</p> <p>Classification labels (oil, wind, and unknown) are provided, as well as confidence levels (high, medium, or low) reflecting our certainty in the assigned label. Detections can be filtered and colored on the map using both label and confidence level.<em></em>The data is updated on a monthly basis, and new classified detections are added at the beginning of every month. Viewing change using the timebar is simple, and allows anyone to recognize the rapid industrialization of the world’s oceans. For example, you can easily observe the expansion of wind farms in the North and East China Seas, or changes in oil infrastructure in the Gulf of Mexico or Persian Gulf.</p> <p>By overlaying the existing map layers, you can explore how vessels interact with oil and wind structures, visualise the density of synthetic aperture radar (SAR) and Visible Infrared Imaging Radiometer Suite (VIIRS) vessel detections around infrastructure, or determine which marine protected areas (MPAs) contain wind, oil, or other infrastructure types. These are only examples of the types of questions we can now ask. Offshore fixed infrastructure is a first of its kind dataset that not only brings to light the extensive industrialization of our oceans, but enables users across industries to use this information in research, monitoring and management.</p> <h2>Use cases</h2> <ul> <li>Maritime domain awareness</li> <ul> <li>Infrastructure locations can support maritime domain awareness, and understanding of other activities occurring at sea.</li> <li>Infrastructure data supports assessments of ocean industrialization, facilitating monitoring of areas experiencing build-up or new development</li> </ul> <li>Monitoring vessels</li> <ul> <li>Infrastructure locations can be used to analyse the behaviour of vessels associated with infrastructure, including grouping vessels based on their interaction with oil and wind structures.</li> <li>Interactions between vessels and infrastructure can help quantify the resources required to support offshore industrial activity</li> <li>The impacts of infrastructure on fishing, including attracting or deterring fishing, can be analysed.</li> </ul> <li>Marine protected areas (MPAs) and marine spatial planning</li> <ul> <li>During the planning stage in the designation of new protected areas, knowing the location of existing infrastructure will be vital to understand which stakeholders shall be included in the consultation process, to understand potential conflicts, and identify easy wins.</li> </ul> <li>Environmental impacts</li> <ul> <li>Infrastructure locations can be used to help detect marine pollution events, and to differentiate between types of pollution events (e.g. pollution from vessels versus pollution from platforms)</li> </ul> </ul> <h2>Caveats</h2> <ul> <li><strong>Sentinel-1 and Sentinel-2 satellites do not sample most of the open ocean.</strong></li> <ul> <li>Most industrial activity happens relatively close to shore.</li> <li>The extent and frequency of SAR acquisitions is determined by the mission priorities.</li> <li>For more info see: https://www.nature.com/articles/s41586-023-06825-8/figures/5</li> </ul> <li><strong>We do not provide detections of infrastructure within 1 km of shore</strong></li> <ul> <li>We do not classify objects within 1 km of shore because it is difficult to map where the shoreline begins, and ambiguous coastlines and rocks cause false positives.</li> <li>The bulk of industrial activities, including offshore development with medium-to-large oil rigs and wind farms, occur several kilometers from shore.</li> </ul> <li> <strong>False positives can be produced from noise artifacts.</strong> </li> <ul> <li>Rocks, small islands, sea ice, radar ambiguities (radar echoes), and image artifacts can cause false positives</li> <li>Detections in some areas including Southern Chile, the Arctic, and the Norwegian Sea have been filtered to remove noise.</li> </ul> <li><strong>Spatial coverage varies over time, which can produce different detections results year on year - <a target=\"_blank\" href=\"https://share.cleanshot.com/yG0qfF\"> <span style=\"color:rgb(0, 0, 0);\">Example</span> </a></strong> </li> <ul> <li>Infrastructure detentions from 2017-01-01 to near real time are available, and updated on a monthly basis.</li> </ul> <li> <strong>Labels can change over time</strong> </li> <ul> <li>The label assigned to a structure is the greatest predicted label averaged across time. As we get more data, the label may change, and more accurately predict the true infrastructure type.</li> </ul> <li><strong>Global datasets aren’t perfect</strong></li> <ul> <li>We’ve done our best to create the most accurate product possible, but there will be infrastructure that isn’t detected, or has been classified incorrectly. This will be most evident when working at the project level.</li> <li>We strongly encourage users to provide feedback to the research team so that we may improve future versions of the model. All feedback is greatly appreciated.</li> </ul> </ul> <h2>Methods</h2> <h3>SAR imagery</h3> <p>We use SAR imagery from the Copernicus Sentinel-1 mission of the European Space Agency (ESA) [1]. The images are sourced from two satellites (S1A and S1B up until December 2021 when S1B stopped operating, and S1A only from 2022 onward) that orbit 180 degrees out of phase with each other in a polar, sun-synchronous orbit. Each satellite has a repeat-cycle of 12 days, so that together they provide a global mapping of coastal waters around the world approximately every six days for the period that both were operating. The number of images per location, however, varies greatly depending on mission priorities, latitude, and degree of overlap between adjacent satellite passes. Spatial coverage also varies over time [2]. Our data consist of dual-polarization images (VH and VV) from the Interferometric Wide (IW) swath mode, with a resolution of about 20 m.</p> <p>[1] <a target=\"_blank\" href=\"https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf\"> <span style=\"color:rgb(0, 0, 0);\">https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf</span> </a> </p> <p>[2]<a target=\"_blank\" href=\"https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario\"> <span style=\"color:rgb(0, 0, 0);\"></span> <span style=\"color:rgb(0, 0, 0);\">https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario</span> </a> </p> <h3>Infrastructure detection by SAR</h3> <p>Detecting infrastructure with SAR is based on the widely used Constant False Alarm Rate (CFAR) algorithm, an anomaly detection method conceived for detecting ships in synthetic aperture radar images, that has been modified to remove non-stationary objects. This algorithm is designed to search for pixel values that are unusually bright (the targets) compared to those in the surrounding area (the sea clutter). This method sets a threshold based on the pixel values of the local background (within a window), scanning the whole image pixel-by-pixel. Pixel values above the threshold constitute an anomaly and are likely to be samples from a target.</p> <h3>Infrastructure classification</h3> <p>To classify every detected offshore infrastructure, we used deep learning and designed a ConvNet based on the ConvNeXt architecture. A novel aspect of our deep learning classification approach is the combination of SAR imagery from Sentinel-1 with optical imagery from Sentinel-2. From six-month composites of dual-band SAR (VH and VV) and four-band optical (RGB and NIR) images, we extracted small tiles for every detected fixed infrastructure, with the respective objects at the center of the tile. A single model output includes the probabilities for the specified classes: wind, oil, unknown, lake maracaibo, and noise.</p> <h3>Filtering</h3> <p>GFW post-processed the classified SAR detections to reduce noise (false positives), remove vessels, exclude areas with sea ice at high latitudes, and incorporate expert feedback. We used a clustering approach to identify detections across time (within a 50 m radius) that were likely the same structure but their coordinates differed slightly, and assigned them the greatest average predicted label of the cluster. We also filled in gaps for fixed structures that were missing in one timestep but detected in the previous and following timesteps, and dropped detections appearing in a single timestep. Finally, the dataset underwent extensive manual review and editing by researchers and industry experts in order to refine the final product, and provide the most accurate dataset possible.</p> <h3>Data field descriptions</h3> <p>Each detection has a unique individual identifier (<em>detection_id</em>). A six-month image composite is used in the classification, therefore the <em>detection_date</em> represents the middle of the six month period. This helps to remove non-stationary objects (i.e. vessels), and avoid confusion in the model if a structure is being built, or there isn’t adequate imagery available. <em>structure_id</em> allows you to track a structure through time. There are therefore many <em>detection_id</em> (one for each month the structure is detected) for each <em>structure_id</em>. Labels of <em>wind</em> and <em>oil </em>represent any wind or oil related structure respectively. <em>Unknown</em> represents a structure that is not oil or wind related, such as bridges or navigational buoys. </p> <p>Label confidence levels of ‘High’. ‘Medium’ and ‘Low’ are assigned to each structure, and are conditional on where the detections fell in relation to the boundaries of manually developed wind and oil polygons, and whether the label has changed from the previous month. The <em>label_confidence</em> field can be used to filter analysis. </p> <h2>Resources, code and other notes</h2> <p>Two repos are used in the automation process, both of which are private, and should not be shared publicly.</p> <p>Detection and classification: https://github.com/GlobalFishingWatch/sentinel-1-ee/tree/master</p> <p>Clustering and reclassification: https://github.com/GlobalFishingWatch/infrastructure-post-processing</p> <p>All code developed for the paper, Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity.</p> <h2>Sources data and citations</h2> <p>Copernicus Sentinel data 2017-current</p> <p>Lujala, Päivi; Jan Ketil Rød &amp; Nadia Thieme, 2007. 'Fighting over Oil: Introducing A New Dataset', Conflict Management and Peace Science 24(3), 239-256</p> <p>Sabbatino, M., Romeo, L., Baker, V., Bauer, J., Barkhurst, A., Bean, A., DiGiulio, J., Jones, K., Jones, T.J., Justman, D., Miller III, R., Rose, K., and Tong., A., Global Oil &amp; Gas Infrastructure Features Database Geocube Collection, 2019-03-25, https://edx.netl.doe.gov/dataset/global-oil-gas-infrastructure-features-database-geocube-collection, DOI: 10.18141/1502839</p> <h2>License</h2> <p>Non-Commercial Use Only. The Site and the Services are provided for Non-Commercial use only in accordance with the CC BY-NC 4.0 license. If you would like to use the Site and/or the Services for commercial purposes, please contact us.</p> <h2>Global Fishing Watch metadata</h2> <p>Infrastructure development methods should reference the paper:</p> <p>Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8</p> <p>All code developed for the paper, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity. All the data generated and used by these scripts can reference the following data repos:</p> <p>Analysis and Figures: https://doi.org/10.6084/m9.figshare.24309475</p> <p>Training and Evaluation: https://doi.org/10.6084/m9.figshare.24309469</p>",
+    "schema": {
+      "label": {
+        "keyword": "label",
+        "enum": {
+          "oil": "oil",
+          "wind": "wind",
+          "unknown": "unknown"
+        }
+      },
+      "structure_id": "structure_id",
+      "label_confidence": {
+        "keyword": "label_confidence",
+        "enum": {
+          "high": "high",
+          "low": "low",
+          "medium": "medium"
+        }
+      },
+      "structure_end_date": "structure_end_date",
+      "structure_start_date": "structure_start_date"
+    }
+  },
   "public-global-all-tracks": {
     "name": "Rotas",
     "description": "The dataset contains the tracks from all vessels (AIS) - Version 20231026"
@@ -1088,20 +1120,17 @@
   },
   "public-global-encounters-events": {
     "name": "Encounter Events. (AIS)",
-    "description": "The dataset contains encounter events for AIS.",
+    "description": "Identified from AIS data as locations where two vessels, a carrier and fishing vessel, were within 500 meters for at least 2 hours and traveling at a median speed under 2 knots, while at least 10 km from a coastal anchorage.",
     "schema": {
-      "duration": {
-        "keyword": "duração",
-        "enum": {
-          "120": "120",
-          "4320": "4320"
-        }
-      }
+      "duration": "duration"
     }
   },
   "public-global-fishing-effort": {
     "name": "AIS",
-    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as known or possible commercial fishing vessels, and applies a fishing presence algorithm to determine “apparent fishing activity” based on changes in vessel speed and direction. The algorithm classifies each AIS broadcast data point for these vessels as either apparently fishing or not fishing and shows the former on the Global Fishing Watch fishing activity heat map. AIS data as broadcast may vary in completeness, accuracy and quality. Also, data collection by satellite or terrestrial receivers may introduce errors through missing or inaccurate data. Global Fishing Watch’s fishing presence algorithm is a best effort mathematically to identify “apparent fishing activity.” As a result, it is possible that some fishing activity is not identified as such by Global Fishing Watch; conversely, Global Fishing Watch may show apparent fishing activity where fishing is not actually taking place. For these reasons, Global Fishing Watch qualifies designations of vessel fishing activity, including synonyms of the term “fishing activity,” such as “fishing” or “fishing effort,” as “apparent,” rather than certain. Any/all Global Fishing Watch information about “apparent fishing activity” should be considered an estimate and must be relied upon solely at your own risk. Global Fishing Watch is taking steps to make sure fishing activity designations are as accurate as possible. Global Fishing Watch fishing presence algorithms are developed and tested using actual fishing event data collected by observers, combined with expert analysis of vessel movement data resulting in the manual classification of thousands of known fishing events. Global Fishing Watch also collaborates extensively with academic researchers through our research program to share fishing activity classification data and automated classification techniques."
+    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as known or possible commercial fishing vessels, and applies a fishing presence algorithm to determine “apparent fishing activity” based on changes in vessel speed and direction. The algorithm classifies each AIS broadcast data point for these vessels as either apparently fishing or not fishing and shows the former on the Global Fishing Watch fishing activity heat map. AIS data as broadcast may vary in completeness, accuracy and quality. Also, data collection by satellite or terrestrial receivers may introduce errors through missing or inaccurate data. Global Fishing Watch’s fishing presence algorithm is a best effort mathematically to identify “apparent fishing activity.” As a result, it is possible that some fishing activity is not identified as such by Global Fishing Watch; conversely, Global Fishing Watch may show apparent fishing activity where fishing is not actually taking place. For these reasons, Global Fishing Watch qualifies designations of vessel fishing activity, including synonyms of the term “fishing activity,” such as “fishing” or “fishing effort,” as “apparent,” rather than certain. Any/all Global Fishing Watch information about “apparent fishing activity” should be considered an estimate and must be relied upon solely at your own risk. Global Fishing Watch is taking steps to make sure fishing activity designations are as accurate as possible. Global Fishing Watch fishing presence algorithms are developed and tested using actual fishing event data collected by observers, combined with expert analysis of vessel movement data resulting in the manual classification of thousands of known fishing events. Global Fishing Watch also collaborates extensively with academic researchers through our research program to share fishing activity classification data and automated classification techniques.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-fishing-vessels": {
     "name": "AIS (Fishing Vessels)",
@@ -1147,7 +1176,10 @@
   },
   "public-global-presence": {
     "name": "AIS",
-    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as carriers. The activity layer displays a heatmap of vessel presence. The presence is determined by taking one position per day per vessel from the positions transmitted by the vessel's AIS."
+    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as carriers. The activity layer displays a heatmap of vessel presence. The presence is determined by taking one position per day per vessel from the positions transmitted by the vessel's AIS.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-salinity": {
     "name": "Salinidade",
@@ -1229,6 +1261,10 @@
     "name": "Altura da onda",
     "description": "<h2>Visão geral</h2>\n<ul>\n<li>A altura da onda é a distância vertical do vale (fundo) até a crista (topo) de uma onda na superfície do mar. Este conjunto de dados usa a altura significativa da onda, que é a média do terço mais alto de todas as alturas das ondas durante um determinado período de amostragem.</li>\n<ul>\n<h2>Fonte</h2>\n<ul>\n <a href='https://www.pacioos.hawaii.edu/metadata/ww3_global.html'>Cheung, K.F. 2010, updated 2021. WaveWatch III (WW3) Global Wave Model. Distributed by the Pacific Islands Ocean Observing System (PacIOOS), which is a part of the U.S. Integrated Ocean Observing System (IOOS®), funded in part by National Oceanic and Atmospheric Administration (NOAA) Awards #NA16NOS0120024 and #NA21NOS0120091.</a></li>"
   },
+  "public-global-tracks": {
+    "name": "Tracks",
+    "description": "The dataset contains the tracks from all vessels (AIS) - Version 3.0"
+  },
   "public-global-vessel-identity": {
     "name": "AIS (all vessel types)",
     "description": "Vessel Identity (all shiptypes)"
@@ -1238,14 +1274,31 @@
     "description": "Vessel Indicadores from AIS"
   },
   "public-global-viirs-presence": {
-    "name": "VIIRS",
+    "name": "Night light detections (VIIRS)",
     "description": "The night lights vessel detections layer, known as visible infrared imaging radiometer suite or VIIRS, shows vessels at sea that satellites have detected by the light they emit at night. Though not exclusively associated with fishing vessels, this activity layer is likely to show vessels associated with activities like squid fishing, which use bright lights and fish at night.The satellite makes a single over-pass across the entire planet every night, detecting lights not obscured by clouds and designed to give at least one observation globally every day. Because the vessels are detected solely based on light emission, we can detect individual vessels and even entire fishing fleets that are not broadcasting automatic identification system (AIS) and so are not represented in the AIS apparent fishing effort layer. Lights from fixed offshore infrastructure and other non-vessel sources are excluded. Global Fishing Watch ingests boat detections processed from low light imaging data collected by the U.S. National Oceanic and Atmospheric Administration (NOAA) VIIRS. The boat detections are processed in near-real time by NOAA’s Earth Observation Group, located in Boulder, Colorado. The data, known as VIIRS boat detections, picks up the presence of fishing vessels using lights to attract catch or to conduct operations at night. More than 85% of the detections are from vessels that lack AIS or Vessel Monitoring System (VMS) transponders. Due to the orbit design of polar orbiting satellites, regions closer to polar will have more over-passes per day, while equatorial regions have only one over-pass daily. Read more about this product, and download the data <a href=\"https://ngdc.noaa.gov/eog/viirs/download_boat.html\" target=\"_blank\" rel=\"noopener\">here</a>.Those using night light detections data should acknowledge the South Atlantic Anomaly (SAA), an area where the Earth's inner Van Allen radiation belt is at its lowest altitude, allowing more energetic particles from space to penetrate. When such particles hit the sensors on a satellite, this can create a false signal which might cause the algorithm to recognize it as a boat presence. A filtration algorithm has been applied but there may still be some mis-identification. The GFW layer includes quality flags (QF), including a filter to show only detections which NOAA has classified as vessels (QF1)",
     "schema": {
+      "bearing": "bearing",
+      "matched": {
+        "keyword": "matched",
+        "enum": {
+          "true": "true",
+          "false": "false"
+        }
+      },
       "radiance": {
         "keyword": "radiance",
         "enum": {
-          "1": "1",
-          "1000": "1000"
+          "0": "0",
+          "10000": "10000"
+        }
+      },
+      "shiptype": {
+        "keyword": "shiptype",
+        "enum": {
+          "unknown": "unknown",
+          "fishing": "fishing",
+          "carrier": "carrier",
+          "support": "support"
         }
       },
       "qf_detect": {

package/source/datasets.json

@@ -618,6 +618,13 @@
       "bearing": "bearing"
     }
   },
+  "proto-global-encounters-events-30min": {
+    "name": "PROTOTYPE - Encounter Events of 30min. (AIS)",
+    "description": "The dataset contains encounter events of 30min for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]",
+    "schema": {
+      "duration": "duration"
+    }
+  },
   "proto-global-encounters-events": {
     "name": "Encounter Events. (AIS)",
     "description": "The dataset contains encounter events with authorizations for AIS. [Fishing-Carriers, Carriers-Fishing, Support-Fishing, Fishing-Support]"
@@ -1051,6 +1058,31 @@
       "structure_start_date": "structure_start_date"
     }
   },
+  "public-fixed-infrastructure-filtered": {
+    "name": "Offshore Fixed Infrastructure (SAR, Optical)",
+    "description": "<h2>Overview</h2> <p>Offshore fixed infrastructure is a global dataset that uses AI and machine learning to detect and classify structures throughout the world’s oceans.</p> <p>Classification labels (oil, wind, and unknown) are provided, as well as confidence levels (high, medium, or low) reflecting our certainty in the assigned label. Detections can be filtered and colored on the map using both label and confidence level.<em></em>The data is updated on a monthly basis, and new classified detections are added at the beginning of every month. Viewing change using the timebar is simple, and allows anyone to recognize the rapid industrialization of the world’s oceans. For example, you can easily observe the expansion of wind farms in the North and East China Seas, or changes in oil infrastructure in the Gulf of Mexico or Persian Gulf.</p> <p>By overlaying the existing map layers, you can explore how vessels interact with oil and wind structures, visualise the density of synthetic aperture radar (SAR) and Visible Infrared Imaging Radiometer Suite (VIIRS) vessel detections around infrastructure, or determine which marine protected areas (MPAs) contain wind, oil, or other infrastructure types. These are only examples of the types of questions we can now ask. Offshore fixed infrastructure is a first of its kind dataset that not only brings to light the extensive industrialization of our oceans, but enables users across industries to use this information in research, monitoring and management.</p> <h2>Use cases</h2> <ul> <li>Maritime domain awareness</li> <ul> <li>Infrastructure locations can support maritime domain awareness, and understanding of other activities occurring at sea.</li> <li>Infrastructure data supports assessments of ocean industrialization, facilitating monitoring of areas experiencing build-up or new development</li> </ul> <li>Monitoring vessels</li> <ul> <li>Infrastructure locations can be used to analyse the behaviour of vessels associated with infrastructure, including grouping vessels based on their interaction with oil and wind structures.</li> <li>Interactions between vessels and infrastructure can help quantify the resources required to support offshore industrial activity</li> <li>The impacts of infrastructure on fishing, including attracting or deterring fishing, can be analysed.</li> </ul> <li>Marine protected areas (MPAs) and marine spatial planning</li> <ul> <li>During the planning stage in the designation of new protected areas, knowing the location of existing infrastructure will be vital to understand which stakeholders shall be included in the consultation process, to understand potential conflicts, and identify easy wins.</li> </ul> <li>Environmental impacts</li> <ul> <li>Infrastructure locations can be used to help detect marine pollution events, and to differentiate between types of pollution events (e.g. pollution from vessels versus pollution from platforms)</li> </ul> </ul> <h2>Caveats</h2> <ul> <li><strong>Sentinel-1 and Sentinel-2 satellites do not sample most of the open ocean.</strong></li> <ul> <li>Most industrial activity happens relatively close to shore.</li> <li>The extent and frequency of SAR acquisitions is determined by the mission priorities.</li> <li>For more info see: https://www.nature.com/articles/s41586-023-06825-8/figures/5</li> </ul> <li><strong>We do not provide detections of infrastructure within 1 km of shore</strong></li> <ul> <li>We do not classify objects within 1 km of shore because it is difficult to map where the shoreline begins, and ambiguous coastlines and rocks cause false positives.</li> <li>The bulk of industrial activities, including offshore development with medium-to-large oil rigs and wind farms, occur several kilometers from shore.</li> </ul> <li> <strong>False positives can be produced from noise artifacts.</strong> </li> <ul> <li>Rocks, small islands, sea ice, radar ambiguities (radar echoes), and image artifacts can cause false positives</li> <li>Detections in some areas including Southern Chile, the Arctic, and the Norwegian Sea have been filtered to remove noise.</li> </ul> <li><strong>Spatial coverage varies over time, which can produce different detections results year on year - <a target=\"_blank\" href=\"https://share.cleanshot.com/yG0qfF\"> <span style=\"color:rgb(0, 0, 0);\">Example</span> </a></strong> </li> <ul> <li>Infrastructure detentions from 2017-01-01 to near real time are available, and updated on a monthly basis.</li> </ul> <li> <strong>Labels can change over time</strong> </li> <ul> <li>The label assigned to a structure is the greatest predicted label averaged across time. As we get more data, the label may change, and more accurately predict the true infrastructure type.</li> </ul> <li><strong>Global datasets aren’t perfect</strong></li> <ul> <li>We’ve done our best to create the most accurate product possible, but there will be infrastructure that isn’t detected, or has been classified incorrectly. This will be most evident when working at the project level.</li> <li>We strongly encourage users to provide feedback to the research team so that we may improve future versions of the model. All feedback is greatly appreciated.</li> </ul> </ul> <h2>Methods</h2> <h3>SAR imagery</h3> <p>We use SAR imagery from the Copernicus Sentinel-1 mission of the European Space Agency (ESA) [1]. The images are sourced from two satellites (S1A and S1B up until December 2021 when S1B stopped operating, and S1A only from 2022 onward) that orbit 180 degrees out of phase with each other in a polar, sun-synchronous orbit. Each satellite has a repeat-cycle of 12 days, so that together they provide a global mapping of coastal waters around the world approximately every six days for the period that both were operating. The number of images per location, however, varies greatly depending on mission priorities, latitude, and degree of overlap between adjacent satellite passes. Spatial coverage also varies over time [2]. Our data consist of dual-polarization images (VH and VV) from the Interferometric Wide (IW) swath mode, with a resolution of about 20 m.</p> <p>[1] <a target=\"_blank\" href=\"https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf\"> <span style=\"color:rgb(0, 0, 0);\">https://sedas.satapps.org/wp-content/uploads/2015/07/Sentinel-1_User_Handbook.pdf</span> </a> </p> <p>[2]<a target=\"_blank\" href=\"https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario\"> <span style=\"color:rgb(0, 0, 0);\"></span> <span style=\"color:rgb(0, 0, 0);\">https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1/observation-scenario</span> </a> </p> <h3>Infrastructure detection by SAR</h3> <p>Detecting infrastructure with SAR is based on the widely used Constant False Alarm Rate (CFAR) algorithm, an anomaly detection method conceived for detecting ships in synthetic aperture radar images, that has been modified to remove non-stationary objects. This algorithm is designed to search for pixel values that are unusually bright (the targets) compared to those in the surrounding area (the sea clutter). This method sets a threshold based on the pixel values of the local background (within a window), scanning the whole image pixel-by-pixel. Pixel values above the threshold constitute an anomaly and are likely to be samples from a target.</p> <h3>Infrastructure classification</h3> <p>To classify every detected offshore infrastructure, we used deep learning and designed a ConvNet based on the ConvNeXt architecture. A novel aspect of our deep learning classification approach is the combination of SAR imagery from Sentinel-1 with optical imagery from Sentinel-2. From six-month composites of dual-band SAR (VH and VV) and four-band optical (RGB and NIR) images, we extracted small tiles for every detected fixed infrastructure, with the respective objects at the center of the tile. A single model output includes the probabilities for the specified classes: wind, oil, unknown, lake maracaibo, and noise.</p> <h3>Filtering</h3> <p>GFW post-processed the classified SAR detections to reduce noise (false positives), remove vessels, exclude areas with sea ice at high latitudes, and incorporate expert feedback. We used a clustering approach to identify detections across time (within a 50 m radius) that were likely the same structure but their coordinates differed slightly, and assigned them the greatest average predicted label of the cluster. We also filled in gaps for fixed structures that were missing in one timestep but detected in the previous and following timesteps, and dropped detections appearing in a single timestep. Finally, the dataset underwent extensive manual review and editing by researchers and industry experts in order to refine the final product, and provide the most accurate dataset possible.</p> <h3>Data field descriptions</h3> <p>Each detection has a unique individual identifier (<em>detection_id</em>). A six-month image composite is used in the classification, therefore the <em>detection_date</em> represents the middle of the six month period. This helps to remove non-stationary objects (i.e. vessels), and avoid confusion in the model if a structure is being built, or there isn’t adequate imagery available. <em>structure_id</em> allows you to track a structure through time. There are therefore many <em>detection_id</em> (one for each month the structure is detected) for each <em>structure_id</em>. Labels of <em>wind</em> and <em>oil </em>represent any wind or oil related structure respectively. <em>Unknown</em> represents a structure that is not oil or wind related, such as bridges or navigational buoys. </p> <p>Label confidence levels of ‘High’. ‘Medium’ and ‘Low’ are assigned to each structure, and are conditional on where the detections fell in relation to the boundaries of manually developed wind and oil polygons, and whether the label has changed from the previous month. The <em>label_confidence</em> field can be used to filter analysis. </p> <h2>Resources, code and other notes</h2> <p>Two repos are used in the automation process, both of which are private, and should not be shared publicly.</p> <p>Detection and classification: https://github.com/GlobalFishingWatch/sentinel-1-ee/tree/master</p> <p>Clustering and reclassification: https://github.com/GlobalFishingWatch/infrastructure-post-processing</p> <p>All code developed for the paper, Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity.</p> <h2>Sources data and citations</h2> <p>Copernicus Sentinel data 2017-current</p> <p>Lujala, Päivi; Jan Ketil Rød &amp; Nadia Thieme, 2007. 'Fighting over Oil: Introducing A New Dataset', Conflict Management and Peace Science 24(3), 239-256</p> <p>Sabbatino, M., Romeo, L., Baker, V., Bauer, J., Barkhurst, A., Bean, A., DiGiulio, J., Jones, K., Jones, T.J., Justman, D., Miller III, R., Rose, K., and Tong., A., Global Oil &amp; Gas Infrastructure Features Database Geocube Collection, 2019-03-25, https://edx.netl.doe.gov/dataset/global-oil-gas-infrastructure-features-database-geocube-collection, DOI: 10.18141/1502839</p> <h2>License</h2> <p>Non-Commercial Use Only. The Site and the Services are provided for Non-Commercial use only in accordance with the CC BY-NC 4.0 license. If you would like to use the Site and/or the Services for commercial purposes, please contact us.</p> <h2>Global Fishing Watch metadata</h2> <p>Infrastructure development methods should reference the paper:</p> <p>Paolo, F.S., Kroodsma, D., Raynor, J. et al. Satellite mapping reveals extensive industrial activity at sea. Nature 625, 85–91 (2024). https://doi.org/10.1038/s41586-023-06825-8</p> <p>All code developed for the paper, including SAR detection, deep learning models, and analyses is open source and freely available at https://github.com/GlobalFishingWatch/paper-industrial-activity. All the data generated and used by these scripts can reference the following data repos:</p> <p>Analysis and Figures: https://doi.org/10.6084/m9.figshare.24309475</p> <p>Training and Evaluation: https://doi.org/10.6084/m9.figshare.24309469</p>",
+    "schema": {
+      "label": {
+        "keyword": "label",
+        "enum": {
+          "oil": "oil",
+          "wind": "wind",
+          "unknown": "unknown"
+        }
+      },
+      "structure_id": "structure_id",
+      "label_confidence": {
+        "keyword": "label_confidence",
+        "enum": {
+          "high": "high",
+          "low": "low",
+          "medium": "medium"
+        }
+      },
+      "structure_end_date": "structure_end_date",
+      "structure_start_date": "structure_start_date"
+    }
+  },
   "public-global-all-tracks": {
     "name": "Tracks",
     "description": "The dataset contains the tracks from all vessels (AIS) - Version 20231026"
@@ -1088,20 +1120,17 @@
   },
   "public-global-encounters-events": {
     "name": "Encounter Events. (AIS)",
-    "description": "The dataset contains encounter events for AIS.",
+    "description": "Identified from AIS data as locations where two vessels, a carrier and fishing vessel, were within 500 meters for at least 2 hours and traveling at a median speed under 2 knots, while at least 10 km from a coastal anchorage.",
     "schema": {
-      "duration": {
-        "keyword": "duration",
-        "enum": {
-          "120": "120",
-          "4320": "4320"
-        }
-      }
+      "duration": "duration"
     }
   },
   "public-global-fishing-effort": {
     "name": "AIS fishing bq",
-    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as known or possible commercial fishing vessels, and applies a fishing presence algorithm to determine “apparent fishing activity” based on changes in vessel speed and direction. The algorithm classifies each AIS broadcast data point for these vessels as either apparently fishing or not fishing and shows the former on the Global Fishing Watch fishing activity heat map. AIS data as broadcast may vary in completeness, accuracy and quality. Also, data collection by satellite or terrestrial receivers may introduce errors through missing or inaccurate data. Global Fishing Watch’s fishing presence algorithm is a best effort mathematically to identify “apparent fishing activity.” As a result, it is possible that some fishing activity is not identified as such by Global Fishing Watch; conversely, Global Fishing Watch may show apparent fishing activity where fishing is not actually taking place. For these reasons, Global Fishing Watch qualifies designations of vessel fishing activity, including synonyms of the term “fishing activity,” such as “fishing” or “fishing effort,” as “apparent,” rather than certain. Any/all Global Fishing Watch information about “apparent fishing activity” should be considered an estimate and must be relied upon solely at your own risk. Global Fishing Watch is taking steps to make sure fishing activity designations are as accurate as possible. Global Fishing Watch fishing presence algorithms are developed and tested using actual fishing event data collected by observers, combined with expert analysis of vessel movement data resulting in the manual classification of thousands of known fishing events. Global Fishing Watch also collaborates extensively with academic researchers through our research program to share fishing activity classification data and automated classification techniques."
+    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as known or possible commercial fishing vessels, and applies a fishing presence algorithm to determine “apparent fishing activity” based on changes in vessel speed and direction. The algorithm classifies each AIS broadcast data point for these vessels as either apparently fishing or not fishing and shows the former on the Global Fishing Watch fishing activity heat map. AIS data as broadcast may vary in completeness, accuracy and quality. Also, data collection by satellite or terrestrial receivers may introduce errors through missing or inaccurate data. Global Fishing Watch’s fishing presence algorithm is a best effort mathematically to identify “apparent fishing activity.” As a result, it is possible that some fishing activity is not identified as such by Global Fishing Watch; conversely, Global Fishing Watch may show apparent fishing activity where fishing is not actually taking place. For these reasons, Global Fishing Watch qualifies designations of vessel fishing activity, including synonyms of the term “fishing activity,” such as “fishing” or “fishing effort,” as “apparent,” rather than certain. Any/all Global Fishing Watch information about “apparent fishing activity” should be considered an estimate and must be relied upon solely at your own risk. Global Fishing Watch is taking steps to make sure fishing activity designations are as accurate as possible. Global Fishing Watch fishing presence algorithms are developed and tested using actual fishing event data collected by observers, combined with expert analysis of vessel movement data resulting in the manual classification of thousands of known fishing events. Global Fishing Watch also collaborates extensively with academic researchers through our research program to share fishing activity classification data and automated classification techniques.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-fishing-vessels": {
     "name": "AIS (Fishing Vessels)",
@@ -1147,7 +1176,10 @@
   },
   "public-global-presence": {
     "name": "AIS",
-    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as carriers. The activity layer displays a heatmap of vessel presence. The presence is determined by taking one position per day per vessel from the positions transmitted by the vessel's AIS."
+    "description": "Global Fishing Watch uses data about a vessel’s identity, type, location, speed, direction and more that is broadcast using the Automatic Identification System (AIS) and collected via satellites and terrestrial receivers. AIS was developed for safety/collision-avoidance. Global Fishing Watch analyzes AIS data collected from vessels that our research has identified as carriers. The activity layer displays a heatmap of vessel presence. The presence is determined by taking one position per day per vessel from the positions transmitted by the vessel's AIS.",
+    "schema": {
+      "bearing": "bearing"
+    }
   },
   "public-global-salinity": {
     "name": "Surface Salinity",
@@ -1229,6 +1261,10 @@
     "name": "Waves height",
     "description": "<h2>Overview</h2>\n<ul>\n<li>Wave height is the vertical distance from the trough (bottom) to the crest (top) of a wave on the sea surface. This dataset uses the significant wave height, which is the average of the highest one-third of all wave heights over a given sample period.</li>\n<ul>\n<h2>Source</h2>\n<ul>\n <a href='https://www.pacioos.hawaii.edu/metadata/ww3_global.html'>Cheung, K.F. 2010, updated 2021. WaveWatch III (WW3) Global Wave Model. Distributed by the Pacific Islands Ocean Observing System (PacIOOS), which is a part of the U.S. Integrated Ocean Observing System (IOOS®), funded in part by National Oceanic and Atmospheric Administration (NOAA) Awards #NA16NOS0120024 and #NA21NOS0120091.</a></li>"
   },
+  "public-global-tracks": {
+    "name": "Tracks",
+    "description": "The dataset contains the tracks from all vessels (AIS) - Version 3.0"
+  },
   "public-global-vessel-identity": {
     "name": "AIS (all vessel types)",
     "description": "Vessel Identity (all shiptypes)"
@@ -1238,14 +1274,31 @@
     "description": "Vessel Insights from AIS"
   },
   "public-global-viirs-presence": {
-    "name": "VIIRS",
+    "name": "Night light detections (VIIRS)",
     "description": "The night lights vessel detections layer, known as visible infrared imaging radiometer suite or VIIRS, shows vessels at sea that satellites have detected by the light they emit at night. Though not exclusively associated with fishing vessels, this activity layer is likely to show vessels associated with activities like squid fishing, which use bright lights and fish at night.The satellite makes a single over-pass across the entire planet every night, detecting lights not obscured by clouds and designed to give at least one observation globally every day. Because the vessels are detected solely based on light emission, we can detect individual vessels and even entire fishing fleets that are not broadcasting automatic identification system (AIS) and so are not represented in the AIS apparent fishing effort layer. Lights from fixed offshore infrastructure and other non-vessel sources are excluded. Global Fishing Watch ingests boat detections processed from low light imaging data collected by the U.S. National Oceanic and Atmospheric Administration (NOAA) VIIRS. The boat detections are processed in near-real time by NOAA’s Earth Observation Group, located in Boulder, Colorado. The data, known as VIIRS boat detections, picks up the presence of fishing vessels using lights to attract catch or to conduct operations at night. More than 85% of the detections are from vessels that lack AIS or Vessel Monitoring System (VMS) transponders. Due to the orbit design of polar orbiting satellites, regions closer to polar will have more over-passes per day, while equatorial regions have only one over-pass daily. Read more about this product, and download the data <a href=\"https://ngdc.noaa.gov/eog/viirs/download_boat.html\" target=\"_blank\" rel=\"noopener\">here</a>.Those using night light detections data should acknowledge the South Atlantic Anomaly (SAA), an area where the Earth's inner Van Allen radiation belt is at its lowest altitude, allowing more energetic particles from space to penetrate. When such particles hit the sensors on a satellite, this can create a false signal which might cause the algorithm to recognize it as a boat presence. A filtration algorithm has been applied but there may still be some mis-identification. The GFW layer includes quality flags (QF), including a filter to show only detections which NOAA has classified as vessels (QF1)",
     "schema": {
+      "bearing": "bearing",
+      "matched": {
+        "keyword": "matched",
+        "enum": {
+          "true": "true",
+          "false": "false"
+        }
+      },
       "radiance": {
         "keyword": "radiance",
         "enum": {
-          "1": "1",
-          "1000": "1000"
+          "0": "0",
+          "10000": "10000"
+        }
+      },
+      "shiptype": {
+        "keyword": "shiptype",
+        "enum": {
+          "unknown": "unknown",
+          "fishing": "fishing",
+          "carrier": "carrier",
+          "support": "support"
         }
       },
       "qf_detect": {

package/val/datasets.json

@@ -618,6 +618,13 @@
       "bearing": "crwdns83330:0crwdne83330:0"
     }
   },
+  "proto-global-encounters-events-30min": {
+    "name": "crwdns83426:0crwdne83426:0",
+    "description": "crwdns83428:0crwdne83428:0",
+    "schema": {
+      "duration": "crwdns83430:0crwdne83430:0"
+    }
+  },
   "proto-global-encounters-events": {
     "name": "crwdns65467:0crwdne65467:0",
     "description": "crwdns65469:0crwdne65469:0"
@@ -1051,6 +1058,31 @@
       "structure_start_date": "crwdns83302:0crwdne83302:0"
     }
   },
+  "public-fixed-infrastructure-filtered": {
+    "name": "crwdns83352:0crwdne83352:0",
+    "description": "crwdns83354:0crwdne83354:0",
+    "schema": {
+      "label": {
+        "keyword": "crwdns83356:0crwdne83356:0",
+        "enum": {
+          "oil": "crwdns83358:0crwdne83358:0",
+          "wind": "crwdns83360:0crwdne83360:0",
+          "unknown": "crwdns83362:0crwdne83362:0"
+        }
+      },
+      "structure_id": "crwdns83364:0crwdne83364:0",
+      "label_confidence": {
+        "keyword": "crwdns83366:0crwdne83366:0",
+        "enum": {
+          "high": "crwdns83368:0crwdne83368:0",
+          "low": "crwdns83370:0crwdne83370:0",
+          "medium": "crwdns83372:0crwdne83372:0"
+        }
+      },
+      "structure_end_date": "crwdns83374:0crwdne83374:0",
+      "structure_start_date": "crwdns83376:0crwdne83376:0"
+    }
+  },
   "public-global-all-tracks": {
     "name": "crwdns69888:0crwdne69888:0",
     "description": "crwdns69890:0crwdne69890:0"
@@ -1088,20 +1120,17 @@
   },
   "public-global-encounters-events": {
     "name": "crwdns66233:0crwdne66233:0",
-    "description": "crwdns69914:0crwdne69914:0",
+    "description": "crwdns83472:0crwdne83472:0",
     "schema": {
-      "duration": {
-        "keyword": "crwdns70220:0crwdne70220:0",
-        "enum": {
-          "120": "crwdns70222:0crwdne70222:0",
-          "4320": "crwdns70224:0crwdne70224:0"
-        }
-      }
+      "duration": "crwdns83434:0crwdne83434:0"
     }
   },
   "public-global-fishing-effort": {
     "name": "crwdns66257:0crwdne66257:0",
-    "description": "crwdns66259:0crwdne66259:0"
+    "description": "crwdns66259:0crwdne66259:0",
+    "schema": {
+      "bearing": "crwdns83436:0crwdne83436:0"
+    }
   },
   "public-global-fishing-vessels": {
     "name": "crwdns66305:0crwdne66305:0",
@@ -1147,7 +1176,10 @@
   },
   "public-global-presence": {
     "name": "crwdns66453:0crwdne66453:0",
-    "description": "crwdns66455:0crwdne66455:0"
+    "description": "crwdns66455:0crwdne66455:0",
+    "schema": {
+      "bearing": "crwdns83438:0crwdne83438:0"
+    }
   },
   "public-global-salinity": {
     "name": "crwdns83024:0crwdne83024:0",
@@ -1159,7 +1191,7 @@
   },
   "public-global-sar-presence": {
     "name": "crwdns69930:0crwdne69930:0",
-    "description": "crwdns70350:0crwdne70350:0",
+    "description": "crwdns83470:0crwdne83470:0",
     "schema": {
       "bearing": "crwdns83336:0crwdne83336:0",
       "matched": {
@@ -1229,6 +1261,10 @@
     "name": "crwdns83030:0crwdne83030:0",
     "description": "crwdns83032:0crwdne83032:0"
   },
+  "public-global-tracks": {
+    "name": "crwdns83442:0crwdne83442:0",
+    "description": "crwdns83444:0crwdne83444:0"
+  },
   "public-global-vessel-identity": {
     "name": "crwdns70132:0crwdne70132:0",
     "description": "crwdns70134:0crwdne70134:0"
@@ -1238,14 +1274,31 @@
     "description": "crwdns66549:0crwdne66549:0"
   },
   "public-global-viirs-presence": {
-    "name": "crwdns66563:0crwdne66563:0",
+    "name": "crwdns83474:0crwdne83474:0",
     "description": "crwdns66565:0crwdne66565:0",
     "schema": {
+      "bearing": "crwdns83448:0crwdne83448:0",
+      "matched": {
+        "keyword": "crwdns83450:0crwdne83450:0",
+        "enum": {
+          "true": "crwdns83452:0crwdne83452:0",
+          "false": "crwdns83454:0crwdne83454:0"
+        }
+      },
       "radiance": {
         "keyword": "crwdns66577:0crwdne66577:0",
         "enum": {
-          "1": "crwdns66579:0crwdne66579:0",
-          "1000": "crwdns66581:0crwdne66581:0"
+          "0": "crwdns83456:0crwdne83456:0",
+          "10000": "crwdns83458:0crwdne83458:0"
+        }
+      },
+      "shiptype": {
+        "keyword": "crwdns83460:0crwdne83460:0",
+        "enum": {
+          "unknown": "crwdns83462:0crwdne83462:0",
+          "fishing": "crwdns83464:0crwdne83464:0",
+          "carrier": "crwdns83466:0crwdne83466:0",
+          "support": "crwdns83468:0crwdne83468:0"
         }
       },
       "qf_detect": {