opticallyshallowdeep 1.2.0__tar.gz → 1.2.1__tar.gz

{opticallyshallowdeep-1.2.0/opticallyshallowdeep.egg-info → opticallyshallowdeep-1.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: opticallyshallowdeep
-Version: 1.2.0
+Version: 1.2.1
 Summary: Identify optically shallow and deep waters in satellite imagery
 Author: Yulun Wu
 Author-email: yulunwu8@gmail.com
@@ -23,7 +23,7 @@ Requires-Dist: tensorflow
 
 This python tool delineates optically shallow and deep waters in Sentinel-2 imagery. The tool uses a deep neural network (DNN) that was trained on a diverse set of global images.
 
-Supported input includes L1C SAFE files and ACOLITE-processed L2R netCDF files. The output geotiff contains probabilities of water pixels being optically shallow and deep. 
+Supported input includes Level-1C (L1C) SAFE files and ACOLITE-processed L2R netCDF files. The output geotiff contains probabilities of water pixels being optically shallow and deep. 
 
 Originally coded by by Galen Richardson and Anders Knudby, modified and packaged by Yulun Wu
 
@@ -47,7 +47,6 @@ For mac OS:
 ```bash
 conda install -c apple tensorflow-deps
 python -m pip install tensorflow-macos
-
 ```
 
 
@@ -55,14 +54,6 @@ For windows:
 
 ```bash
 pip3 install tensorflow==2.13.0
-
-```
-
-In case of compatibility issues, please try the newest version of tensorflow: 
-
-```bash
-pip3 install --upgrade --force-reinstall tensorflow
-
 ```
 
 
@@ -106,16 +97,23 @@ file_L2R = 'test_folder_in/L2R.nc'
 folder_out = 'folder/test_folder_out'
 
 # Run the OSW/ODW classifier 
-osd.run(file_in, folder_out, file_L2R=file_L2R)
+osd.run(file_L1C, folder_out, file_L2R=file_L2R)
 ```
 
-The L1C file is always required as it contains a cloud mask. Pixels within 8 pixels of the cloud mask are masked to reduce the impact of clouds. 
+The L1C file is always required as it contains a built-in cloud mask. Pixels within 8 pixels of the cloud mask are masked to reduce the impact of clouds. 
 
 
-Output is a 1-band geotiff, with values of prediction probability of OSW (100 means most likely OSW, 0 means most likely ODW). Non-water pixels are masked. It is recommended to use pixels between 0 and 40 as ODW, and pixels between 60 and 100 as OSW (publication in review).
+Output is a 1-band geotiff, with values of prediction probability of optically shallow water (OSW): 100 means most likely OSW, 0 means most likely optically deep water (ODW). Non-water pixels are masked. It is recommended to treat pixels between 0 and 40 as ODW, and pixels between 60 and 100 as OSW (publication in review).
 
 A log file, an intermediate multi-band geotiff, and a preview PNG are also generated in the output folder. They can be deleted after the processing. 
 
+
+**Sample Sentinel-2 scene and output:**
+
+<img src="images/TOA.jpeg"  height="500">
+
+<img src="images/OSW.jpeg"  height="500">
+
 ## Training, test, and validation data 
 
 All annotated shapefiles used in training, testing, and validating the DNN model are in the annotated_shapefiles folder, grouped by Sentinel-2 Scene ID.

{opticallyshallowdeep-1.2.0 → opticallyshallowdeep-1.2.1}/README.md

@@ -2,7 +2,7 @@
 
 This python tool delineates optically shallow and deep waters in Sentinel-2 imagery. The tool uses a deep neural network (DNN) that was trained on a diverse set of global images.
 
-Supported input includes L1C SAFE files and ACOLITE-processed L2R netCDF files. The output geotiff contains probabilities of water pixels being optically shallow and deep. 
+Supported input includes Level-1C (L1C) SAFE files and ACOLITE-processed L2R netCDF files. The output geotiff contains probabilities of water pixels being optically shallow and deep. 
 
 Originally coded by by Galen Richardson and Anders Knudby, modified and packaged by Yulun Wu
 
@@ -26,7 +26,6 @@ For mac OS:
 ```bash
 conda install -c apple tensorflow-deps
 python -m pip install tensorflow-macos
-
 ```
 
 
@@ -34,14 +33,6 @@ For windows:
 
 ```bash
 pip3 install tensorflow==2.13.0
-
-```
-
-In case of compatibility issues, please try the newest version of tensorflow: 
-
-```bash
-pip3 install --upgrade --force-reinstall tensorflow
-
 ```
 
 
@@ -85,16 +76,23 @@ file_L2R = 'test_folder_in/L2R.nc'
 folder_out = 'folder/test_folder_out'
 
 # Run the OSW/ODW classifier 
-osd.run(file_in, folder_out, file_L2R=file_L2R)
+osd.run(file_L1C, folder_out, file_L2R=file_L2R)
 ```
 
-The L1C file is always required as it contains a cloud mask. Pixels within 8 pixels of the cloud mask are masked to reduce the impact of clouds. 
+The L1C file is always required as it contains a built-in cloud mask. Pixels within 8 pixels of the cloud mask are masked to reduce the impact of clouds. 
 
 
-Output is a 1-band geotiff, with values of prediction probability of OSW (100 means most likely OSW, 0 means most likely ODW). Non-water pixels are masked. It is recommended to use pixels between 0 and 40 as ODW, and pixels between 60 and 100 as OSW (publication in review).
+Output is a 1-band geotiff, with values of prediction probability of optically shallow water (OSW): 100 means most likely OSW, 0 means most likely optically deep water (ODW). Non-water pixels are masked. It is recommended to treat pixels between 0 and 40 as ODW, and pixels between 60 and 100 as OSW (publication in review).
 
 A log file, an intermediate multi-band geotiff, and a preview PNG are also generated in the output folder. They can be deleted after the processing. 
 
+
+**Sample Sentinel-2 scene and output:**
+
+<img src="images/TOA.jpeg"  height="500">
+
+<img src="images/OSW.jpeg"  height="500">
+
 ## Training, test, and validation data 
 
 All annotated shapefiles used in training, testing, and validating the DNN model are in the annotated_shapefiles folder, grouped by Sentinel-2 Scene ID.

{opticallyshallowdeep-1.2.0 → opticallyshallowdeep-1.2.1}/opticallyshallowdeep/process_as_strips.py

@@ -179,13 +179,15 @@ def process_image_with_filters(img, selected_columns):
     for band, kernel_size, filter_type in filter_list:
         
         if filter_type is None:
-            filtered_band = img[:, :, band].astype(np.uint16)#this means it is a single pixel
+            filtered_band = img[:, :, band]
         else:
             with warnings.catch_warnings():
                 warnings.simplefilter("ignore", category=RuntimeWarning)
                 filtered_band = apply_filter(img[:, :, band].astype(np.float32), kernel_size, filter_type)
                 filtered_band[filtered_band==-32768] = 32768
-                filtered_band = filtered_band.astype(np.uint16)
+            
+        filtered_band[filtered_band<0] = 0
+        filtered_band = filtered_band.astype(np.uint16)#this means it is a single pixel
             
         output_bands.append(filtered_band)#append to list of filters
         del filtered_band

{opticallyshallowdeep-1.2.0 → opticallyshallowdeep-1.2.1}/opticallyshallowdeep/run.py

@@ -32,7 +32,11 @@ def run(file_L1C, folder_out, file_L2R = None, to_log=True):
         # Start logging in txt file
         orig_stdout = sys.stdout
         
-        log_base = os.path.basename(file_L1C).replace('.safe','.txt').replace('.SAFE','.txt')
+        if file_L2R is None: 
+            log_base = os.path.basename(file_L1C).replace('.safe','.txt').replace('.SAFE','.txt')
+        else:
+            log_base = os.path.basename(file_L2R).replace('.nc','.txt')
+        
         log_base = 'OSD_log_'+ log_base
         log_file = os.path.join(folder_out,log_base)
 

{opticallyshallowdeep-1.2.0 → opticallyshallowdeep-1.2.1/opticallyshallowdeep.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: opticallyshallowdeep
-Version: 1.2.0
+Version: 1.2.1
 Summary: Identify optically shallow and deep waters in satellite imagery
 Author: Yulun Wu
 Author-email: yulunwu8@gmail.com
@@ -23,7 +23,7 @@ Requires-Dist: tensorflow
 
 This python tool delineates optically shallow and deep waters in Sentinel-2 imagery. The tool uses a deep neural network (DNN) that was trained on a diverse set of global images.
 
-Supported input includes L1C SAFE files and ACOLITE-processed L2R netCDF files. The output geotiff contains probabilities of water pixels being optically shallow and deep. 
+Supported input includes Level-1C (L1C) SAFE files and ACOLITE-processed L2R netCDF files. The output geotiff contains probabilities of water pixels being optically shallow and deep. 
 
 Originally coded by by Galen Richardson and Anders Knudby, modified and packaged by Yulun Wu
 
@@ -47,7 +47,6 @@ For mac OS:
 ```bash
 conda install -c apple tensorflow-deps
 python -m pip install tensorflow-macos
-
 ```
 
 
@@ -55,14 +54,6 @@ For windows:
 
 ```bash
 pip3 install tensorflow==2.13.0
-
-```
-
-In case of compatibility issues, please try the newest version of tensorflow: 
-
-```bash
-pip3 install --upgrade --force-reinstall tensorflow
-
 ```
 
 
@@ -106,16 +97,23 @@ file_L2R = 'test_folder_in/L2R.nc'
 folder_out = 'folder/test_folder_out'
 
 # Run the OSW/ODW classifier 
-osd.run(file_in, folder_out, file_L2R=file_L2R)
+osd.run(file_L1C, folder_out, file_L2R=file_L2R)
 ```
 
-The L1C file is always required as it contains a cloud mask. Pixels within 8 pixels of the cloud mask are masked to reduce the impact of clouds. 
+The L1C file is always required as it contains a built-in cloud mask. Pixels within 8 pixels of the cloud mask are masked to reduce the impact of clouds. 
 
 
-Output is a 1-band geotiff, with values of prediction probability of OSW (100 means most likely OSW, 0 means most likely ODW). Non-water pixels are masked. It is recommended to use pixels between 0 and 40 as ODW, and pixels between 60 and 100 as OSW (publication in review).
+Output is a 1-band geotiff, with values of prediction probability of optically shallow water (OSW): 100 means most likely OSW, 0 means most likely optically deep water (ODW). Non-water pixels are masked. It is recommended to treat pixels between 0 and 40 as ODW, and pixels between 60 and 100 as OSW (publication in review).
 
 A log file, an intermediate multi-band geotiff, and a preview PNG are also generated in the output folder. They can be deleted after the processing. 
 
+
+**Sample Sentinel-2 scene and output:**
+
+<img src="images/TOA.jpeg"  height="500">
+
+<img src="images/OSW.jpeg"  height="500">
+
 ## Training, test, and validation data 
 
 All annotated shapefiles used in training, testing, and validating the DNN model are in the annotated_shapefiles folder, grouped by Sentinel-2 Scene ID.

{opticallyshallowdeep-1.2.0 → opticallyshallowdeep-1.2.1}/setup.py

@@ -5,7 +5,7 @@ with open("readme.md", "r") as fh:
 
 setup(
     name='opticallyshallowdeep',
-    version='1.2.0',
+    version='1.2.1',
     author='Yulun Wu',
     author_email='yulunwu8@gmail.com',
     description='Identify optically shallow and deep waters in satellite imagery',