eo-tides 0.0.21__tar.gz → 0.0.22__tar.gz

{eo_tides-0.0.21 → eo_tides-0.0.22}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: eo-tides
-Version: 0.0.21
+Version: 0.0.22
 Summary: Tide modelling tools for large-scale satellite earth observation analysis
 Author-email: Robbi Bishop-Taylor <Robbi.BishopTaylor@ga.gov.au>
 Project-URL: Homepage, https://GeoscienceAustralia.github.io/eo-tides/
@@ -22,23 +22,24 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: <4.0,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: colorama
-Requires-Dist: geopandas>=1.0.0
-Requires-Dist: numpy
-Requires-Dist: odc-geo
-Requires-Dist: pandas
-Requires-Dist: pyproj
+Requires-Dist: colorama>=0.4.3
+Requires-Dist: geopandas>=0.10.0
+Requires-Dist: matplotlib>=3.8.0
+Requires-Dist: numpy>=1.26.0
+Requires-Dist: odc-geo>=0.4.7
+Requires-Dist: pandas>=2.2.0
+Requires-Dist: pyproj>=3.6.1
 Requires-Dist: pyTMD==2.1.6
-Requires-Dist: scikit-learn
-Requires-Dist: scipy
-Requires-Dist: shapely
-Requires-Dist: tqdm
-Requires-Dist: xarray
+Requires-Dist: scikit-learn>=1.4.0
+Requires-Dist: scipy>=1.11.2
+Requires-Dist: shapely>=2.0.6
+Requires-Dist: tqdm>=4.55.0
+Requires-Dist: xarray>=2022.3.0
 Provides-Extra: notebooks
 Requires-Dist: odc-stac>=0.3.10; extra == "notebooks"
-Requires-Dist: pystac-client; extra == "notebooks"
-Requires-Dist: folium; extra == "notebooks"
-Requires-Dist: matplotlib; extra == "notebooks"
+Requires-Dist: pystac-client>=0.8.3; extra == "notebooks"
+Requires-Dist: folium>=0.16.0; extra == "notebooks"
+Requires-Dist: planetary_computer>=1.0.0; extra == "notebooks"
 
 # `eo-tides`: Tide modelling tools for large-scale satellite earth observation analysis
 

{eo_tides-0.0.21 → eo_tides-0.0.22}/eo_tides/model.py

@@ -243,7 +243,7 @@ def _model_tides(
             lon,
             lat,
             pytmd_model.model_file,
-            grid=pytmd_model.type,
+            grid=pytmd_model.file_format,
             crop=crop,
             bounds=bounds,
             method=method,
@@ -277,6 +277,10 @@ def _model_tides(
 
         # Delta time (TT - UT1)
         deltat = timescale.tt_ut1
+    else:
+        raise Exception(
+            f"Unsupported model format ({pytmd_model.format}). This may be due to an incompatible version of `pyTMD`."
+        )
 
     # Calculate complex phase in radians for Euler's
     cph = -1j * ph * np.pi / 180.0

{eo_tides-0.0.21 → eo_tides-0.0.22}/eo_tides/stats.py

@@ -26,8 +26,10 @@ def tide_stats(
     tidepost_lon: float | None = None,
     plain_english: bool = True,
     plot: bool = True,
+    plot_col: str | None = None,
     modelled_freq: str = "2h",
     linear_reg: bool = False,
+    min_max_q: tuple = (0.0, 1.0),
     round_stats: int = 3,
     **model_tides_kwargs,
 ) -> pd.Series:
@@ -73,6 +75,10 @@ def tide_stats(
         An optional boolean indicating whether to plot how satellite-
         observed tide heights compare against the full tidal range.
         Defaults to True.
+    plot_col : str, optional
+        Optional name of a coordinate, dimension or variable in the array
+        that will be used to plot observations with unique symbols.
+        Defaults to None, which will plot all observations as circles.
     modelled_freq : str, optional
         An optional string giving the frequency at which to model tides
         when computing the full modelled tidal range. Defaults to '2h',
@@ -84,6 +90,11 @@ def tide_stats(
         increasing trends over time. This may indicate whether your
         satellite data may produce misleading trends based on uneven
         sampling of the local tide regime.
+    min_max_q : tuple, optional
+        Quantiles used to calculate max and min observed and modelled
+        astronomical tides. By default `(0.0, 1.0)` which is equivalent
+        to minimum and maximum; to use a softer threshold that is more
+        robust to outliers, use e.g. `(0.1, 0.9)`.
     round_stats : int, optional
         The number of decimal places used to round the output statistics.
         Defaults to 3.
@@ -135,6 +146,7 @@ def tide_stats(
         return_tideposts=True,
         **model_tides_kwargs,
     )
+    ds_tides = ds_tides.sortby("time")
 
     # Drop spatial ref for nicer plotting
     ds_tides = ds_tides.drop_vars("spatial_ref")
@@ -160,8 +172,8 @@ def tide_stats(
     # Get coarse statistics on all and observed tidal ranges
     obs_mean = ds_tides.tide_height.mean().item()
     all_mean = all_tides_df.tide_height.mean()
-    obs_min, obs_max = ds_tides.tide_height.quantile([0.0, 1.0]).values
-    all_min, all_max = all_tides_df.tide_height.quantile([0.0, 1.0]).values
+    obs_min, obs_max = ds_tides.tide_height.quantile(min_max_q).values
+    all_min, all_max = all_tides_df.tide_height.quantile(min_max_q).values
 
     # Calculate tidal range
     obs_range = obs_max - obs_min
@@ -169,47 +181,89 @@ def tide_stats(
 
     # Calculate Bishop-Taylor et al. 2018 tidal metrics
     spread = obs_range / all_range
-    low_tide_offset = abs(all_min - obs_min) / all_range
-    high_tide_offset = abs(all_max - obs_max) / all_range
+    low_tide_offset_m = abs(all_min - obs_min)
+    high_tide_offset_m = abs(all_max - obs_max)
+    low_tide_offset = low_tide_offset_m / all_range
+    high_tide_offset = high_tide_offset_m / all_range
+
+    # Plain text descriptors
+    mean_diff = "higher" if obs_mean > all_mean else "lower"
+    mean_diff_icon = "⬆️" if obs_mean > all_mean else "⬇️"
+    spread_icon = "🟢" if spread >= 0.9 else "🟡" if 0.7 < spread <= 0.9 else "🔴"
+    low_tide_icon = "🟢" if low_tide_offset <= 0.1 else "🟡" if 0.1 <= low_tide_offset < 0.2 else "🔴"
+    high_tide_icon = "🟢" if high_tide_offset <= 0.1 else "🟡" if 0.1 <= high_tide_offset < 0.2 else "🔴"
 
     # Extract x (time in decimal years) and y (distance) values
     all_times = all_tides_df.index.get_level_values("time")
-    all_x = all_times.year + ((all_times.dayofyear - 1) / 365) + ((all_times.hour - 1) / 24)
+    all_x = all_times.year + ((all_times.dayofyear - 1) / 365) + ((all_times.hour) / 24)
     time_period = all_x.max() - all_x.min()
 
     # Extract x (time in decimal years) and y (distance) values
-    obs_x = ds_tides.time.dt.year + ((ds_tides.time.dt.dayofyear - 1) / 365) + ((ds_tides.time.dt.hour - 1) / 24)
+    obs_x = ds_tides.time.dt.year + ((ds_tides.time.dt.dayofyear - 1) / 365) + ((ds_tides.time.dt.hour) / 24)
     obs_y = ds_tides.tide_height.values.astype(np.float32)
 
     # Compute linear regression
     obs_linreg = stats.linregress(x=obs_x, y=obs_y)
 
+    # return obs_linreg
+
     if plain_english:
+        print(f"\n\n🌊 Modelled astronomical tide range: {all_range:.2f} metres.")
+        print(f"🛰️ Observed tide range: {obs_range:.2f} metres.\n")
+        print(f"    {spread_icon} {spread:.0%} of the modelled astronomical tide range was observed at this location.")
+        print(
+            f"    {high_tide_icon} The highest {high_tide_offset:.0%} ({high_tide_offset_m:.2f} metres) of the tide range was never observed."
+        )
         print(
-            f"\n{spread:.0%} of the {all_range:.2f} m modelled astronomical "
-            f"tidal range is observed at this location.\nThe lowest "
-            f"{low_tide_offset:.0%} and highest {high_tide_offset:.0%} "
-            f"of astronomical tides are never observed.\n"
+            f"    {low_tide_icon} The lowest {low_tide_offset:.0%} ({low_tide_offset_m:.2f} metres) of the tide range was never observed.\n"
+        )
+        print(f"🌊 Mean modelled astronomical tide height: {all_mean:.2f} metres.")
+        print(f"🛰️ Mean observed tide height: {obs_mean:.2f} metres.\n")
+        print(
+            f"    {mean_diff_icon} The mean observed tide height was {obs_mean - all_mean:.2f} metres {mean_diff} than the mean modelled astronomical tide height."
         )
 
         if linear_reg:
-            if obs_linreg.pvalue > 0.05:
-                print(f"Observed tides show no significant trends " f"over the ~{time_period:.0f} year period.")
+            if obs_linreg.pvalue > 0.01:
+                print("    ➖ Observed tides showed no significant trends over time.")
             else:
-                obs_slope_desc = "decrease" if obs_linreg.slope < 0 else "increase"
+                obs_slope_desc = "decreasing" if obs_linreg.slope < 0 else "increasing"
                 print(
-                    f"Observed tides {obs_slope_desc} significantly "
-                    f"(p={obs_linreg.pvalue:.3f}) over time by "
-                    f"{obs_linreg.slope:.03f} m per year (i.e. a "
-                    f"~{time_period * obs_linreg.slope:.2f} m "
-                    f"{obs_slope_desc} over the ~{time_period:.0f} year period)."
+                    f"    ⚠️ Observed tides showed a significant {obs_slope_desc} trend over time (p={obs_linreg.pvalue:.3f}, {obs_linreg.slope:.2f} metres per year)"
                 )
 
     if plot:
         # Create plot and add all time and observed tide data
-        fig, ax = plt.subplots(figsize=(10, 5))
-        all_tides_df.reset_index(["x", "y"]).tide_height.plot(ax=ax, alpha=0.4)
-        ds_tides.tide_height.plot.line(ax=ax, marker="o", linewidth=0.0, color="black", markersize=2)
+        fig, ax = plt.subplots(figsize=(10, 6))
+        all_tides_df.reset_index(["x", "y"]).tide_height.plot(ax=ax, alpha=0.4, label="Modelled tides")
+
+        # Look through custom column values if provided
+        if plot_col is not None:
+            # Create a list of marker styles
+            markers = ["o", "^", "s", "D", "v", "<", ">", "p", "*", "h", "H", "+", "x", "d", "|", "_"]
+            for i, value in enumerate(np.unique(ds_tides[plot_col])):
+                ds_tides.where(ds_tides[plot_col] == value, drop=True).tide_height.plot.line(
+                    ax=ax,
+                    linewidth=0.0,
+                    color="black",
+                    marker=markers[i % len(markers)],
+                    markersize=4,
+                    label=value,
+                )
+        # Otherwise, plot all data at once
+        else:
+            ds_tides.tide_height.plot.line(
+                ax=ax, marker="o", linewidth=0.0, color="black", markersize=3.5, label="Satellite observations"
+            )
+
+        ax.legend(loc="upper center", bbox_to_anchor=(0.5, 1.04), ncol=20, borderaxespad=0, frameon=False)
+
+        ax.plot(
+            ds_tides.time.isel(time=[0, -1]),
+            obs_linreg.intercept + obs_linreg.slope * obs_x[[0, -1]],
+            "r",
+            label="fitted line",
+        )
 
         # Add horizontal lines for spread/offsets
         ax.axhline(obs_min, color="black", linestyle=":", linewidth=1)

{eo_tides-0.0.21 → eo_tides-0.0.22}/eo_tides.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: eo-tides
-Version: 0.0.21
+Version: 0.0.22
 Summary: Tide modelling tools for large-scale satellite earth observation analysis
 Author-email: Robbi Bishop-Taylor <Robbi.BishopTaylor@ga.gov.au>
 Project-URL: Homepage, https://GeoscienceAustralia.github.io/eo-tides/
@@ -22,23 +22,24 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Python: <4.0,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: colorama
-Requires-Dist: geopandas>=1.0.0
-Requires-Dist: numpy
-Requires-Dist: odc-geo
-Requires-Dist: pandas
-Requires-Dist: pyproj
+Requires-Dist: colorama>=0.4.3
+Requires-Dist: geopandas>=0.10.0
+Requires-Dist: matplotlib>=3.8.0
+Requires-Dist: numpy>=1.26.0
+Requires-Dist: odc-geo>=0.4.7
+Requires-Dist: pandas>=2.2.0
+Requires-Dist: pyproj>=3.6.1
 Requires-Dist: pyTMD==2.1.6
-Requires-Dist: scikit-learn
-Requires-Dist: scipy
-Requires-Dist: shapely
-Requires-Dist: tqdm
-Requires-Dist: xarray
+Requires-Dist: scikit-learn>=1.4.0
+Requires-Dist: scipy>=1.11.2
+Requires-Dist: shapely>=2.0.6
+Requires-Dist: tqdm>=4.55.0
+Requires-Dist: xarray>=2022.3.0
 Provides-Extra: notebooks
 Requires-Dist: odc-stac>=0.3.10; extra == "notebooks"
-Requires-Dist: pystac-client; extra == "notebooks"
-Requires-Dist: folium; extra == "notebooks"
-Requires-Dist: matplotlib; extra == "notebooks"
+Requires-Dist: pystac-client>=0.8.3; extra == "notebooks"
+Requires-Dist: folium>=0.16.0; extra == "notebooks"
+Requires-Dist: planetary_computer>=1.0.0; extra == "notebooks"
 
 # `eo-tides`: Tide modelling tools for large-scale satellite earth observation analysis
 

eo_tides-0.0.22/eo_tides.egg-info/requires.txt

@@ -0,0 +1,19 @@
+colorama>=0.4.3
+geopandas>=0.10.0
+matplotlib>=3.8.0
+numpy>=1.26.0
+odc-geo>=0.4.7
+pandas>=2.2.0
+pyproj>=3.6.1
+pyTMD==2.1.6
+scikit-learn>=1.4.0
+scipy>=1.11.2
+shapely>=2.0.6
+tqdm>=4.55.0
+xarray>=2022.3.0
+
+[notebooks]
+odc-stac>=0.3.10
+pystac-client>=0.8.3
+folium>=0.16.0
+planetary_computer>=1.0.0

{eo_tides-0.0.21 → eo_tides-0.0.22}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "eo-tides"
-version = "0.0.21"
+version = "0.0.22"
 description = "Tide modelling tools for large-scale satellite earth observation analysis"
 authors = [{ name = "Robbi Bishop-Taylor", email = "Robbi.BishopTaylor@ga.gov.au" }]
 readme = "README.md"
@@ -30,19 +30,19 @@ classifiers = [
 ]
 requires-python = ">=3.9,<4.0"
 dependencies = [
-  "colorama",
-  "geopandas>=1.0.0",
-  "numpy",
-  "odc-geo",
-  "pandas",
-  "pyproj",
-  "pyTMD==2.1.6",
-  # "pyTMD@git+https://github.com/tsutterley/pyTMD",
-  "scikit-learn",
-  "scipy",
-  "shapely",
-  "tqdm",
-  "xarray",
+    "colorama>=0.4.3",
+    "geopandas>=0.10.0",
+    "matplotlib>=3.8.0",
+    "numpy>=1.26.0",
+    "odc-geo>=0.4.7",
+    "pandas>=2.2.0",
+    "pyproj>=3.6.1",
+    "pyTMD==2.1.6",
+    "scikit-learn>=1.4.0",
+    "scipy>=1.11.2",
+    "shapely>=2.0.6",
+    "tqdm>=4.55.0",
+    "xarray>=2022.3.0",
 ]
 
 [project.urls]
@@ -53,28 +53,27 @@ Documentation = "https://GeoscienceAustralia.github.io/eo-tides/"
 [project.optional-dependencies]
 notebooks = [
     "odc-stac>=0.3.10",
-    "pystac-client",
-    "folium",
-    "matplotlib",
+    "pystac-client>=0.8.3",
+    "folium>=0.16.0",
+    "planetary_computer>=1.0.0",
 ]
 
 [tool.uv]
 dev-dependencies = [
-    "pytest>=7.2.0",
-    "nbval>=0.11.0",
-    "pre-commit>=2.20.0",
-    "tox-uv>=1.11.3",
+    "pytest>=6.0.0",
+    "pre-commit>=0.2.0",
     "deptry>=0.20.0",
-    "mypy>=0.991",
-    "pytest-cov>=4.0.0",
-    "ruff>=0.6.9",
-    "mkdocs>=1.4.2",
-    "mkdocs-material>=8.5.10",
-    "mkdocs-jupyter>=0.25.0",
-    "mkdocstrings[python]>=0.19.0",
+    "mypy>=0.900",
+    "pytest-cov>=0.6",
+    "ruff>=0.0.200",
+    "mkdocs>=1.2",
+    "mkdocs-material>=9.5.0",
+    "mkdocs-jupyter>=0.24.0",
+    "mkdocstrings[python]>=0.20.0",
+    "nbval>=0.10.0",
+    "odc-stac>=0.3.8",
     "pystac-client>=0.8.3",
-    "odc-stac>=0.3.10",
-    "black>=24.8.0",
+    "planetary_computer>=1.0.0",
 ]
 
 [build-system]

{eo_tides-0.0.21 → eo_tides-0.0.22}/tests/test_model.py

@@ -3,8 +3,9 @@ import pathlib
 import numpy as np
 import pandas as pd
 import pytest
+from pyTMD.compute import tide_elevations
 
-from eo_tides.model import list_models, model_tides
+from eo_tides.model import _set_directory, list_models, model_tides
 from eo_tides.validation import eval_metrics
 
 GAUGE_X = 122.2183
@@ -12,94 +13,92 @@ GAUGE_Y = -18.0008
 ENSEMBLE_MODELS = ["EOT20", "HAMTIDE11"]  # simplified for tests
 
 
-@pytest.fixture()
-def measured_tides_ds():
-    """
-    Load measured sea level data from the Broome ABSLMP tidal station:
-    http://www.bom.gov.au/oceanography/projects/abslmp/data/data.shtml
-    """
-    # Metadata for Broome ABSLMP tidal station:
-    # http://www.bom.gov.au/oceanography/projects/abslmp/data/data.shtml
-    ahd_offset = -5.322
-
-    # Load measured tides from ABSLMP tide gauge data
-    measured_tides_df = pd.read_csv(
-        "tests/data/IDO71013_2020.csv",
-        index_col=0,
-        parse_dates=True,
-        na_values=-9999,
-    )[["Sea Level"]]
-
-    # Update index and column names
-    measured_tides_df.index.name = "time"
-    measured_tides_df.columns = ["tide_height"]
-
-    # Apply station AHD offset
-    measured_tides_df += ahd_offset
-
-    # Return as xarray dataset
-    return measured_tides_df.to_xarray()
-
-
 # Test available tide models
 def test_list_models():
     # Using env var
     available_models, supported_models = list_models()
-    assert available_models == ["EOT20", "HAMTIDE11"]
-    assert len(supported_models) > 2
+    assert available_models == ["EOT20", "GOT5.5", "HAMTIDE11"]
+    assert len(supported_models) > 3
 
     # Not printing outputs
     available_models, supported_models = list_models(show_available=False, show_supported=False)
-    assert available_models == ["EOT20", "HAMTIDE11"]
+    assert available_models == ["EOT20", "GOT5.5", "HAMTIDE11"]
 
     # Providing a string path
     available_models, supported_models = list_models(directory="./tests/data/tide_models")
-    assert available_models == ["EOT20", "HAMTIDE11"]
+    assert available_models == ["EOT20", "GOT5.5", "HAMTIDE11"]
 
     # Providing a pathlib
     path = pathlib.Path("./tests/data/tide_models")
     available_models, supported_models = list_models(directory=path)
-    assert available_models == ["EOT20", "HAMTIDE11"]
+    assert available_models == ["EOT20", "GOT5.5", "HAMTIDE11"]
 
 
 # Run test for multiple input coordinates, CRSs and interpolation methods
 @pytest.mark.parametrize(
-    "x, y, crs, method",
+    "x, y, crs, method, model",
     [
-        (GAUGE_X, GAUGE_Y, "EPSG:4326", "bilinear"),  # WGS84, bilinear interp
-        (GAUGE_X, GAUGE_Y, "EPSG:4326", "spline"),  # WGS84, spline interp
+        (GAUGE_X, GAUGE_Y, "EPSG:4326", "bilinear", "EOT20"),  # WGS84, bilinear interp
+        (GAUGE_X, GAUGE_Y, "EPSG:4326", "spline", "EOT20"),  # WGS84, spline interp
         (
             -1034913,
             -1961916,
             "EPSG:3577",
             "bilinear",
+            "EOT20",
         ),  # Australian Albers, bilinear interp
+        (GAUGE_X, GAUGE_Y, "EPSG:4326", "spline", "GOT5.5"),
+        (GAUGE_X, GAUGE_Y, "EPSG:4326", "spline", "HAMTIDE11"),
     ],
 )
-def test_model_tides(measured_tides_ds, x, y, crs, method):
-    # Run EOT20 tidal model for locations and timesteps in tide gauge data
+def test_model_tides(measured_tides_ds, x, y, crs, method, model):
+    # Run modelling for locations and timesteps in tide gauge data
     modelled_tides_df = model_tides(
         x=[x],
         y=[y],
         time=measured_tides_ds.time,
         crs=crs,
         method=method,
+        model=model,
     )
 
-    # Compare measured and modelled tides
-    val_stats = eval_metrics(x=measured_tides_ds.tide_height, y=modelled_tides_df.tide_height)
-
     # Test that modelled tides contain correct headings and have same
     # number of timesteps
     assert modelled_tides_df.index.names == ["time", "x", "y"]
     assert modelled_tides_df.columns.tolist() == ["tide_model", "tide_height"]
     assert len(modelled_tides_df.index) == len(measured_tides_ds.time)
 
+    # Run equivalent pyTMD code
+    pytmd_tides = tide_elevations(
+        x=x,
+        y=y,
+        delta_time=measured_tides_ds.time,
+        DIRECTORY=_set_directory(None),
+        MODEL=model,
+        EPSG=int(crs[-4:]),
+        TIME="datetime",
+        EXTRAPOLATE=True,
+        CUTOFF=np.inf,
+        METHOD=method,
+    )
+
+    # Verify that pyTMD produces same results as `model_tides`
+    assert np.allclose(modelled_tides_df.tide_height.values, pytmd_tides.data)
+
+    # Compare measured and modelled tides
+    val_stats = eval_metrics(x=measured_tides_ds.tide_height, y=modelled_tides_df.tide_height)
+
     # Test that modelled tides meet expected accuracy
-    assert val_stats["Correlation"] > 0.99
-    assert val_stats["RMSE"] < 0.27
-    assert val_stats["R-squared"] > 0.96
-    assert abs(val_stats["Bias"]) < 0.20
+    if model == "HAMTIDE11":
+        assert val_stats["Correlation"] > 0.99
+        assert val_stats["RMSE"] < 0.34
+        assert val_stats["R-squared"] > 0.98
+        assert abs(val_stats["Bias"]) < 0.20
+    else:
+        assert val_stats["Correlation"] > 0.99
+        assert val_stats["RMSE"] < 0.27
+        assert val_stats["R-squared"] > 0.99
+        assert abs(val_stats["Bias"]) < 0.20
 
 
 # Run tests for one or multiple models, and long and wide format outputs
@@ -108,8 +107,8 @@ def test_model_tides(measured_tides_ds, x, y, crs, method):
     [
         (["EOT20"], "long"),
         (["EOT20"], "wide"),
-        (["EOT20", "HAMTIDE11"], "long"),
-        (["EOT20", "HAMTIDE11"], "wide"),
+        (["EOT20", "GOT5.5", "HAMTIDE11"], "long"),
+        (["EOT20", "GOT5.5", "HAMTIDE11"], "wide"),
     ],
     ids=[
         "single_model_long",

eo_tides-0.0.21/eo_tides.egg-info/requires.txt

@@ -1,18 +0,0 @@
-colorama
-geopandas>=1.0.0
-numpy
-odc-geo
-pandas
-pyproj
-pyTMD==2.1.6
-scikit-learn
-scipy
-shapely
-tqdm
-xarray
-
-[notebooks]
-odc-stac>=0.3.10
-pystac-client
-folium
-matplotlib