StarShoal
Satellite-derived bathymetry: download Sentinel-2 and map shallow water depth calibrated with your own depth points.
StarShoal downloads Sentinel-2 imagery from the Copernicus Data Space Ecosystem, prepares masked surface reflectance and estimates shallow-water depth with Stumpf log-ratio, Lyzenga multiband and Random Forest, calibrated and validated on the same points (spatial blocks). Includes Hedley sunglint correction and area masking by polygon. One window with tabs, in Spanish and English; every tool is also in the Processing Toolbox. Outputs depth and trust rasters plus an HTML accuracy report. Optical SDB only works in clear, shallow water. Dependencies: only GDAL and numpy (shipped with QGIS); Random Forest also needs scikit-learn (on Windows, from the OSGeo4W Shell: python -m pip install scikit-learn); without it the method is skipped with a warning. Downloads need a free Copernicus Data Space Ecosystem account.