SPACE-BORNE CLOUD-NATIVE SATELLITE-DERIVED BATHYMETRY (SDB) MODELS USING ICESat-2 and SENTINEL-2

Shallow nearshore coastal waters provide a wealth of societal, economic and ecosystem services, yet their structure is poorly mapped due to the use of expensive and time intensive methods. Bathymetric mapping from space has sought to alleviate this but has remained dependent upon in situ water-based measurements. Here we fuse ICESat-2 lidar data with Sentinel-2 optical imagery, within the Google Earth Engine geospatial cloud platform, to create wall-to-wall high-resolution bathymetric maps at regional-to-national scales in Florida, Crete and Bermuda. ICESat-2 bathymetric classified photons are used to train three common Satellite Derived Bathymetry (SDB) methods, including Lyzenga, Stumpf and Support Vector Regression algorithms. For each study site the Lyzenga algorithm yielded the lowest RMSE (approx. 10-15%) when compared with in situ NOAA DEM data. We demonstrate a means of using ICESat-2 for both model calibration and validation, thus cementing a pathway for a fully space-borne approach to map nearshore bathymetry.