Performance test of clean-coastal-water composite sentinel 2A image for shallow water bathymetry mapping

Abstract

The “clean-coastal-water time-series composite” image preprocessing algorithm is one of the alternatives for obtaining minimal atmospheric disturbance satellite images for data inputs in Satellite-Derived Bathymetry (SDB). However, the performance of time-series composite images for shallow water bathymetric mapping needs to be assessed, considering the presence of pixel and band dispersion during the composite image construction process. This research aims to study the result of a clean-coastal-water time-series composite Sentinel-2 by using cloud computing preprocessing as input data for SDB in shallow waters, compare the results of SDB from a Sentinel-2 single date image and from the clean-coastal-water time-series composite image using a random forest regressor (RFR) algorithm in terms of accuracy and spatial distribution of the bathymetry, and evaluate the performance and quality of bathymetric maps obtained from a single date image and clean-coastal-water time-series composite Sentinel-2 images based on International Hydrographic Organization standards (IHO). The results show that not all time-series composite processes can produce clean images of interference from clouds, sunglints, bad waters, and pixel wave breaks. The acquisition time range affects the quality of the time-series composite image. The SDB RFR model can handle the complex relationship between the in situ water depth variable and the surface reflectance value of a clean-coastal-water time-series composite image that has pixel and band dispersion. Overall, the SDB RFR model was successfully used to predict bathymetry in shallow waters with accuracy that meets the IHO standard CATZOC requirements, with RMSE and MAE values of less than 0.5 m as well as TVU confidence level values of more than 95% at a depth of 0–5 m resulting from each - respectively clean-coastal-water time-series composite images in shallow waters around Morotai Island.