Water depth estimation from Sentinel-2 imagery using advanced machine learning methods and explainable artificial intelligence

Abstract

The estimation of water depth in coastal areas and shallow waters is crucial for marine management and monitoring. However, direct measurements using fieldwork methods can be costly and time-consuming. Therefore, remote sensing imagery is a promising source of geospatial information for coastal planning and development. To this end, this study investigates advanced machine learning (ML) methods and redesigned morphological profiles for water depth estimation using high-resolution Sentinel-2 satellite imagery. The proposed framework involves three main steps: (1) morphological feature generation, (2) model training using several ML methods (Decision Tree, Random Forest, eXtreme Gradient BOOSTing, Light Gradient Boosting Machine, Deep Neural Network, and CatBoost), and (3) model interpretation using eXplainable Artificial Intelligence (XAI). The performance of the proposed method was evaluated in two different coastal areas (port and jetty) with reference data from accurate hydrographic data (Echo-sounder and differential global positioning systems). The statistical analysis revealed that the proposed method had high efficiency for depth estimation of the coastal area, achieving a best R2 value of 0.96 and Root Mean Square Error (RMSE) of 0.27 m in water depth estimation in the shallow water of Chabahar Bay in the Oman Sea. Additionally, the higher impact and interaction of the morphological features were verified using XAI for water depth mapping.