Satellite-Derived Bathymetry in Dynamic Coastal Geomorphological Environments Through Machine Learning Algorithms

In the field of coastal geomorphology, advancements in space technology have revolutionized coastal mapping and understanding. Satellite-derived bathymetry (SDB) research has progressed, focusing on various estimation methods using high-resolution satellite imagery and in-situ data. Challenges arise when applying these methods to the Indian coastline due to its turbid waters and intricate features such as creeks and deltas, laden with sediment and submerged rocks. A study aims to assess multivariate machine learning (ML) regression techniques for estimating bathymetric data. The study employs ground-truth data and imagery from Aster, Landsat-8, and Sentinel-2 at distinct sites known for complex underwater landscapes. Several algorithms including Multiple Linear Regression, Support Vector Regressor, Gaussian Process Regression (GPR), Decision Tree Regression, K-Neighbors Regressor, k-fold cross-validation with Decision Tree Regression, and Random Forest (RF) are evaluated for SDB. Results from the Vengurla Site show that using the Landsat-8 data set with the GPR algorithm achieves R2 0.94, root mean squared error (RMSE) 1.53 m, and MAE 1.14 m, utilizing visible spectrum bands. At Mormugao, the Sentinel-2 data set with GPR and RF algorithms attains R2 0.97 and RMSE 1.23 m, with GPR outperforming RF, having an MAE of 1.05 m compared to RF's 1.22 m. This study underscores the potential of ML regression techniques in overcoming challenges with using SDB for mapping coastal geomorphology, particularly in intricate underwater terrains and turbid waters by assimilating sophisticated algorithms and their refined cartographic representation. Researchers are leveraging advancements in space technology to enhance the mapping and comprehension of coastal regions, particularly focusing on satellite-derived bathymetry (SDB). SDB utilizes high-resolution satellite imagery in conjunction with on-site data to estimate the submerged terrain. However, the application of these methodologies along the Indian coastline poses challenges due to factors such as turbidity and the presence of complex geological formations like creeks and deltas. This study explored the utilization of multivariate machine learning (ML) regression techniques to improve the estimation of SDB. Various algorithms were tested using data sourced from satellites such as Aster, Landsat-8, and Sentinel-2 across two different sites with diverse underwater landscapes. Results demonstrate promising accuracy, particularly when employing Landsat-8 data in conjunction with Gaussian Process Regression (GPR), yielding an R2 value of 0.94. Similarly, at another site, the combination of SENTINEL-2 data with GPR and RF achieved an R2 value of 0.97, underscoring the potential of ML techniques in mapping intricate coastal terrains despite challenges like turbid waters. Advancements in space technology for coastal bathymetry mapping Predicting coastal geomorphology with satellite-derived bathymetry (SDB) Multivariate machine learning regression for estimating SDB