Estimating thermohaline structures in the tropical Indian Ocean from surface parameters using an improved CNN model

Accurately estimating the ocean's subsurface thermohaline structure is essential for advancing our understanding of regional and global ocean dynamics. In this study, we propose a novel neural network model based on Convolutional Block Attention Module-Convolutional Neural Network (CBAM-CNN) to simultaneously estimate the ocean subsurface thermal structure (OSTS) and ocean subsurface salinity structure (OSSS) in the tropical Indian Ocean using satellite observations. The input variables include sea surface temperature (SST), sea surface salinity (SSS), sea surface height anomaly (SSHA), eastward component of sea surface wind (ESSW), northward component of sea surface wind (NSSW), longitude (LON), and latitude (LAT). We train and validate the model using Argo data, and compare its accuracy with that of the original Convolutional Neural Network (CNN) model using root mean square error (RMSE), normalized root mean square error (NRMSE), and determination coefficient (R-2). Our results show that the CBAM-CNN model outperforms the CNN model, exhibiting superior performance in estimating thermohaline structures in the tropical Indian Ocean. Furthermore, we evaluate the model's accuracy by comparing its estimated OSTS and OSSS at different depths with Argo-derived data, demonstrating that the model effectively captures most observed features using sea surface data. Additionally, the CBAM-CNN model demonstrates good seasonal applicability for OSTS and OSSS estimation. Our study highlights the benefits of using CBAM-CNN for estimating thermohaline structure and offers an efficient and effective method for estimating thermohaline structure in the tropical Indian Ocean.