A Dual-attention Embedded CNN Model for Estimating Mixed Layer Depths in the Bay of Bengal

Variations in ocean mixed layer depth (MLD) show a significant impact on energy balance in the global climate systems and marine ecosystems. So far, the accuracy of modeling MLD, especially in the region with complex ocean dynamics, remains a challenge. This thus calls for an emergency using Artificial intelligence (AI) approach to improve the assessment of the MLD. In this study, we introduce a novel convolutional neural network model based on a dual-attention module (DA-CNN) to estimate the MLD in the Bay of Bengal (BoB) by integrating multi-source remote sensing data and Argo gridded data. Compared with the original CNN model, the DA-CNN model exhibits superior performance with notable improvements in the annual average RMSE and R2 values by 13.0% and 8.4%, respectively, while more accurately capturing the seasonal variations in MLD. Moreover, the results using the DA-CNN model show minimum RMSE and maximum R2 values, in comparison to the calculation by the random forest (RF), neural network (ANN) model, and the Hybrid Coordinate Ocean Model (HYCOM). Accordingly, our findings suggest that the newly developed DA-CNN model provides an effective advantage in studying the MLD and the associated ocean processes.