Estimating the mixed layer depth of the global ocean by combining multisource remote sensing and spatiotemporal deep learning

Estimating the ocean mixed layer depth (MLD) is crucial for studying the atmosphere-ocean interaction and global climate change. Satellite observations can accurately estimate the MLD over large scales, effectively overcoming the limitation of sparse in situ observations and reducing uncertainty caused by estimation based on in situ and reanalysis data. However, combining multisource satellite observations to accurately estimate the global MLD is still extremely challenging. This study proposed a novel Residual Convolutional Gate Recurrent Unit (ResConvGRU) neural networks, to accurately estimate global MLD along with multisource remote sensing data and Argo gridded data. With the inherent spatiotemporal nonlinearity and dependence of the ocean dynamic process, the proposed method is effective in spatiotemporal feature learning by considering temporal dependence and capturing more spatial features of the ocean observation data. The performance metrics show that the proposed ResConvGRU outperforms other well-used machine learning models, with a global determination coefficient (R2) and a global root mean squared error (RMSE) of 0.886 and 17.83 m, respectively. Overall, the new deep learning approach proposed is more robust and advantageous in data-driven spatiotemporal modeling for retrieving ocean MLD at the global scale, and significantly improves the estimation accuracy of MLD from remote sensing observations.