Retrieving Global Ocean Subsurface Density by Combining Remote Sensing Observations and Multiscale Mixed Residual Transformer

Journal Title
Journal ISSN
Volume Title
IEEE Transactions on Geoscience and Remote Sensing
Subsurface density (SD) is a crucial dynamic environment parameter reflecting a 3-D ocean process and stratification, with significant implications for the physical, chemical, and biological processes of the ocean environment. Thus, accurate SD retrieval is essential for studying dynamic processes in the ocean interior. However, complete spatiotemporally accurate SD retrieval remains a challenge in terms of the equation of state and physical methods. This study proposes a novel multiscale mixed residual transformer (MMRT) neural network method to compensate for the inadequacy of the existing methods in dealing with spatiotemporal nonlinear processes and dependence. Considering the spatial correlation and temporal dependence of dynamic processes within the ocean, the MMRT addresses temporal dependence by fully using the transformer’s processing of time-series data and spatial correlation by compensating for deficiencies in spatial feature information through multiscale mixed residuals. The MMRT model was compared with the existing random forest (RF) and recurrent neural network (RNN) methods. The MMRT model achieves the best accuracy with an average determination coefficient ( R2 ) of 0.988 and an average root mean square error (RMSE) of 0.050 kg/m3 for all layers. The MMRT model not only outperforms the RF and RNN methods regarding reliability and generalization ability when estimating global ocean SD from remote sensing data but also has a more interpretable encoding process. The MMRT model offers a new method for directly estimating SD using multisource satellite observations, providing significant technical support for future remote sensing super-resolution and prediction of subsurface parameters.
This article was originally published in IEEE Transactions on Geoscience and Remote Sensing. The version of record is available at: © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This article will be embargoed until 01/05/2026.
global ocean, remote sensing observations, subsurface density (SD), transformer
H. Su, J. Qiu, Z. Tang, Z. Huang and X. -H. Yan, "Retrieving Global Ocean Subsurface Density by Combining Remote Sensing Observations and Multiscale Mixed Residual Transformer," in IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-13, 2024, Art no. 4201513, doi: 10.1109/TGRS.2024.3350346.