Work

Reconstruction of the Subsurface Temperature and Salinity in the South China Sea Using Deep-Learning Techniques with a Physical Guidance

Year: 2025

Type: article

Abstract: In this paper, we develop a deep-learning neural network characterized by feature fusion and physical guidance (denoted as FFPG-net) for reconstructing subsurface sea temperature (T) and salinity (S) from sea surface data. Designed with the idea of feature fusion, FFPG-net combines the deep learning algorithms of residual and channel attention with the physical constraints of vertical modes of T/S profiles decomposed by empirical orthogonal functions (EOFs). The results from a series of experiments show that FFPG-net outperforms those networks without physical guidance or feature fusion in the reconstruction of subsurface T/S in a region of the South China Sea (SCS), with the monthly mean RMSEs of 0.31°C (0.35°C) and 0.06psu (0.07psu) for the reconstructed T/S profiles in winter (summer) averaged over the water depth of 1200m and the study area. In addition, the performance of the FFPG-net can be improved significantly by incorporating the full surface currents or the geostrophic currents derived from SSH into the input variables for training the neural network. The preliminary application of FFPG-net in the SCS using satellite-derived sea surface observations indicates that FFPG-net is reliable and feasible for reconstructing the subsurface ocean in real situations. Our study highlights the advantages and necessity of combining deep learning algorithms with the physical constraints in reconstructing subsurface T/S profiles, which provides an effective tool for reconstructing the subsurface global ocean from remote-sensing sea surface observations in the future.

Source: Remote Sensing

DOI: 10.3390/rs17172954

Authors: Qianlong Zhao, Yuting Cai, Guoqiang Zhong, Shiqiu Peng, Shaotian Li