Reconstructing Ocean Subsurface Temperature and Salinity from Sea Surface Information Based on Dual Path Convolutional Neural Networks

Satellite remote sensing can provide observation information of the sea surface, and using surface to reconstruct subsurface temperature (ST) salinity (SS) has significant application values. This study proposes an intelligent algorithm based on Dual Path Convolutional Neural Networks (DP-CNNs) ST SS. The DP-CNN integrate known including (SST), (SSS), height (SSH) reconstruction model solve problem detail loss in traditional CNN (Convolutional Network) models. performs experiments for South China Sea under different seasons reanalysis data. experimental results show that models have higher accuracy than models, this proves DP-CNNs effectively mitigate detailed Compared with ground truth data, ST/SS exhibited a high coefficient determination (0.93/0.86) low root mean square error (around 0.31 °C/0.05 PSU). Therefore, be used as effective approach SS information.