Abstract
Accurate predicting sea surface temperature (SST) is practically important to ocean-related fields. However, due to the nonlinear temporal characteristics and complex spatial correlation of SST, fully extracting its spatiotemporal features for dependable short-term SST prediction remains challenging. In this work, we presented a multi-layer channel spatial attention Convolutional LSTM (CSACL) network to better capture the spatiotemporal information of SST recordings. Utilizing multi-scale spatial attention to obtain global-local spatial information and dynamic channel attention for inter-channel interaction, the CSA module achieves comprehensive extraction of spatial features in SST data. Moreover, the multilayer LSTM structure ensures that the network can capture the temporal dependency of short-term SST very well. Finally, we proposed a novel two-stage adaptive loss function training method to solve the accuracy degradation problem for longer prediction cycles. We have evaluated CSACL on three public datasets, and the results demonstrate its superior performance over other classical methods in short-term SST prediction.

This publication has 11 references indexed in Scilit: