A Coupled Transformer–CNN Network: Advancing Sea Surface Temperature Forecast Accuracy
- 29 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-14
Abstract
Sea surface temperature (SST) is critically important for understanding ocean dynamics and supporting various marine activities, making accurate short-term SST forecasting highly significant. However, accurately modeling the multi-scale variability of SST remains challenging for existing deep learning (DL) models. This study introduces the Coupled Transformer-CNN Network (CoTCN), a hybrid architecture designed to leverage the multi-scale variability of SST. The CoTCN combines the strengths of Transformers and convolutional neural networks (CNNs), significantly enhancing SST forecasts’ spatial continuity and predictive accuracy. Compared to five state-of-the-art DL models based on Transformer or CNN that include ConvLSTM, ConvGRU, AFNO, PredRNN, and SwinLSTM, CoTCN demonstrates superior performance in global and local areas of SST forecasting. At 1-day lead time, CoTCN reduces the global average root mean square error (RMSE) by over 15%, with forecast errors ranging from 0.20°C to 0.53°C across 1–10 day lead times. Moreover, the CoTCN effectively mitigates the checkerboard artifacts inherent to the Vision Transformer architecture. These findings highlight the effectiveness of CoTCN in capturing SST’s multi-scale features and underscore the promising potential of hybrid architectures for future DL models.Keywords
Funding Information
- Strategic Priority Research Program of the Chinese Academy of Sciences (XDB0500303)
- Key Program for Developing Basic Sciences (2022YFC3104802)
- National Natural Science Foundations of China (92358302)
This publication has 38 references indexed in Scilit:
- Forecasting sea surface temperature during typhoon events in the Bohai Sea using spatiotemporal neural networksAtmospheric Research, 2024
- Effective attention model for global sea surface temperature predictionExpert Systems with Applications, 2024
- Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation2023
- A deep learning approach to predict sea surface temperature based on multiple modesOcean Modelling, 2022
- Composite of Typhoon‐Induced Sea Surface Temperature and Chlorophyll‐a Responses in the South China SeaJournal of Geophysical Research: Oceans, 2020
- Prediction of sea surface temperatures using deep learning neural networksSN Applied Sciences, 2020
- Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approachRemote Sensing of Environment, 2019
- A spatiotemporal deep learning model for sea surface temperature field prediction using time-series satellite dataEnvironmental Modelling & Software, 2019
- A global analysis of coral bleaching over the past two decadesNature Communications, 2019
- Attribution of SST variability in global oceans and the role of ENSOClimate Dynamics, 2013