Dynamic Graph Contrastive Learning Neural Network for Sea Surface Temperature Prediction
- 9 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23 (1545598X) , 1-5
Abstract
Accurate daily mean sea surface temperature (SST) forecasting not only contributes to a deeper understanding of natural processes but also enhances our knowledge of global climate change and marine ecosystems. However, existing methods are often susceptible to noise and overlook dynamic spatial correlations, making it difficult for them to capture complex spatiotemporal dependencies. To address these issues, we propose a Dynamic Graph Contrastive Learning Network (DGCLN) for daily mean SST spatiotemporal forecasting. Specifically, we improve robustness to noise through topological data augmentation and generate both local and global augmented graphs using predefined adjacency matrices and self-optimized matrices. In addition, a dual-branch shared network that integrates multi-head self-attention with dynamic graphs is employed to fully exploit the dynamic spatiotemporal dependencies in SST sequences. Furthermore, a spatiotemporal contrastive learning auxiliary task is introduced to alleviate the problem of sparse supervision and extract critical spatiotemporal information. Experiments conducted on the Bohai Sea and South China Sea datasets demonstrate that DGCLN significantly outperforms existing state-of-the-art methods. Specifically, on the South China Sea dataset, the model achieves an MAE of 0.1506 for 1-day prediction, while outperforming the best-performing baseline by an average of 3.3% across all evaluated horizons.Keywords
Funding Information
- Zhejiang Provincial Natural Science Foundation of China (LQN25D060001)
- National Program on Key Research Project of China (2021YFC3101600)
- Pioneer and Leading Goose Research and Development Program of Zhejiang (2024C03033)
- Science Foundation of Zhejiang Sci-Tech University (23232090-Y)
This publication has 16 references indexed in Scilit:
- Adaptive Spatiotemporal Graph Recurrent Network for Sea Surface Temperature ForecastingIEEE Transactions on Geoscience and Remote Sensing, 2024
- Neural general circulation models for weather and climateNature, 2024
- Lake Water Temperature Modeling in an Era of Climate Change: Data Sources, Models, and Future ProspectsReviews of Geophysics, 2024
- GSTCN: Graph-Based Spatial-Temporal Convolutional Networks for Advanced ENSO Forecasting2023
- Global Spatiotemporal Graph Attention Network for Sea Surface Temperature PredictionIEEE Geoscience and Remote Sensing Letters, 2023
- Sea Surface Temperature Prediction With Memory Graph Convolutional NetworksIEEE Geoscience and Remote Sensing Letters, 2021
- Prediction of sea surface temperatures using deep learning neural networksSN Applied Sciences, 2020
- Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) networkPhysica D: Nonlinear Phenomena, 2020
- An Adaptive Scale Sea Surface Temperature Predicting Method Based on Deep Learning With Attention MechanismIEEE Geoscience and Remote Sensing Letters, 2019
- Estimating Land and Sea Surface Temperature From Cross-Calibrated Chinese Gaofen-5 Thermal Infrared Data Using Split-Window AlgorithmIEEE Geoscience and Remote Sensing Letters, 2019