Interpretable Adaptive Multiscale Spatiotemporal Network for Long-Term Global Sea Surface Temperature Prediction
Remote Sensing · 26.03.2026 · 18 (7) · 997
DOI: 10.3390/rs18070997 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 26.03.2026. Verfasst von Rixu Hao und 2 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China https://ror.org/01h0zpd94, National Natural Science Foundation of Heilongjiang Province, China.
Abstract (Originalsprache)
Sea surface temperature (SST) serves as a fundamental driver of ocean–atmosphere interactions and global climate variability, exhibiting strong nonstationarity, multiscale dynamics, and cross-variable coupling. However, current deep learning models often fail to capture these complex characteristics, limiting their ability to support accurate and physically consistent long-term SST prediction. To address these issues, we propose PAMSTnet, a unified deep learning framework for physics-informed adaptive multiscale spatiotemporal prediction. PAMSTnet leverages three-dimensional empirical wavelet transform (3DEWT) to learn interpretable multiscale spatiotemporal dynamics from raw observations, and applies multivariate spatiotemporal empirical orthogonal function (MSTEOF) to identify dominant cross-variable coupled modes. These physically meaningful representations are integrated into a deep ConvLSTM predictive network (DCPN) to support coordinated multiscale dynamical learning. Furthermore, PAMSTnet introduces physics-informed consistency learning (PICL) to enforce thermodynamic and dynamic constraints, enhancing physical consistency and interpretability. Extensive experiments demonstrate that PAMSTnet achieves superior performance against state-of-the-art baselines in long-term global SST prediction, reducing RMSE by 8.1% and improving ACC by 2.8% compared with the best-performing baseline, particularly under extreme climate events. Interpretation insights further highlight PAMSTnet’s adaptive representation of variable contributions and regional physical drivers. These findings position PAMSTnet as a promising paradigm for developing intelligent ocean prediction systems with enhanced physical consistency and interpretability.
Förderung
- National Natural Science Foundation of China https://ror.org/01h0zpd94
- National Natural Science Foundation of Heilongjiang Province, China
Zitieren
APA
Hao, R., Zhao, Y., & Deng, X. (2026). Interpretable Adaptive Multiscale Spatiotemporal Network for Long-Term Global Sea Surface Temperature Prediction. Remote Sensing, 18(7), 997. https://doi.org/10.3390/rs18070997
Vancouver
Hao R, Zhao Y, Deng X. Interpretable Adaptive Multiscale Spatiotemporal Network for Long-Term Global Sea Surface Temperature Prediction. Remote Sensing. 2026;18(7):997. doi:10.3390/rs18070997
BibTeX
@article{Hao2026,
author = {Hao, Rixu and Zhao, Yuxin and Deng, Xiong},
title = {Interpretable Adaptive Multiscale Spatiotemporal Network for Long-Term Global Sea Surface Temperature Prediction},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {7},
pages = {997},
doi = {10.3390/rs18070997}
}
EUVIMED