A Hybrid Mamba–ConvLSTM Framework for Multi-Day Sea Surface Temperature Forecasting at 0.05° Resolution
Journal of Marine Science and Engineering · 12.05.2026 · 14 (10) · 898
DOI: 10.3390/jmse14100898 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 12.05.2026. Verfasst von Bo Peng und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate multi-day sea surface temperature (SST) prediction at sub-mesoscale resolution is challenging due to nonlinear ocean dynamics, heterogeneous multi-source observations, and error accumulation during autoregressive rollout. This paper proposes a hybrid Mamba–ConvLSTM framework that combines recurrent local spatiotemporal encoding with selective state-space long-range spatial modeling. The ConvLSTM branch captures local spatial patterns and short-range temporal dependencies through convolutional gating, while the Mamba branch captures long-range spatial dependencies across each frame through cross-direction window scanning and maintains temporal coherence via persistent hidden states across successive time steps. A physically informed preprocessing stage aligns 0.083° reanalysis variables to the 0.05° OSTIA target grid via a Grow-and-Cut strategy and extracts gradient-based advection and diffusion proxy features under boundary-aware finite differencing. During autoregressive rollout, auxiliary variables are held at their last observed values and physical proxies are recomputed from the predicted SST, following a clearly specified protocol. Experiments on a South China Sea benchmark compare the proposed model against nine baselines—including persistence, daily climatology, ConvLSTM, PredRNN, ConvGRU, TCTN, PANN, Swin-UNet, and ViT-ST—under an identical data-split, normalization, and rollout protocol. Evaluation with RMSE, MAE, SSIM, R2, and anomaly correlation coefficient (ACC) shows that the proposed model achieves a 10-day average RMSE of 0.512 °C, outperforming the strongest learning-based baseline ViT-ST by 5.0% and the persistence forecast by 21.0%. Ablation studies, sensitivity analyses, seasonal evaluation, and statistical significance testing verify the contribution of each component and the robustness of the results.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Peng, B., Hong, Z., & Wang, G. (2026). A Hybrid Mamba–ConvLSTM Framework for Multi-Day Sea Surface Temperature Forecasting at 0.05° Resolution. Journal of Marine Science and Engineering, 14(10), 898. https://doi.org/10.3390/jmse14100898
Vancouver
Peng B, Hong Z, Wang G. A Hybrid Mamba–ConvLSTM Framework for Multi-Day Sea Surface Temperature Forecasting at 0.05° Resolution. Journal of Marine Science and Engineering. 2026;14(10):898. doi:10.3390/jmse14100898
BibTeX
@article{Peng2026,
author = {Peng, Bo and Hong, Zhonghua and Wang, Guansuo},
title = {A Hybrid Mamba–ConvLSTM Framework for Multi-Day Sea Surface Temperature Forecasting at 0.05° Resolution},
journal = {Journal of Marine Science and Engineering},
year = {2026},
volume = {14},
number = {10},
pages = {898},
doi = {10.3390/jmse14100898}
}
EUVIMED