Deep Learning-Based Bias Correction Model for Spatiotemporal Significant Wave Height Prediction Using Multi-Channel VMRNN
Oceans · 01.07.2026 · 7 (4) · 54
DOI: 10.3390/oceans7040054 ↗Kurz gefasst
Fachartikel in der Zeitschrift Oceans, online erschienen am 01.07.2026. Verfasst von Bao Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Province Natural Resources Science and Technology Project.
Abstract (Originalsprache)
Accurate prediction of significant wave height (SWH) is essential for fisheries management, coastal socioeconomic activities, and marine ecological conservation. In recent years, deep learning-based bias correction has shown considerable potential for improving numerical wave forecasts. However, many existing approaches are still constrained by limited receptive fields and often struggle to capture long-range spatiotemporal dependencies in wave forecast errors. To deal with this issue, we adapt and improve a video prediction framework, namely the Vision Mamba Recurrent Neural Network (VMRNN), to model and correct the spatiotemporal patterns of SWH prediction biases. Comprehensive evaluations show that the multi-channel VMRNN achieves consistently high predictive accuracy across different forecast lead times and sea-state conditions. When validated against reanalysis data, the proposed model reduces the root mean square error (RMSE) of WAVEWATCH III forecasts by 28.2%, 26.1%, and 24.7% at lead times of 24, 48, and 72 h, respectively. It also preserves the spatial structure of SWH fields quite well, with the spatial structural similarity index remaining as high as 0.945 even at the 72 h lead time. Regional assessments over high-wave areas further indicate that VMRNN can effectively reduce both the mean error and the systematic overestimation commonly found in numerical wave models. Additional validation using in situ buoys observations confirms that the model has a robust ability to correct systematic positive biases, especially for wave heights ranging from 0.5 m to 2 m. Taken together, these results suggest that VMRNN has strong spatiotemporal modeling capability and can serve as a promising post-processing framework for improving operational physics-based wave forecasting systems.
Förderung
- Jiangsu Province Natural Resources Science and Technology Project
Zitieren
APA
Wang, B., Xiao, J., Feng, C., Pan, X., & Wang, B. (2026). Deep Learning-Based Bias Correction Model for Spatiotemporal Significant Wave Height Prediction Using Multi-Channel VMRNN. Oceans, 7(4), 54. https://doi.org/10.3390/oceans7040054
Vancouver
Wang B, Xiao J, Feng C, Pan X, Wang B. Deep Learning-Based Bias Correction Model for Spatiotemporal Significant Wave Height Prediction Using Multi-Channel VMRNN. Oceans. 2026;7(4):54. doi:10.3390/oceans7040054
BibTeX
@article{Wang2026,
author = {Wang, Bao and Xiao, Jie and Feng, Chuhan and Pan, Xishan and Wang, Bin},
title = {Deep Learning-Based Bias Correction Model for Spatiotemporal Significant Wave Height Prediction Using Multi-Channel VMRNN},
journal = {Oceans},
year = {2026},
volume = {7},
number = {4},
pages = {54},
doi = {10.3390/oceans7040054}
}
EUVIMED