EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

XAI Helps in Storm Surge Forecasts: A Case Study for the Southeastern Chinese Coasts

Lei Han, Wenfang Lu, Changming Dong

Journal of Marine Science and Engineering · 30.04.2025 · 13 (5) · 896

DOI: 10.3390/jmse13050896 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 30.04.2025. Verfasst von Lei Han und 2 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key Research and Development Program of China, the Science and Technology Innovation Project of Laoshan Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Storm surge forecasting presents a significant challenge for coastal resilience, particularly in typhoon-prone regions such as southeastern China, where compound flooding events lead to substantial socioeconomic losses. Although artificial intelligence (AI) models have shown strong potential in storm surge prediction, their inherent “black-box” nature limits both their interpretability and operational trust. In this study, we integrate a Vision Transformer (ViT) model with an explainable AI (XAI) method—specifically, Shapley value analysis (SHAP)—to develop an interpretable, high-performance storm surge forecasting framework. The baseline ViT model demonstrates excellent predictive skill, achieving spatiotemporal correlation coefficients exceeding 0.90 over a 12 h lead time. However, it exhibits systematic underestimations in topographically complex regions, such as semi-enclosed bays (e.g., up to 0.06 m). SHAP analysis reveals that the model primarily relies on the autocorrelation of historical surge levels rather than external wind forcing—contrary to the conventional physical understanding of storm surge dynamics. Guided by these insights, we introduce the surge time difference (ΔZ/Δt) as an explicit input feature to enhance the model’s physical representation. This modification yields substantial improvements: during the critical first hour of forecasting—a key window for disaster mitigation—the RMSE is reduced from 0.01 m to 0.005 m, while the correlation coefficient increases from 0.92 to 0.98. This study bridges the gap between data-driven forecasting and physical interpretability, offering a transparent and trustworthy framework for next-generation intelligent storm surge prediction.

Förderung

  • the National Key Research and Development Program of China
  • the Science and Technology Innovation Project of Laoshan Laboratory

Zitieren

APA

Han, L., Lu, W., & Dong, C. (2025). XAI Helps in Storm Surge Forecasts: A Case Study for the Southeastern Chinese Coasts. Journal of Marine Science and Engineering, 13(5), 896. https://doi.org/10.3390/jmse13050896

Vancouver

Han L, Lu W, Dong C. XAI Helps in Storm Surge Forecasts: A Case Study for the Southeastern Chinese Coasts. Journal of Marine Science and Engineering. 2025;13(5):896. doi:10.3390/jmse13050896

BibTeX
@article{Han2025,
  author = {Han, Lei and Lu, Wenfang and Dong, Changming},
  title = {XAI Helps in Storm Surge Forecasts: A Case Study for the Southeastern Chinese Coasts},
  journal = {Journal of Marine Science and Engineering},
  year = {2025},
  volume = {13},
  number = {5},
  pages = {896},
  doi = {10.3390/jmse13050896}
}
Kostenlos starten →