EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Toward transferable models for efficient spatiotemporal flood prediction across coastal-estuarine systems

Samuel Daramola iD, David F Muñoz, Chaopeng Shen

Cambridge Prisms: Coastal Futures · 2026 · 4

DOI: 10.1017/cft.2026.10037 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Cambridge Prisms: Coastal Futures, online erschienen am 04.06.2026. Verfasst von Samuel Daramola und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil, Environment, and Ocean Engineering, Stevens Institute of Technology, NJ, USA. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This perspective examines the application of transfer learning (TL) within deep learning (DL) frameworks for extreme water level (EWL) and spatiotemporal flood predictions. We discuss the main advantages of TL, such as enabling model transferability of pretrained DL models from/to diverse coastal-estuarine systems and reducing computational time compared to physics-based models. These advantages can accelerate the deployment of flood prediction models in data-limited locations. We also discuss challenges and limitations that hinder accurate pattern recognition and propagation of EWLs from gauge (observation) stations to surrounding locations within model domains. These limitations include dependence on similarity in data distributions, overfitting the training data and both lag and hysteresis effects in the timing of peak water levels and flood dynamics. Lastly, we explain several misconceptions and challenges in current DL approaches that hinder EWL and spatiotemporal flood prediction, including training models exclusively on extreme conditions, assessing accuracy solely through goodness-of-fit metrics, and connecting the model’s knowledge of input data with physical explanations of flood processes without an adequate context. We argue that these challenges can be addressed by prioritizing storm-relevant patterns of the input data features as well as embedding spatial propagation of EWLs in DL frameworks to mimic coastal-estuarine hydrodynamic models. Ultimately, progress toward generalizable model transferability relies on the modeler’s ability to incorporate physical understanding in DL architectures, alongside continued advances in physics-informed machine learning models via soft or hard constraint approaches. There remains substantial work to establish guidelines and/or formal procedures to develop robust, interpretable, and generalizable DL models for spatiotemporal flood prediction, thereby supporting effective flood management, mitigation, and emergency preparedness.

Schlagwörter

Stichwörter der Autor:innen

coastal-estuarine hydrodynamicsextreme water levelsphysics-informed machine learningspatiotemporal flood predictiontransfer learning

Autor:innen und Institutionen

  • Department of Civil, Environment, and Ocean Engineering, Stevens Institute of Technology, NJ, USA.
  • Department of Civil and Environmental Engineering, Virginia Tech, Blacksburg, VA, USA.
  • Department of Civil and Environmental Engineering, Pennsylvania State University, PA, USA.

ORCID-Profile: Samuel Daramola

Zitieren

APA

Daramola, S., Muñoz, D. F., & Shen, C. (2026). Toward transferable models for efficient spatiotemporal flood prediction across coastal-estuarine systems. Cambridge Prisms: Coastal Futures, 4. https://doi.org/10.1017/cft.2026.10037

Vancouver

Daramola S, Muñoz DF, Shen C. Toward transferable models for efficient spatiotemporal flood prediction across coastal-estuarine systems. Cambridge Prisms: Coastal Futures. 2026;4. doi:10.1017/cft.2026.10037

BibTeX
@article{Daramola2026,
  author = {Daramola, Samuel and Muñoz, David F and Shen, Chaopeng},
  title = {Toward transferable models for efficient spatiotemporal flood prediction across coastal-estuarine systems},
  journal = {Cambridge Prisms: Coastal Futures},
  year = {2026},
  volume = {4},
  doi = {10.1017/cft.2026.10037}
}
Kostenlos starten →