A Hybrid CNN-LSTM Surrogate Model for Hyper-Resolution Spatiotemporal Flood Forecasting in Norfolk, Virginia

Authors

• Yidi Wang, University of Virginia
• Jonathan L. Goodall, University of Virginia
• Chetan Kumar, Old Dominion UniversityFollow
• Diana McSpadden, Thomas Jefferson National Accelerator Facility
• Sergio A. Barbosa, Oak Ridge National Laboratory
• Binata Roy, University of Virginia
• Ali Shahabi, Florida International University
• Navid Tahvildari, Florida International University

ORCID

0000-0003-2755-7338 (Kumar)

Document Type

Article

Publication Date

2026

DOI

10.1016/j.ejrh.2026.103234

Publication Title

Journal of Hydrology: Regional Studies

Volume

64

Pages

103234

Abstract

Study region

Norfolk, Virginia, United States

Study focus

Accurate and timely flood forecasting is essential for enhancing resilience in coastal urban areas in the context of increasing frequency and intensity of rainfall, sea level rise and urbanization. This study presents a hybrid deep learning-based surrogate model that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to enable real-time spatiotemporal flood forecasting. The model leverages CNN to capture spatial features from inputs such as elevation and Topographic Wetness Index (TWI), while LSTM processes time-series inputs of rainfall and tide data to capture temporal features.

New hydrologic insights for the region

The hybrid CNN-LSTM model was trained using the physics-based hydrodynamic model simulations obtained from the Two-dimensional Unsteady FLOW (TUFLOW) model for Norfolk, Virginia, and achieved high predictive accuracy across diverse flood-prone areas. The reduced computational time from four to six hours using TUFLOW to 3.2 min per event using CNN-LSTM enables rapid flood inundation mapping and early warning applications. The model effectively captured both spatial flood extents and their temporal evolution across different flooding scenarios, providing forecasts at a 2.5-m spatial resolution and 15-min temporal resolution and a one-hour-ahead prediction horizon. While challenges remain in terms of transferability to new regions and real-time data assimilation, this approach demonstrates strong potential for supporting operational flood risk management in coastal urban environments.

Rights

© 2026 The Authors.

This is an open access article under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) License.

Data Availability

Article states: "Data is available in Hydroshare at the following link: http://www.hydroshare.org/resource/43244f815e7947e6bac6b6705a9f7941."

Original Publication Citation

Wang, Y., Goodall, J. L., Kumar, C., McSpadden, D., Barbosa, S. A., Roy, B., Shahabi, A., & Tahvildari, N. (2026). A hybrid CNN-LSTM surrogate model for hyper-resolution spatiotemporal flood forecasting in Norfolk, Virginia. Journal of Hydrology: Regional Studies, 64, Article 103234. https://doi.org/10.1016/j.ejrh.2026.103234

Repository Citation

Wang, Y., Goodall, J. L., Kumar, C., McSpadden, D., Barbosa, S. A., Roy, B., Shahabi, A., & Tahvildari, N. (2026). A hybrid CNN-LSTM surrogate model for hyper-resolution spatiotemporal flood forecasting in Norfolk, Virginia. Journal of Hydrology: Regional Studies, 64, Article 103234. https://doi.org/10.1016/j.ejrh.2026.103234