October 8, 2025
Journal Article

A Comparative Study of Physics-Informed and Data-Driven Neural Networks for Compound Flood Simulation at River-Ocean Interfaces: A Case Study of Hurricane Irene

Abstract

Simulating compound flooding (CF) at the river-ocean interface within large-scale Earth System Models (ESMs) presents significant challenges due to complex interactions between river discharge, storm surge and tides. By framing CF simulation as a testbed, this study assesses the comparative advantages of physics-informed and data-driven machine learning (ML) approaches for enhancing local ESM performance. We systematically compare data-driven neural network models (i.e., CNNs, U-Net, LSTM, GRU) and physics-informed neural network (PINN) models, including vanilla PINN and a finite-difference-based PINN (FD-PINN) for CF modeling. Specifically, FD-PINN is introduced to enhance computational efficiency, accelerating vanilla PINNs by ~6.5 times while improving accuracy. To enhance data-driven model training, a new data-generation approach is developed to extract and sample historical fluvial and coastal flood events, which ensures a robust dataset for extreme event prediction. The models are evaluated using a realistic one-dimensional river domain extracted from an ESM’s river mesh and the Hurricane Irene event as an independent test case. Results show that FD-PINN achieves stable and accurate predictions with significantly reduced computational costs relative to vanilla PINNs. Among data-driven models, the best overall performance is achieved by a CNN-LSTM hybrid, which balances accuracy and efficiency. While a fully connected CNN (CNN-FC) provides the best accuracy, it incurs high computational cost. Architectures lacking strong temporal modeling tend to underperform on unseen events. These findings highlight the importance of sequence-aware designs for robust generalization. This study reveals the trade-offs between physics-informed and data-driven models and proposes an adaptive hybrid framework for integrating machine learning into ESMs to enhance local flood simulations.

Published: October 8, 2025

Citation

Feng D., Z. Tan, Z. Lin, D. Xu, C. Yu, and Q. He. 2025. A Comparative Study of Physics-Informed and Data-Driven Neural Networks for Compound Flood Simulation at River-Ocean Interfaces: A Case Study of Hurricane Irene. Journal of Geophysical Research: Machine Learning and Computation 2, no. 4:e2025JH000758. PNNL-SA-211143. doi:10.1029/2025JH000758

Research topics