High-Performance Full-Scale Urban Flood Prediction: A Scalable Solution for Dynamic Inundation Mapping

Floods pose a significant threat to urban areas due to their high population densities and extensive infrastructure, a vulnerability exacerbated by climate change, rapid urbanization, and the proliferation of impermeable surfaces. While traditional flood prediction efforts have focused on maximum inundation depths, dynamic flood inundation mapping has gained prominence for its ability to provide detailed insights into flood timing, duration, and progression, which are critical for effective emergency response, infrastructure planning, and resilience-building. The integration of high-resolution Digital Elevation Models (DEMs) has improved modeling accuracy by capturing intricate urban topographies, but this advancement has introduced substantial computational challenges, particularly for large-scale, fine-resolution simulations using physics-based hydrodynamic models. Convolutional neural networks (CNNs), particularly U-Net, have shown promise in flood prediction due to their ability to handle complex segmentation tasks and varying input sizes; however, scaling these models to handle large datasets with meter-scale resolutions remains computationally intensive. Addressing this challenge, this study develops a novel approach to predict dynamic flood maps for a large urban area at 10-meter resolution (~10⁶ cells) by dividing the area into smaller tiles for U-Net training, leveraging a comprehensive rainstorm-inundation database (200 cases) created through 2D hydrodynamic simulations, and integrating results into a surrogate model. This innovative framework delivers accurate and rapid predictions of flood dynamics, including spatial extent, depth, and temporal evolution, providing essential tools for urban flood risk management and mitigation strategies. For training, validation, and testing of the U-Net model, 160, 30, and 20 cases were used, respectively. The RMSE, CSI, and POD metrics were used to evaluate the model's performance on the validation and test datasets. The results show high performance for validation with RMSE, CSI, and POD values of 0.015, 0.92, and 0.74, respectively, and for testing with values of 0.017, 0.90, and 0.81, respectively.