Convolutional neural network model for rapid prediction of urban flash flood water depth and velocity maps

Urbanization and climate change have intensified the need for rapid and accurate predictions of flash floods, especially in urban areas. Although numerical models produce accurate predictions, their computational cost makes them impractical for real-time simulations. Several machine learning models have been proposed as surrogates for such applications. However, most models focus only on predicting water depths and have little insight into the required variety and amount of data to train such models. In this study, we present a Convolutional Neural Network (CNN) surrogate model designed to predict both water depths and flow velocities for urban pluvial flooding, using as inputs a rainfall hyetograph and seven hydro-morphological descriptors, such as aspect, curvature, slope, Manning’s roughness coefficient, topographic wetness index, flow accumulation, and digital terrain model. To train and test our approach, we considered a dataset of numerical simulations carried out using a 2D shallow-water hydrodynamic modeling in the city of Matera, Italy. For the physical-based simulations, we considered several rainfall hyetographs, either obtained from real events or derived from design scenarios for different return periods, and simulated the associated pluvial floods propagation extracting as outputs the corresponding maps of the maximum envelope of the water depths and flow velocities. The CNN model obtained a testing 0.37 cm mean absolute error (MAE), 1.7 cm root mean squared error (RMSE), and 0.80 critical success index (CSI) for water depth predictions, and 0.054 m/s MAE, 0.178 m/s RMSE, and 0.84 CSI for flow velocity predictions. The CNN model was 116.5 times faster than the physically-based hydrodynamic model using the same computational hardware. We also analyzed the effect of different combinations of rainfall events to train and validate the CNN model, showing that it benefits from a balanced dataset in terms of different return periods and presence of both synthetic and real hyetographs. We then employed the model to extrapolate urban flooding for higher return periods (200, 300, 500, and 1000 years), showing that the model can predict well severe extreme events, as highlighted by a high correlation between predicted maximum water volumes and total rainfall. This study contributes to the practical usability of deep learning models by providing essential support for real- time or low lead-time urban flash flood predictions, which are crucial for effective early warning and emergency management.