A deep learning model of river water levels

At the national level in Italy the FloodPROOFs hydrological forecasting chain is operational for flood forecasting, monitoring and emergency management. It is based on the physically based and spatially distributed hydrological model Continuum. While highly reliable, such modelling chains are often computationally demanding, posing limitations for rapid simulations and large-scale operational applications. 

To investigate whether artificial intelligence can support flood forecasting and support and integrate FloodPROOFs with comparable or better skill while significantly reducing computational costs, this study presents an AI-based framework for river water-level emulation designed for operational flood monitoring. The framework integrates a limited yet heterogeneous set of data sources typically available in real-time contexts, including topographic information derived from Digital Elevation Models, meteorological forcings from in situ measurements (precipitation and air temperature), and observed river water levels provided by the National System of Civil Protection and shared in myDEWETRA platform. 

 Convolutional Neural Networks are employed to capture the nonlinear spatial and temporal interactions between terrain characteristics, atmospheric forcing, and hydrological response. The model is trained and fine-tuned using observed water-level time series, enabling the direct simulation of river stage dynamics and the detection of critical threshold exceedances relevant for civil protection warning procedures. 

The proposed framework operates at high spatial resolution over the Italian peninsula while maintaining low computational requirements, making it suitable for near-real-time applications at the centre of the work of the Italian Civil Protection. Its demonstrated generalization capability allows deployment across multiple spatial scales, from individual catchments to regional and national domains. Overall, the results highlight the potential of AI-driven emulators as complementary tools to traditional hydrological modelling chains, enhancing the efficiency and robustness of operational flood forecasting and decision-support systems for civil protection services.