Flood risk mitigation in small catchments using an early-warning system based on machine learning models

Abstract In consideration of ongoing climate changes, it has been necessary to provide new tools capable of mitigating hydrogeological risks. These effects will be more marked in small catchments, where the geological and environmental contexts do not require long warning times to implement risk mitigation measures. In this context, deep learning models can be an effective tool for local authorities to have solid forecasts of outflows and to make correct choices during the alarm phase. However, in small river basins, model uncertainty appears to play an important role. In this study, we address this issue by providing machine learning models able to estimate uncertainty on the basis of the observed hydrometric height. Once the deep learning models have been trained, their application is purely objective and very rapid, permitting the development of simple software that can be used even by lower skilled individuals.