Feature importance measures for flood forecasting system design
Francesco Cappelli, Flavia Tauro, Ciro Apollonio, Andrea Petroselli, Emanuele Borgonovo, Elena Volpi, Salvatore Grimaldi
Abstract
Effective proxy selection in hydrological processes is crucial in several applications. This study investigates the role of sub-basins in hydrological response, which remains unclear. Our focus is on exploring feature importance measures to identify influential sub-basins in a flood forecasting system. We use the Tiber River basin as a case study and employ a synthetic flood hydrograph dataset, consisting in approximately 20 000 simulated annual maximum hydrographs across 39 sub-basins and the basin outlet. Through this study, we present a proof of concept for ranking sub-basins based on their contribution to basin response using six feature importance measures. The results reveal eight influential sub-basins and provide guidance for strategically installing measurement instrumentation for an efficient and cost-effective flood early warning system.