A coupled hydrologic-machine learning modelling framework to support hydrologic modelling in river basins under Interbasin Water Transfer regimes

Abstract

Interbasin Water Transfer (IWT) is often a complex decision-making process that depends on factors ranging from hydro-meteorological conditions to socio-economic pressures. Hydrologic modelling is particularly challenging under these circumstances, requiring accurate quantitative information which may not always be available. This study proposes a methodological framework to simulate IWT flow contributions in the absence of observational data by introducing a coupled machine learning–hydrologic modelling approach. The proposed methodology employs a hydrologic model to simulate the rainfall-runoff process of a watershed, while a machine learning algorithm is used to simulate the decision-making process of IWTs. Methods are illustrated by simulating the hydrologic balance of the Dese-Zero River Basin (DZRB), a highly artificially modified catchment located in North-East Italy. Results suggest the proposed methodological framework can successfully simulate the complex water flow dynamics of the studied watershed and be a useful instrument to support complex scenario analysis under IWTs data scarce conditions.