Two integrated conceptual–wavelet-based data-driven model approaches for daily rainfall–runoff modelling

Abstract Rainfall–runoff modelling is crucial for enhancing the effectiveness and sustainability of water resources. Conceptual models can have difficulties, such as coping with nonlinearity needing more data, whereas data-driven be deprived reflecting physical process basin. In this regard, two hybrid model approaches, namely Génie Rural à 4 paramètres Journalier (GR4 J)–wavelet-based (i.e., wavelet-based genetic algorithm–artificial neural network (WGANN); GR4 J–WGANN1 J–WGANN2), were implemented to improve daily rainfall–runoff modelling. The novel includes outflow (QR) direct flow (QD) obtained from J model, J–WGANN2 soil moisture index (SMI) input data. models, wavelet analysis Boruta algorithm decompose data select components. Four gauging stations in Eastern Black Sea Kızılırmak basins Turkey used observe performance. exhibited poor performance extreme forecasting. approach performed better than improved up 40% compared model. integrated conceptual–wavelet-based useful improving conceptual performance, especially regarding