“…This may have been due to the fact that the representativeness of the forecast dataset is not strong, and that the correlation between the Arid-Pa and runoff series is unstable. In fact, many potential factors are involved in runoff generation (Bafitlhile & Li, 2019), thus the forecasting deviations are unavoidable, and there are many reasons for these deviations. It is worth noting that the model does not select the soil surface characteristics as input factors, which has an impact on runoff generation (Ribolzi et al, 2007), and may even exceed the slope (Descroix, Gonzalez Barrios, Vandervaere, Viramontes, & Bollery, 2002).…”