Multi-step ahead streamflow and uncertainty forecasting using a HyMoLAP rainfall-runoff model-based framework integrated with Bayesian neural networks in the Ouémé river basin, Benin

PLOS ONE, 20, e0333590 (2025)

Links: DOI

Summary. Couples the HyMoLAP conceptual rainfall–runoff model with Bayesian neural networks to produce multi-step ahead streamflow forecasts for the Ouémé river basin, combining process-based hydrology with machine learning while retaining calibrated uncertainty estimates.