Combining Machine Learning and Process-Based Modelling for Sediment Load Estimation in the Data-Scarce Upper Blue Nile Basin

The Upper Blue Nile Basin contributes about 60% of the Nile River’s annual streamflow but faces severe sediment-related challenges driven by intense monsoonal erosion and reservoir siltation. Accurate estimation of suspended sediment concentration (SSC) and sediment load in large, data‑scarce watersheds remains difficult due to sparse monitoring and complex supply‑limited transport dynamics. This study develops a hybrid approach that combines machine‑learning‑based reconstruction of SSC with process‑based hydrological and sediment modelling for the Kessie watershed, a major sediment source upstream of the GERD. The approach combines Random Forest (RF) based SSC reconstruction from only 251 sparse samples with a two-stage calibration of the WASA-SED model. Using hydrologically informed predictors, the RF algorithm substantially outperformed traditional sediment rating curves and other machine‑learning algorithms, increasing the coefficient of determination from 0.23 to 0.693. The reconstructed daily SSC yielded a mean annual sediment load of 180.7 Mt/yr. The model performed well, particularly at monthly scales for 1995–2011, and reproduced dominant hydrological and sediment regimes. Trend analysis indicated no significant changes in rainfall, streamflow, or sediment load. The combining approach captures monsoon‑driven sediment fluxes and provides reliable sediment load estimates that support improved reservoir sedimentation assessment, erosion-risk evaluation, and transboundary water‑resources planning in data‑scarce tropical highlands.