Evaluating the Sensitivity of Hydrological Models to Remotely Sensed Precipitation in a Transboundary Basin

Accurate precipitation data is vital for hydrological modelling, particularly in transboundary basins with scarce hydro-climatic stations. This study evaluates the performance of 20 gridded precipitation products (GPPs), derived from remotely sensed data and reanalyses, in the transboundary Lake Titicaca basin. The methodology integrates two approaches: first, a spatial and temporal accuracy assessment of the GPPs, and second, their application as input data in hydrological models.

For spatial accuracy, annual precipitation maps were generated for each GPP, preserving their native resolution, and compared with gauge-based maps. Temporal accuracy was assessed using Taylor diagrams. To evaluate the impact of GPPs on hydrological modelling, streamflow simulations were performed using the GR4J (lumped) and MGB-IPH (semi-distributed) models for three sub-basins, with model performance assessed through Kling-Gupta Efficiency (KGE).

Results indicate that CHIRPS, IMERG, and MSWEP excel in spatial and temporal accuracy, capturing the north-to-south precipitation gradient shaped by Andean topography. Streamflow simulations showed that GPPs often outperform gauge-based precipitation in basins with uneven station distribution. In GR4J, MSWEP and CHIRPS yielded the highest KGE values across all sub-basins, while in MGB-IPH, SM2Rain_CCI and IMERG-FR performed best. Notably, the higher KGE scores observed for the GR4J model can be attributed to its lumped structure, which compensates for GPP over/under estimations and spatial distribution inconsistencies.

This comprehensive evaluation demonstrates the potential of remotely sensed precipitation products to address data scarcity in transboundary basins. By improving streamflow simulations, these products support informed water resource management, climate adaptation, and transboundary collaboration.