Interrogating process deficiencies in large-scale hydrologic models with interpretable machine learning

Abstract. Large-scale hydrologic models are increasingly being developed for operational use in the forecasting and planning of water resources. However, the predictive strength of such models depends on how well they resolve various functions of catchment hydrology, which are influenced by gradients in climate, topography, soils, and land use. Most assessments of these hydrologic models has been limited to traditional statistical approaches. The rise of machine learning techniques can provide novel insights into identifying process deficiencies in large-scale hydrologic models. In this study, we train a random forest model to predict the Kling-Gupta Efficiency (KGE) of National Water Model (NWM) and National Hydrologic Model (NHM) predictions for 4,383 streamgages across the conterminous United States. Thereafter, we explain the local and global controls that 48 catchment attributes exert on KGE prediction using interpretable Shapley values. Overall, we find that soil water content is the most impactful feature controlling successful model performance, suggesting that soil water storage is difficult for hydrologic models to resolve, particularly for arid locations. We identify non-linear thresholds beyond which predictive performance decreases for NWM and NHM. For example, soil water content less than 210 mm, precipitation less than 900 mm/yr, road density greater than 5 km/km², and lake area percent greater than 10 % contributed to lower KGE values. These results suggest that improvements in how these influential processes are represented could result in the largest increases in predictive performance of NWM and NHM. This study demonstrates the utility of interrogating process-based models using data-driven techniques, which has broad applicability and potential for improving the next generation of large-scale hydrologic models.