Open access
Aug 2026
Physics-informed hybrid GR4J–XGBoost model for streamflow prediction: integrating conceptual states, SHAP interpretability, and uncertainty analysis
This study proposes a physics-informed hybrid modeling framework that integrates the GR4J conceptual model with the XGBoost machine learning algorithm, enabling a process-based representation of catchment dynamics within the machine learning framework.
Ozgur Kisi, S. Heddam, K. Parmar et al.
· Scientific Reports · 0 citations