My research focus centers on the critical intersection of artificial intelligence and hydrological sciences, addressing the development and application of advanced machine learning methodologies for complex water systems analysis and prediction. Research expertise encompasses physics-informed machine learning approaches, including physics-informed neural networks (PINNs) and neural ordinary differential equations, which integrate fundamental hydrological principles with data-driven insights. Work extends to explainable AI techniques, particularly SHAP analysis and attention mechanisms, to enhance model interpretability and understanding of decision-making processes in hydrological applications. Work encompasses multiple scales of hydrological modeling, from local watershed management to regional water resource systems, with particular emphasis on spatiotemporal deep learning for water quality prediction and environmental system analysis.