Three core research areas — Catchment Hydrology, Large-Scale Modeling, and AI/ML for Hydrology — integrating observations, physics-based models, and machine learning to advance water science.
My research program spans catchment-scale ecohydrology, continental-to-global modeling, and AI-driven hydrological prediction — grounded in 20+ peer-reviewed publications.
Investigating water balance, ecohydrological processes, and sediment dynamics at the catchment scale — linking vegetation productivity, drought propagation, and flood frequency to landscape and climatic controls.
Developing and advancing continental-to-global hydrological and earth system models — coupling land, river, and reservoir components to simulate water, carbon, and sediment cycles under climate change.
Applying machine learning and deep learning to advance hydrological prediction, parameter estimation, and water systems optimization — from ML-derived geospatial datasets to physics-informed neural networks and reinforcement learning for reservoir operations.
A convergent science approach that bridges computation, observation, and theory across spatial and temporal scales.
Harnessing GRACE-FO, MODIS, Landsat, and Sentinel to constrain models with multi-scale observations of water storage, evapotranspiration, and land cover change.
Running E3SM, VIC, and MOSART at regional-to-global scales on national supercomputing facilities (NERSC, Perlmutter) to simulate water cycle dynamics.
Embedding deep learning within physical model frameworks — using neural networks to learn residuals, emulate expensive computations, and improve predictions.
Translating scientific outputs into actionable frameworks — reservoir operating rules, early warning systems, and policy-relevant metrics for water managers.
Working across disciplinary boundaries with hydrologists, climate scientists, economists, and policy experts to tackle complex socio-environmental challenges.
Committed to reproducible research — publishing code, data, and workflows on GitHub to advance transparency and accelerate scientific progress in the community.
Primary affiliation — HORA Lab
E3SM Earth System Model project
GRACE-FO data assimilation
High-performance computing
Interested in collaborating on research in hydrology, AI/ML, or water systems?
Get in TouchSite Visitors