HydroORBIT
A physics-informed, multimodal foundation model for continental-scale hydrologic prediction.
Research
Research projects
Foundation models, graph neural networks, and spatiotemporal deep learning for predicting streamflow across space and time, from my current work at Oak Ridge National Laboratory to my doctoral research at Michigan State.
At Oak Ridge National Laboratory
Research Intern, Graduate Research Opportunity Program · 2026 – present
GNNs for Distributed Streamflow
Graph neural networks over the river network, pretrained on National Water Model simulations and fine-tuned on gauges.
Doctoral research
Michigan State University · 2023 – present
HydroTransformer
A transformer framework that learns streamflow from distributed, gridded inputs and generalizes across space and time.
Watershed-Agnostic Forecasting
An explainable, distributed CNN–LSTM hydrologic model that is not tied to a single watershed.
Earlier and applied work
Optimization, computer vision, and industry machine learning
Optimization for Smallholder Farmers
Linear and multi-objective (NSGA-II) optimization balancing cost-effectiveness and nutrition.
Visual Quality Inspection
A transfer-learning architecture for scalable visual quality inspection (ICAI 2022).
Real-time Compliance Monitoring
CNN form detection and OCR over more than 20,000 agent screen recordings.