HYDRA
Hybrid Deep-learning for Residual Analysis
Problem
National water models often struggle with local precision. During events like Hurricane Helene, NWM forecasts significantly underestimated peak flows in complex terrain, leaving communities with uncertain flood warnings.
Why it matters
Achieved up to 48% improvement in predicting streamflow across unregulated Appalachian watersheds. Live at hydramodel.ai. Manuscript in preparation for Water Resources Research (AGU).
Approach
- Developed an advanced 1-million parameter hybrid GRU-Transformer model to catch residuals that physical models miss.
- Integrated multi-source data (NWM v3.0+, ERA5, USGS) for a comprehensive view.
- Designed leakage-safe evaluation to ensure performance holds up in real-time constraints.
- Preparing manuscript for submission to Water Resources Research (AGU).
Stack
PyTorchTransformerHydraMLflowxarrayAWS Batch
Results
- Up to 48% improvement in predictions across unregulated Appalachian watersheds.
- Consistent improvement across varying forecast horizons and extreme storm events.
- Demonstrated stability under seasonal distribution shifts.
What I learned
- Hybrid architectures can correct physical model biases without overfitting.
- Rigorous evaluation design is the difference between a demo and a product.
- Balancing research goals with operational constraints mirrors how ML systems are built in production teams.