Sensitivity Augmented Gradient Exploration (SAGE) for Rapid Model Calibration
Day 1 Session 2 (1:30PM)
Presenters:
Jasper Vrugt (University of California, Irvine)
Jonathan Frame (University of Alabama)
This hands-on workshop introduces the Sensitivity Augmented Gradient Exploration (SAGE) framework for accelerated calibration and uncertainty analysis of hydrologic models. Participants will run calibration experiments using large CAMELS basin datasets, explore parameter sensitivities and uncertainty structures, and examine how high-performance SAGE workflows enable model training and evaluation in minutes rather than days.
The session demonstrates how sensitivity-aware gradient estimation and accelerated calibration methods support rapid experimentation, operational model tuning, and large-scale hydrologic forecasting research. Emphasis is placed on practical workflows that scale efficiently while preserving scientific rigor.
Learning Outcomes:
- Perform rapid hydrologic model calibration using the SAGE framework
- Analyze parameter sensitivities and uncertainty structures in calibrated models
- Run large-scale basin calibration experiments efficiently
- Apply accelerated calibration and sensitivity-analysis methods in operational and research workflows