Hydrological Modeling with Deep Learning
University of California Davis
Tuesday, Apr 06, 2021, 2:00 pmGoToMeeting:
Access Code: 343-392-437
The Hydrology community has known for several decades that machine learning provides better predictions of most hydrological states and fluxes than both calibrated conceptual models and process-based models. This talk will cover recent progress in developing hydrological modeling capacity with deep learning, including: (1) prediction in extrapolation, (2) methods of uncertainty quantification, (3) data assimilation, (4) multi-timescale modeling, (5) leveraging ensembles of forcing products, (6) interpretability of deep learning models, and (7) knowledge-guided machine learning for hydrological modeling.
Speaker Bio: Grey Nearing received a PhD in Hydrology and Water Resources from the University of Arizona in 2013. He was formerly part of model development teams as NASA and NCAR, and an assistant Professor at the University of Alabama. He is currently an Assistant Professor at the University of California Davis and visiting faculty at Google Research.