Rosenberg Institute Seminar Series - Laurel Larsen
Laurel Larsen, Associate Professor/Delta Lead Scientist, UC Berkeley/Delta Stewardship Council
Can a machine become a hydrologist? Integrating physical understanding with deep learning to develop practical and trustworthy hydrologic forecasts
With watersheds experiencing unprecedented shifts in climate and hydrology, developing more accurate forecasts of streamflow has become paramount. Legacy forecasting systems used by public agencies do not harness the power of deep learning models because they are perceived as black boxes. However, more recently, hydrologists and computational scientists have been developing hybrid approaches to integrating physical understanding with deep learning to harness the latter’s predictive power while infusing it with physical grounding. In this talk I dive into recent work by the Environmental Systems Dynamics Laboratory to develop deep-learning and hybrid forecasts for streamflow and nitrate across a range of watersheds in the US. Results yield insight into watershed characteristics that result in better or worse predictivity under different forecasting strategies. We find that generally, combining physical understanding with deep learning produces more generalizable, physically consistent models with performance similar to that of pure deep-learning models.
Dr. Laurel Larsen is an Associate Professor at UC Berkeley with appointments in the Departments of Geography and Civil and Environmental Engineering. Dr. Larsen leads the Environmental Systems Dynamics Laboratory at Berkeley, which is tackling challenges of streamflow forecasting and teasing out understanding of how physics, biology, and human systems interact to influence conservation and restoration objectives. Her research has focused on the Everglades, Chesapeake Bay, and coastal Louisiana, as well as California ecosystems. For 2020-2023, she is serving as the Delta Lead Scientist with the Delta Stewardship Council in Sacramento, CA.