Talk by Luca Delle Monache, Scripps Institution of Oceanography UCSD: Dynamical modeling and machine learning for the prediction of extreme events

Seminar Format

Available in-person and via Zoom webinar. Contact the department to subscribe to the email list (zoom link provided in announcement).

Abstract

CW3E mission is to provide 21st Century water cycle science, technology and outreach to support effective policies and practices that address the impacts of extreme weather and water events on the environment, people and the economy of Western North America. To fulfill its mission, CW3E scientists and engineers develop predictive capabilities based on physics-based models as well as machine learning algorithms to provide water managers across the Western US with accurate and reliable estimates of precipitation and other atmospheric and hydrologic variables over their watersheds at the lead times needed for effective operations. In this presentation, I will provide an overview of the computing and dynamical modeling capabilities we are developing at CW3E, which include the Weather Research and Forecast (WRF) atmospheric model that has been optimized for weather prediction in the Western US, called West-WRF, and a regional 200-member ensemble at 9-km resolution. I will then describe the extensive ongoing research and development of machine learning algorithms that leverages the initial dynamical model estimates to further improve it by training over a 34-year deterministic reforecast or 10 months of data from the large ensemble, and novel reanalysis-trained ML-based weather predictions.

Bio

Dr. Luca Delle Monache is the Deputy Director of the Center for Western Weather and Water Extremes (CW3E), Scripps Institute of Oceanography, University of California San Diego. Dr. DelleMonache oversees the development of the Center’s modeling, data assimilation, postprocessing, artificial intelligence, subseasonal-to-seasonal, supercomputing, and atmospheric science capabilities, with the goal of maintaining state-of-the-art predictive capabilities while actively exploring innovative algorithms and approaches. He leads and contributes to the development and implementation of new scientific and programmatic strategies on understanding, observing, and predicting extreme events in Western North America and other regions across the world. He earned a M.S. in Mathematics from the University of Rome, Italy, an M.S. in Meteorology from the San Jose State University, U.S., and a Ph.D. in Atmospheric Sciences from the University of British Columbia, Canada. His interests include the design of ensemble methods, probabilistic prediction and uncertainty quantification, numerical weather prediction, data assimilation, inverse modeling, postprocessing methods including artificial intelligence algorithms, renewable energy, extreme weather and water events, air quality and transport and dispersion modeling. Dr. Delle Monache has been the principal investigator of several multi-institution multi-million projects funded by the National Science Foundation, the National Oceanic and Atmospheric Administration, the National Aeronautics and Space Administration, the Department of Energy, the Department of Defense, and the private sector. Before joining CW3E, he was a postdoc and then a staff scientist at the Lawrence Livermore National Laboratory, Livermore, California (2006-2009), and a project scientist and then the Science Deputy Director of the National Security Applications Program at the National Center for Atmospheric Research, Boulder, Colorado (2009-2018).

Luca Delle Monache, Deputy Director, CW3E-UCSD: [Email: ldellemonache@ucsd.edu | Scripps Institution of Oceanography | Google Scholar]