Presenter: Y. Qiang Sun, Research Scientist, University of Chicago

Description: AI models produce skillful weather forecasts, including for some extreme events. However, forecasting the strongest events that are so rare they did not exist in the training set (the so-called gray swans) remains a major concern for these models’ operational use, especially as climate change introduces unprecedented conditions. In this work, we train an AI weather model after removing Category 3-5 tropical cyclones from its training set and test it on Category 5 storms. The model could not accurately forecast these unseen cyclones. However, the model shows promise in learning from strong storms in one region and forecasting them in another region. This is encouraging and surprising because regional information is implicitly encoded in inputs. Our work highlights the need for better understanding the limitations of AI weather models and innovations to improve them

Bio: As an atmospheric researcher, I possess a keen interest in extreme weather events and the mysteries of the chaotic Earth system. Prior to joining the University of Chicago, I held the position of Research Scientist at Rice University and was a Postdoctoral Research Associate at the Geophysical Fluid Dynamics Laboratory (GFDL). I earned my Ph.D. in Meteorology and Atmospheric Science from The Pennsylvania State University in 2017.

Hosted by: Professor Ashesh Chattopadhyay 

Zoom link:

https://ucsc.zoom.us/j/3489924873?pwd=T0R5VTNFdHZiOG5HMUw0R1VHaGZpQT09