Using AI to predict the weather

Science Sessions are brief conversations with cutting-edge researchers, National Academy members, and policymakers as they discuss topics relevant to today's scientific community. Learn the behind-the-scenes story of work published in the Proceedings of the National Academy of Sciences (PNAS), plus a broad range of scientific news about discoveries that affect the world around us.

In this episode, researchers discuss advances in AI-enabled weather forecasting.

In this episode, we cover: •[00:00] Introduction •[01:12] Jeffrey Shrader explains what 48 expert forecasters had to say about how weather predictions might further improve through 2100, including the potential role of AI. •[03:43] Ignacio Lopez-Gomez explains how he used generative AI to downscale large-scale earth system models into finer-scale regional climate projections. •[05:35] Xiaofeng Li explains how he used a machine learning model to forecast whether tropical cyclones will rapidly intensify. •[07:40] Hui Su explains what nowcasting is and how her deep diffusion model works. •[09:52] Pedram Hassanzadeh explains what grey swans are and why they may be challenging for AI to predict. •[10:47] Qiang Sun explains how he and his colleagues tested the ability of AI to predict gray swans. •[12:28] Final thoughts and conclusion.

About Our Guests: Jeffrey Shrader Associate Professor of International and Public Affairs Columbia University

Ignacio Lopez-Gomez Research Scientist Google

Xiaofeng Li Research Scientist Institute of Oceanology, Chinese Academy of Sciences

Hui Su Chair Professor Hong Kong University of Science and Technology

Pedram Hassanzadeh Associate Professor University of Chicago

Qiang Sun Research Scientist University of Chicago

Follow us on Spotify, Apple Podcasts, or wherever you get your podcasts for more captivating discussions on scientific breakthroughs!

Visit Science Sessions on PNAS.org: https://www.pnas.org/about/science-sessions-podcast

Follow PNAS: Twitter/X Facebook LinkedIn YouTube Sign up the PNAS Highlights newsletter