GraphCast: Learning skillful medium-range global weather forecasting

Ferran Alet, Google Deepmind
web.mit.edu/alet/www/
Slides and Summary:
sites.google.com/modelingtalk...
Abstract:
Global medium-range weather forecasting is critical to decision-making across many social and economic domains. Traditional numerical weather prediction uses increased compute resources to improve forecast accuracy, but cannot directly use historical weather data to improve the underlying model. We introduce a machine learning-based method called “GraphCast”, which can be trained directly from reanalysis data. It predicts hundreds of weather variables, over 10 days at 0.25° resolution globally, in under one minute. We show that GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets, and its forecasts support better severe event prediction, including tropical cyclones, atmospheric rivers, and extreme temperatures. GraphCast is a key advance in accurate and efficient weather forecasting, and helps realize the promise of machine learning for modeling complex dynamical systems.
Bio:
Ferran Alet is a Research Scientist at Google DeepMind working on ML for Science, particularly weather forecasting and mathematics. His research leverages techniques from meta-learning and program synthesis, and insights from mathematics and the physical sciences. He completed his PhD at MIT CSAIL advised by Leslie Kaelbling, Tomas Lozano-Perez, and Joshua Tenenbaum. During his PhD, he created the MIT Embodied Intelligence Seminar, mentored 17 students, and won the MIT Outstanding Mentor award 2021. Ferran studied mathematics and physics in Barcelona thanks to CFIS, a program for doing two degrees, where he was the valedictorian of his promotion. In grad school, he earned a “La Caixa” fellowship and was responsible for the high-level planner of the MIT-Princeton team for the Amazon Robotics Challenge, which won the stowing task in 2017. You can find more information and papers at web.mit.edu/alet/www

[@superkaran20]

Thanks for the talk, it was very helpful, but i didn't get what is opreational analysis ground truth at 31:50 time stamp.

[@nkhgs3392]

Is there any guidance on how to interpret the output it provides? It would be a cool project to build a site which uses the data.

[@anonymousanon4822]

I have a question about the surface temperature bias visualization. You can see some areas are "blinking" because the bias seems to have significant differences in magnitude depending on the point in time. Does this again have to do with the assimilation windows? Why is specifically Angola, India and the australian outback blinking so much? It seems to correlate with magnitude as one can see north america and europe starting to blink as magnitude increases as well but antarctica for example doesn't blink at all despite having the highest bias.

[@ajitabhkumar5449]

Great talk. Thanks!