Dorian Abbot
University of Chicago, IL·Earth & Environmental Science
Heat waves and cold snaps are rare, but they have major effects on society. Estimating how often such extremes occur is hard.
- Fields
Earth & Environmental Science
Computer Science
Mathematics & Statistics
- Topics
extreme weather
climate extremes
heat waves
- Grants
- 1 known grant, through Sep 2027
What they work on
- Develop AI Dynamic Galerkin Approximation (AI-DGA) to estimate long return periods, the typical time between extreme events, for heat waves and cold snaps from large ensembles of short AI emulator runs.
- Build AI-RES, a hybrid loop that combines rare-event sampling with numerical climate solvers and AI emulators to produce additional return-period estimates for extreme temperature events.
- Use the extra rare-event data produced by AI-RES to retrain AI emulators, so they perform better on extremes they never saw in training even when they are unreliable over long simulations.
More about the research
AI is changing climate science, but AI models learn from examples, and their training data contain too few rare events to learn them well. This collaborative project brings together AI, mathematics and climate science to develop the mathematical tools needed to use AI to estimate rare-event statistics, in climate and other fields.
Why it matters
Better estimates of how often extreme heat waves and cold snaps occur could help communities and planners prepare for weather extremes that have major societal impacts. The methods could also make AI emulators more useful across climate science and geoscience for studying rare events that are poorly represented in available data.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Jonathan Weare
New York University, NY·Mathematics & Statistics
Develop schemes that estimate dynamical statistics such as mean first-passage times and committors from datasets of short molecular dynamics trajectories, avoiding the need for trajectories long enough to contain the rare event.
Lantao Sun
Colorado State University-Fort Collins, CO·Earth & Environmental Science
Determine how much Arctic sea ice loss affects summer atmospheric circulation and the jet stream, and through what mechanisms, using DAMIP and PAMIP climate model simulations.
Imme Ebert-Uphoff
Colorado State University-Fort Collins, CO·Earth & Environmental Science
Build simple, interpretable AI models that map large-scale environmental variables from reanalysis products to satellite-derived cloud properties, and use them to estimate cloud variability before the satellite era.
The school
University of Chicago: 39 labs on PI Pages, $681M a year on research, 457 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.