[PAOCQ] Laure Zanna (NYU)

“Building AI Climate Models for Scientific Discovery”

Scientists use computer simulations to understand how different parts of the Earth’s system interact, or to explore how they respond to external forcing. These simulations have been carried out using numerical models (global climate models, or GCMs). Recently, modern machine-learning-based emulators have been used to reproduce the same dynamics using data. I will present the first-generation AI digital twin of the climate system, using data from state-of-the-art GCMs. These AI emulators can simulate the climate system 100x faster than typical GCMs on a single GPU. We will discuss how we build, evaluate, and leverage these emulators to make discoveries about the climate system.

PAOC Colloquium —

Interdisciplinary seminar series that brings together the whole PAOC (Program in Atmospheres, Oceans, and Climate) community. Seminar topics include all research concerning the physics, chemistry, and biology of the atmospheres, oceans and climate, as well as talks about societal impacts of climatic processes.

Contact: paoc-colloquium-comm@mit.edu