The Climate Analytics Lab aims to reduce uncertainty in the role of anthropogenic aerosol on the climate by exploiting recent advances in machine learning to enable improved projections and gain new insights from observations.

Project Highlights

JAX-GCM differentiable climate model

JAX-GCM

A fully differentiable climate model enabling ML-enhanced climate science and gradient-based optimization.

Learn more

GAIA Initiative

GAIA Initiative

Harnessing AI to understand, forecast, and steward Earth’s complex systems through interdisciplinary collaboration.

Learn more

Global temperature map

ClimateBench

A benchmark dataset for the emulation of full-complexity climate models.

Learn more

News

  • 25/10 - New papers: Jorge Baño-Medina recently published three excellent papers building large ensembles of AI weather models, their use for attribution, and how well they represent atmospheric physics. It was a pleasure working with him on them!
  • 25/04 - Our new paper “Integrating Top‐Down Energetic Constraints With Bottom‐Up Process‐Based Constraints for More Accurate Projections of Future Warming” has been published in Geophysical Research Letters.
  • 25/03 - Congratulations to Zoe Ludena, Eric Pham, and Ylesia Wu for winning the best Capstone Project award at the 2025 UCSD Data Science Showcase! Read more about their ‘SeeRise’ project here and interact with their app here. Well done!! 🎉
  • 25/01 - PI Watson-Parris was awarded an NSF CAREER award exploring “The Large-scale Buffering of Shallow Cloud Perturbations”. We’re excited to start this new project, which will focus on understanding the role of shallow clouds in the climate system and their response to anthropogenic perturbations 🎉
  • 24/11 - New research in Science which uncoverd a new mechanism of cloud reduction through aerosol pollution was highlighted in UCSD Today!
Show more