Guiding future global temperature distributions with simulations and observations
physics.ao-ph, cs.LG
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/mandt-lab/gdso
License: http://creativecommons.org/licenses/by/4.0/
The gist: Assessing climate risks requires projections of daily temperature distributions, including rare and spatially widespread extremes.
Abstract
Assessing climate risks requires projections of daily temperature distributions, including rare and spatially widespread extremes. Climate simulations are costly and biased, while correcting them toward observations risks suppressing inter-model differences. We train a single machine-learning emulator, a conditional diffusion model, on seventeen CMIP6 models and ERA5 reanalysis to generate spatially coherent daily temperature fields conditioned on model identity, date, and CO2-equivalent concentration. At sampling time, diffusion guidance reduces model biases by steering each emulated climate-model distribution toward observations, with its strength selected through perfect-model experiments using withheld simulated futures. Observational influence decreases with projection horizon and forcing. Across seventeen synthetic targets, guidance more than halves median biases in the 1st and 99th percentiles of daily temperature, improves probabilistic scores and reliability, and reduces median annual global-mean temperature RMSE by 32-57% across three emission scenarios. In a detailed benchmark, guidance also outperforms established bias corrections on daily-field probabilistic scores. Efficient sampling generates large ensembles without further climate simulations. For example, our framework corrects CMIP6's roughly threefold historical overestimate of extreme-heat coverage, yet projects that concurrent extremes will affect nearly half of global land on a typical day in the 2080s under SSP3-7.0.
Sources
- Emulating the Forced Response of Climate Models with Generative Machine Learning
- Climate in a Bottle: Towards a Generative Foundation Model for the Kilometer-Scale Global Atmosphere
- Technical Report: Towards Unified Diffusion Models for Multi-Model Climate Emulation at Scale
Related papers
- Anthropogenic Heat in Urban Climate Systems: Forcing, Sensitivity, and Feedback
- NORi: An ML-Augmented Ocean Boundary Layer Parameterization
- A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modeling
- Quantifying AI data center nitrogen oxide (NO x) emissions from space
- Skillful Thunderstorm Forecasts Learned Directly from Observations
- Wind vector retrieval from miniaturized wave-enabled sea-surface drifters