Tech

UCSD and AI2 compress a century of climate physics into a 25-hour generative forecast

June 15, 2026 · From the archive, written in the Professor's voice before our October 2026 redesign from today.ucsd.edu

What happened

Scientists at UC San Diego and the Allen Institute for AI released Spherical DYffusion, a diffusion model that ingests ERA5 reanalysis and solves the primitive equations on an 0.25-degree spherical grid. The model generated 100-year ensembles at 6-hour resolution using 128 A100 GPUs for 25 wall-clock hours; RMSE against CMIP6 historical runs stayed below 0.8 kelvin for surface temperature. Training used classifier-free guidance with a physics-informed loss term that penalizes divergence of mass and energy.

Why it matters

The result demonstrates that score-based generative models can embed hard physical constraints without hand-coded numerical solvers. Teams forecasting non-stationary systems should replace multi-week HPC queues with fine-tuned diffusion checkpoints when scenario counts exceed a few hundred.

Who's doing it

The Allen Institute for AI's Climate Modeling Group, led by Dr. Yixuan Sun, has open-sourced the 1.2-billion-parameter checkpoint; early adopters at the UK Met Office report a 14-fold reduction in compute cost for regional downscaling experiments.

Try it

1. Navigate to huggingface.co/allenai/spherical-dyffusion and download the model card and config.json.
2. Install the package with pip install dyffusion-climate and run python generate.py --scenario ssp585 --years 2025 2125 --device cuda to produce a 100-year NetCDF output.
3. Open the file in xarray, compute the global mean temperature anomaly relative to 1980-2010, and verify that peak warming lands within 0.3 degrees of the CMIP6 multi-model mean.

Read the original at today.ucsd.edu