ACE

A 200M-parameter, autoregressive machine learning emulator of an existing comprehensive 100-km resolution global atmospheric model.
https://github.com/ai2cm/ace

Category: Atmosphere
Sub Category: Atmospheric Composition and Dynamics

Keywords from Contributors

climate-modeling climate atmospheric-modeling

Last synced: about 1 hour ago
JSON representation

Repository metadata

Ai2 Climate Emulator: fast machine learning models for weather and climate prediction

README.md

Docs
PyPI
Model checkpoints
Open In Colab

Ai2 Climate Emulator

Ai2 Climate Emulator (ACE) is a fast machine learning model that simulates global atmospheric variability in a changing climate over time scales ranging from hours to centuries. This repository contains the fme python package which can be used to train, run and evaluate weather and climate AI models such as ACE. It also contains the data processing scripts and model configurations used in recent papers published by the Ai2 Climate Modeling group.

Installation

pip install fme

Documentation

See complete documentation here and a quickstart guide here.

Model checkpoints

Pretrained model checkpoints are available in the ACE Hugging Face collection.

Papers

The following papers described models trained using code in this repository.

  • "ACE: A fast, skillful learned global atmospheric model for climate prediction" (link)
  • "Application of the Ai2 Climate Emulator to E3SMv2's global atmosphere model, with a focus on precipitation fidelity" (link)
  • "ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses" (link)
  • "ACE2-SOM: Coupling an ML Atmospheric Emulator to a Slab Ocean and Learning the Sensitivity of Climate to Changed CO2" (link)
  • "Applying the ACE2 Emulator to SST Green's Functions for the E3SMv3 Global Atmosphere Model" (link)
  • "SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulators" (link)
  • "HiRO-ACE: Fast and skillful AI emulation and downscaling trained on a 3 km global storm-resolving model" (link)
  • "FloeNet: A mass-conserving global sea ice emulator that generalizes across climates" (link)

⚠️ Important migration notice

This repository had a breaking history change on the main branch in December 2025 as part of our transition to open development. If you have an existing clone from before this migration, you will need to take action.

See MIGRATION.md for complete instructions.

  • If you have no local work to preserve: delete your local clone and re-clone the repository
  • If you have local branches or commits: follow the detailed migration steps in MIGRATION.md

Owner metadata


GitHub Events

Total
Last Year

Committers metadata

Last synced: 2 days ago

Total Commits: 1,823
Total Committers: 25
Avg Commits per committer: 72.92
Development Distribution Score (DDS): 0.671

Commits in past year: 642
Committers in past year: 16
Avg Commits per committer in past year: 40.125
Development Distribution Score (DDS) in past year: 0.65

Name Email Commits
Jeremy McGibbon m****n@u****u 599
Oliver Watt-Meyer o****t@g****m 292
James Duncan j****3 186
Anna Kwa a****k@a****g 178
Gideon Dresdner g****d@a****g 155
Brian Henn b****n@a****g 103
Spencer Clark s****k@g****m 83
Elynn Wu e****0@g****m 73
W. Andre Perkins f****e@g****m 71
Troy Arcomano t****a@a****g 28
Anna Dodson 1****n 11
Naser Mahfouz n****z@p****v 8
rebassoo r****o 8
Alexey Yermakov 4****a 4
Surya Dheeshjith 4****h 4
William Yik y****l@g****m 4
Will Gregory W****y@o****m 4
Gideon Dresdner g****d@g****m 2
Jaideep j****k@n****m 2
Finn Rebassoo r****o@l****n 2
Finn Rebassoo r****o@l****n 2
Copilot 1****t 1
Finn Rebassoo r****o@l****n 1
Finn Rebassoo r****o@l****n 1
dependabot[bot] 4****] 1

Committer domains:


Issue and Pull Request metadata

Last synced: 2 days ago

Total issues: 53
Total pull requests: 292
Average time to close issues: 3 months
Average time to close pull requests: 7 days
Total issue authors: 23
Total pull request authors: 16
Average comments per issue: 1.68
Average comments per pull request: 0.75
Merged pull request: 144
Bot issues: 0
Bot pull requests: 0

Past year issues: 40
Past year pull requests: 251
Past year average time to close issues: 12 days
Past year average time to close pull requests: 9 days
Past year issue authors: 16
Past year pull request authors: 14
Past year average comments per issue: 1.58
Past year average comments per pull request: 0.81
Past year merged pull request: 107
Past year bot issues: 0
Past year bot pull requests: 0

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/ai2cm/ace

Top Issue Authors

  • jpdunc23 (12)
  • brianhenn (7)
  • spencerkclark (4)
  • oliverwm1 (3)
  • pzharrington (2)
  • elynnwu (2)
  • frodre (2)
  • mcgibbon (2)
  • yyexela (2)
  • Z-Richard (2)
  • mahf708 (2)
  • RowenXu (2)
  • Arcomano1234 (1)
  • Zappandy (1)
  • patricia-ternes (1)

Top Pull Request Authors

  • mcgibbon (104)
  • jpdunc23 (39)
  • oliverwm1 (30)
  • frodre (23)
  • elynnwu (19)
  • AnnaKwa (18)
  • brianhenn (15)
  • Arcomano1234 (12)
  • yyexela (11)
  • spencerkclark (9)
  • mahf708 (3)
  • William-gregory (3)
  • yikwill (2)
  • glwagner (2)
  • odiazib (1)

Top Issue Labels

  • bug (5)
  • enhancement (3)
  • ready-for-agent (3)
  • good first issue (1)

Top Pull Request Labels


Package metadata

proxy.golang.org: github.com/ai2cm/ace

  • Homepage:
  • Documentation: https://pkg.go.dev/github.com/ai2cm/ace#section-documentation
  • Licenses:
  • Latest release: v2026.5.1+incompatible (published about 2 months ago)
  • Last Synced: 2026-07-03T03:02:08.387Z (1 day ago)
  • Versions: 5
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Rankings:
    • Dependent packages count: 0.976%
    • Average: 1.008%
    • Dependent repos count: 1.04%
pypi.org: fme

Train and evaluate weather/climate model emulators

  • Homepage: https://github.com/ai2cm/ace
  • Documentation: https://ai2-climate-emulator.readthedocs.io/
  • Licenses: Apache Software License
  • Latest release: 2026.5.1 (published about 2 months ago)
  • Last Synced: 2026-07-02T01:01:45.872Z (2 days ago)
  • Versions: 8
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 533 Last month
  • Rankings:
    • Dependent packages count: 10.224%
    • Average: 33.883%
    • Dependent repos count: 57.542%
  • Maintainers (3)

Dependencies

.github/workflows/pre-commit.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
docker/Dockerfile docker
  • nvcr.io/nvidia/pytorch 22.08-py3 build
scripts/data_process/requirements-coupled.txt pypi
  • cftime *
  • click *
  • dacite *
  • dask *
  • fsspec *
  • gcsfs *
  • h5netcdf *
  • pandas *
  • pyyaml *
  • scipy *
  • xarray >=2025.1.2
  • xpartition >=2025.3.0
  • zarr >=3.0.3
scripts/era5/Dockerfile docker
  • continuumio/miniconda3 24.1.2-0 build
pyproject.toml pypi
.github/workflows/docs.yaml actions
  • actions/cache v4 composite
  • actions/checkout v3 composite
  • actions/deploy-pages v4 composite
  • actions/setup-python v4 composite
  • actions/upload-pages-artifact v3 composite
.github/workflows/tests.yaml actions
  • actions/cache v4 composite
  • actions/checkout v3 composite
  • actions/setup-python v4 composite
scripts/era5/dataflow-requirements.txt pypi
  • apache_beam ==2.54.0
  • cftime *
  • dask *
  • gcsfs *
  • h5netcdf *
  • numpy *
  • scipy *
  • xarray *
  • xarray_beam *
  • zarr *
requirements-healpix.txt pypi
scripts/data_process/requirements-atmosphere.txt pypi
  • beaker-py *
  • cftime *
  • click *
  • dacite *
  • dask *
  • fsspec *
  • gcsfs *
  • pyyaml *
  • scipy *
  • xarray >=2025.1.2
  • xpartition >=2025.3.0
  • zarr >=3.0.3
scripts/data_process/requirements-healpix.txt pypi
scripts/era5/environment.yaml conda
  • metview-batch
  • pip
  • python 3.9
.github/workflows/beaker.yaml actions
  • actions/checkout v3 composite
  • allenai/beaker-run-action v1.2 composite
scripts/data_process/requirements-ocean.txt pypi
  • dacite *
  • dask *
  • gcsfs *
  • h5netcdf *
  • xgcm *
  • xpartition >=0.2.2

Score: 15.524033335288529