Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 29 min ago
Peer-reviewedCC BYGeophysical Research Letters

SamudrACE: Fast and Accurate Coupled Climate Modeling With 3D Ocean and Atmosphere Emulators

  • James Duncan1
  • Elynn Wu1
  • Surya Dheeshjith2
  • Adam Subel2
  • Troy Arcomano1
  • Spencer Koncius Clark1,3
  • Brian Henn1
  • Anna Kwa1
  • Jeremy McGibbon1
  • W. A. Perkins1
  • William King Gregory4
  • Carlos Fernandez‐Granda5,2
6 more authors
  • Julius J. M. Busecke2,6
  • Oliver Watt‐Meyer1
  • William J. Hurlin3
  • Alistair Adcroft4
  • Laure Zanna5,2
  • Christopher S. Bretherton1
6 affiliations
  1. 1Allen Institute for Artificial Intelligence (Ai2) Seattle WA USA
  2. 2Courant Institute of Mathematical Sciences New York University New York NY USA
  3. 3NOAA/Geophysical Fluid Dynamics Laboratory Princeton NJ USA
  4. 4Princeton University Princeton NJ USA
  5. 5Center for Data Science New York University New York NY USA
  6. 6Lamont‐Doherty Earth Observatory of Columbia University New York NY USA
Open at sourceDOICite

Abstract

Traditional numerical global climate models simulate the full Earth system by exchanging boundary conditions between separate simulators of the atmosphere, ocean, sea ice, land surface, and other geophysical processes. This paradigm allows for distributed development of individual components within a common framework, unified by a coupler that handles translation between realms via spatial or temporal alignment and flux exchange. Following a similar approach adapted for machine learning‐based emulators, we present SamudrACE: a coupled global climate model emulator which produces centuries‐long simulations at 1‐degree horizontal, 6‐hourly atmospheric, and 5‐daily oceanic resolution, with 145 2D fields spanning 8 atmospheric and 19 oceanic vertical levels, plus sea ice, surface, and top‐of‐atmosphere variables. SamudrACE is highly stable and has low climate biases comparable to those of its components with prescribed boundary forcing, with realistic variability in coupled climate phenomena such as ENSO that is not possible to simulate in uncoupled mode.

Related

  1. Towards accurate extreme event likelihoods from diffusion model climate emulators
    Peter Manshausen, Noah Brenowitz, Julius Berner +2
    arXivPreprintCC BY 4.0Full textAtmospheric science & meteorologyarXiv
  2. Development and evaluation of the ECHAM6-iMAPLE v1.0 coupled atmosphere–ecosystem model
    Weijie Fu, Chenguang Tian, Yuan Zhao +4
    Geoscientific Model DevelopmentPeer-reviewedCC BY 4.0Full textClimate scienceCrossref
  3. The role of salinity in Snowball Earth: A simplified coupled atmosphere--ocean--ice model
    Sounav Sengupta, Francisco E. Spaulding-Astudillo, Dorian S. Abbot +2
    arXivPreprintCC0Full textAtmospheric science & meteorologyarXiv
  4. cSINGV v1.0: development and evaluation of a 1.5 km coupled atmosphere–ocean–wave modelling system for the Western Maritime Continent
    Rajesh Kumar, Claudio Sanchez, Juan Manuel Castillo +9
    Geoscientific Model DevelopmentPeer-reviewedCC BY 4.0General earth scienceCrossref
  5. An accurate and efficient framework for modeling multimetal competitive adsorption on clay minerals
    Pengyuan Gao, Xiandong Liu, Xiancai Lu +1
    Proceedings of the National Academy of Sciences of the United States of AmericaPeer-reviewedCC BY-NC-ND 4.0Full text6 citedHydrology & soilsHAL

Cite

BibTeXRIS
BibTeX
@article{duncan2026samudrace,
  title = {{SamudrACE: Fast and Accurate Coupled Climate Modeling With 3D Ocean and Atmosphere Emulators}},
  author = {James Duncan and Elynn Wu and Surya Dheeshjith and Adam Subel and Troy Arcomano and Spencer Koncius Clark and Brian Henn and Anna Kwa and Jeremy McGibbon and W. A. Perkins and William King Gregory and Carlos Fernandez‐Granda and Julius J. M. Busecke and Oliver Watt‐Meyer and William J. Hurlin and Alistair Adcroft and Laure Zanna and Christopher S. Bretherton},
  journal = {Geophysical Research Letters},
  year = {2026},
  month = may,
  doi = {10.1029/2025gl119340},
  url = {https://doi.org/10.1029/2025gl119340},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - SamudrACE: Fast and Accurate Coupled Climate Modeling With 3D Ocean and Atmosphere Emulators
AU  - James Duncan
AU  - Elynn Wu
AU  - Surya Dheeshjith
AU  - Adam Subel
AU  - Troy Arcomano
AU  - Spencer Koncius Clark
AU  - Brian Henn
AU  - Anna Kwa
AU  - Jeremy McGibbon
AU  - W. A. Perkins
AU  - William King Gregory
AU  - Carlos Fernandez‐Granda
AU  - Julius J. M. Busecke
AU  - Oliver Watt‐Meyer
AU  - William J. Hurlin
AU  - Alistair Adcroft
AU  - Laure Zanna
AU  - Christopher S. Bretherton
PY  - 2026
DA  - 2026/05/30
JO  - Geophysical Research Letters
DO  - 10.1029/2025gl119340
UR  - https://doi.org/10.1029/2025gl119340
AB  - Traditional numerical global climate models simulate the full Earth system by exchanging boundary conditions between separate simulators of the atmosphere, ocean, sea ice, land surface, and other geophysical processes. This paradigm allows for distributed development of individual components within a common framework, unified by a coupler that handles translation between realms via spatial or temporal alignment and flux exchange. Following a similar approach adapted for machine learning‐based emulators, we present SamudrACE: a coupled global climate model emulator which produces centuries‐long simulations at 1‐degree horizontal, 6‐hourly atmospheric, and 5‐daily oceanic resolution, with 145 2D fields spanning 8 atmospheric and 19 oceanic vertical levels, plus sea ice, surface, and top‐of‐atmosphere variables. SamudrACE is highly stable and has low climate biases comparable to those of its components with prescribed boundary forcing, with realistic variability in coupled climate phenomena such as ENSO that is not possible to simulate in uncoupled mode.
SN  - 0094-8276
SN  - 1944-8007
ER  -