Towards Hybrid Earth System Modeling: A Living Review

This page presents an alphabetical review of emerging approaches that bring machine learning (ML) into Earth system modeling to simulate the full time evolution of climate variables in response to diverse forcings. These models hold promise for improving long-term projections of Earth's physical climate and biogeochemical cycles. Although new creative approaches continue to emerge, most designs fall into two broad categories:

1. Hybridizing existing Earth system models (ESMs)
   Hybrid ESMs build on established ESM codebases, retaining key physics components (e.g., the dynamical core) while replacing or improving parameterizations of hard-to-model processes (e.g., storm formation) with ML. This often involves interfacing Fortran-based codebases with Python-based ML tools. For related technical resources, see this living review maintained by Julien Le Sommer and Alexis Barge.

2. Developing data-driven climate models from scratch
   Climate emulators write prognostic equations directly in differentiable programming frameworks, incorporating explicit physical laws (e.g., conservation equations) only when needed. This is a longer-term endeavor, involving the progressive development and coupling of the atmosphere–ocean–land–cryosphere components.

If you notice any errors, omissions, or outdated information, please feel free to submit a pull request.

<ins>Author</ins>: Tom Beucler (UNIL); written in the context of AI4PEX and the WCRP Lighthouse Activities.

How to cite

Beucler, T. (2025). Towards Hybrid Earth System Modeling: A Living Review (v1.0). Zenodo. https://doi.org/10.5281/zenodo.16967529

Table of Contents

• ACE
• CAMulator
• CBRAIN
• CliMA
• ClimSim
• Corrective ML
• DLESyM
• Hybrid ARP-GEM
• Hybrid CAM
• Hybrid HadGEM
• Hybrid Land Surface Modeling
• Hybrid SAM
• Hybrid SPEEDY
• Hybrid WRF
• ICON-MLe
• LUCIE
• MOM6
• NCAM
• NeuralGCM
• Ola
• Samudra

---

ACE

The Ai2 Climate Emulator (ACE) emulates NOAA's FV3GFS atmospheric model using spherical Fourier neural operators. ACE operates with six prognostic variables, can be forced through insolation and sea surface skin temperature, diagnoses radiative and energy fluxes at the atmosphere's boundaries, and runs on a single GPU. ACE2 improves upon ACE by enforcing global conservation of dry air mass and humidity, making it a hybrid climate model and improving climate stability and surface pressure representation. ACE2, which can be coupled to a slab ocean or a 3D ocean emulator, is trained and tested on historical climate reanalysis (1940-2020) and 100 km-resolution Unified Forecast System (UFS) simulations forced by historical sea surface temperatures and greenhouse gas concentrations.

Latest simulations in Duncan, J. P. C., Wu, E., Dheeshjith, S., Subel, A., Arcomano, T., Clark, S. K., ... & Bretherton, C. (2025). SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulators. arXiv:2509.12490

See also:

• Clark, S. K., Watt-Meyer, O., Kwa, A., McGibbon, J., Henn, B., Perkins, W. A., ... & Harris, L. M. (2024). ACE2-SOM: Coupling to a slab ocean and learning the sensitivity of climate to changes in CO2. arXiv:2412.04418.
• Watt-Meyer, O., Henn, B., McGibbon, J., Clark, S. K., Kwa, A., Perkins, W. A., Wu, E., Harris, L., & Bretherton, C. S. (2025). ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses. npj Climate and Atmospheric Science, 8.
• Wu, E., Rebassoo, F., Pappu, P., Proistosescu, C., Nugent, J. M., ... & Bretherton, C. S. (2025). Applying the ACE2 Emulator to SST Green's Functions for the E3SMv3 Global Atmosphere Model. arXiv preprint 2505.08742.
• Kent, C., Scaife, A. A., Dunstone, N. J., Smith, D., Hardiman, S. C., Dunstan, T., & Watt-Meyer, O (2025). Skilful global seasonal predictions from a machine learning weather model trained on reanalysis data. arXiv preprint 2503.23953.
• Duncan, J. P., Wu, E., Golaz, J. C., Caldwell, P. M., Watt‐Meyer, O., Clark, S. K., ... & Bretherton, C. S. (2024). Application of the AI2 Climate Emulator to E3SMv2's global atmosphere model, with a focus on precipitation fidelity. Journal of Geophysical Research: Machine Learning and Computation, 1(3), e2024JH000136.
• Watt-Meyer, O., Dresdner, G., McGibbon, J., Clark, S. K., Henn, B., Duncan, J., ... & Bretherton, C. S. (2023). ACE: A fast, skillful learned global atmospheric model for climate prediction. arXiv preprint 2310.02074.

---

CAMulator

CAMulator v1 is a machine-learned emulator of the Community Atmosphere Model v6 (CAM6) that predicts atmospheric states from sea surface temperatures and solar radiation. It conserves key physical quantities, captures major climate patterns like ENSO and NAO, and runs 350× faster than CAM6—enabling large-scale, physically grounded climate simulations. While it exhibits a cold bias in high-latitude winters outside its training range, CAMulator represents a major advance toward fast, realistic ML-based climate modeling.

Latest simulations in Chapman, W. E., Schreck, J. S., Sha, Y., Gagne II, D. J., Kimpara, D., Zanna, L., ... & Berner, J. (2025). CAMulator: Fast Emulation of the Community Atmosphere Model. arXiv preprint 2504.06007.

See also:

• Chapman, W. E., & Berner, J. (2025). Improving climate bias and variability via CNN-based state-dependent model-error corrections. Geophysical Research Letters, 52, e2024GL114106.

---

CBRAIN

Cloud Brain (CBRAIN) aims to break the convective parameterization deadlock in the Community Atmosphere Model (CAM) by training neural networks to emulate the total subgrid thermodynamic time tendencies. These tendencies represent the cumulative tendencies of prognostic thermodynamic variables (temperature and specific humidity) due to subgrid-scale processes such as convection, radiation, and turbulence.

• In the aquaplanet ("ocean world") configuration, the Super-Parameterized Community Atmosphere Model v3 (SPCAM3) is used. Here, each coarse grid cell contains a two-dimensional convection-permitting model that explicitly resolves convection, providing the target tendencies for the neural networks.

• In the realistic geography configuration, the Super-Parameterized Community Atmosphere Model v5 (SPCAM5) is coupled with the Community Land Model v4 (CLM4). As in the aquaplanet configuration, each coarse grid cell includes a two-dimensional convection-permitting model that explicitly resolves convection, providing the target tendencies for the neural networks.

Latest simulations in Lin, J., Yu, S., Peng, L., Beucler, T., Wong-Toi, E., Hu, Z., ... & Pritchard, M. S. (2024). Sampling Hybrid Climate Simulation at Scale to Reliably Improve Machine Learning Parameterization. arXiv preprint 2309.16177.

See also:

• Behrens, G., Beucler, T., Iglesias-Suarez, F., Yu, S., Gentine, P., Pritchard, M., ... & Eyring, V. (2024). Improving Atmospheric Processes in Earth System Models with Deep Learning Ensembles and Stochastic Parameterizations. arXiv preprint 2402.03079.
• Rasp, S., Pritchard, M. S., & Gentine, P. (2018). Deep learning to represent subgrid processes in climate models. Proceedings of the national academy of sciences, 115(39), 9684-9689.
• Iglesias‐Suarez, F., Gentine, P., Solino‐Fernandez, B., Beucler, T., Pritchard, M., Runge, J., & Eyring, V. (2024). Causally‐informed deep learning to improve climate models and projections. Journal of Geophysical Research: Atmospheres, 129(4), e2023JD039202.
• Ott, J., Pritchard, M., Best, N., Linstead, E., Curcic, M., & Baldi, P. (2020). A fortran‐keras deep learning bridge for scientific computing. Scientific Programming, 2020(1), 8888811.
• Beucler, T., Gentine, P., Yuval, J., Gupta, A., Peng, L., Lin, J., ... & Pritchard, M. (2024). Climate-invariant machine learning. Science Advances, 10(6), eadj7250.
• Mooers, G., Pritchard, M., Beucler, T., Ott, J., Yacalis, G., Baldi, P., & Gentine, P. (2021). Assessing the potential of deep learning for emulating cloud superparameterization in climate models with real‐geography boundary conditions. Journal of Advances in Modeling Earth Systems, 13(5), e2020MS002385.
• [Gentine, P., Pritchard, M., Rasp, S., Reinaudi