Preprint · 2026 · Open access

Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting

Fırat Özdemir, Yun Cheng, Salman Mohebi, Fanny Lehmann, Simon Adamov, Zhenyi Zhang, Leonardo Trentini, Dana Grund, Oliver Fuhrer, Torsten Hoefler, Siddhartha Mishra, Sebastian Schemm and 2 more

arXiv (Cornell University) · Published 20 April 2026 · DOI 10.48550/arxiv.2605.00850

Free PDFView at the publisherCite this paper

In brief

“Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting” is a 2026 preprint by Fırat Özdemir and 13 co-authors, published in arXiv (Cornell University). OpenAlex counts 9 citations as of 15 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
9
Most cited in
2026 (9)
References
32
Authors
14

Abstract

Foundation models (FMs) for the Earth system learn statistical relationships between physical variables across massive datasets to enable versatile downstream applications through finetuning, separating them from task-specific weather models. Here, we introduce Earth System Foundation Model (ESFM), a fully open model building on the 3D Swin UNet backbone of the pioneering Aurora model. ESFM introduces extensions that increase functionality and foster adoption in climate sciences. First, the encoding scheme and training protocols have been extended to handle diverse datasets, including those containing missing values across all spatio-temporal dimensions such as satellite data, as well as station data, all under one backbone. Axial attention is introduced to capture inter-variable dependencies. As a result ESFM skillfully predicts variables in regions or on pressure levels where no data is present at the initial time, while preserving inter-variable relationships, for example between temperature, pressure, and humidity. Individual variable tokenization enables different sets of variables to be shuffled during training and simplifies the process of building extensions for new downstream tasks. Adaptive layer norm-based ensembles allow for a simple yet effective way to transform deterministic ESFM to a probabilistic FM. We present findings using dense gridded data (ERA5, CMIP6), regionally masked dense data, sparse gridded MODIS satellite data, and station data. Results demonstrate competitive or superior performance relative to state-of-the-art benchmarks. Case studies of Super Typhoon Doksuri (2023) and 2024 sudden stratospheric warming events show accurate positional and magnitude estimations of extreme weather. ESFM retains the strengths of previous foundation models, such as long-term stability, but facilitates application to a variety of downstream tasks.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Özdemir, F., Cheng, Y., Mohebi, S., Lehmann, F., Adamov, S., Zhang, Z., Trentini, L., Grund, D., Fuhrer, O., Hoefler, T., Mishra, S., Schemm, S., Soja, B. S., & Salzmann, M. (2026). Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.00850

MLA 9

Özdemir, Fırat, et al. “Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2605.00850.

Chicago

Özdemir, Fırat, Yun Cheng, Salman Mohebi, Fanny Lehmann, Simon Adamov, Zhenyi Zhang, Leonardo Trentini, et al. 2026. “Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.00850.

Harvard

Özdemir, F. et al. (2026) ‘Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting’, arXiv (Cornell University). doi:10.48550/arxiv.2605.00850.

IEEE

F. Özdemir et al., “Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2605.00850.

BibTeX

@misc{ozdemir2026earth,
  title     = {{Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting}},
  author    = {Özdemir, Fırat and Cheng, Yun and Mohebi, Salman and Lehmann, Fanny and Adamov, Simon and Zhang, Zhenyi and Trentini, Leonardo and Grund, Dana and Fuhrer, Oliver and Hoefler, Torsten and Mishra, Siddhartha and Schemm, Sebastian and Soja, Benedikt S. and Salzmann, Mathieu},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2605.00850},
  url       = {https://doi.org/10.48550/arxiv.2605.00850}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations

  • heterogeneous data integration
  • missing data
  • satellite data
  • station data
  • axial attention
  • inter-variable dependencies
  • probabilistic forecasting
  • extreme weather prediction

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Özdemir, F., Cheng, Y., Mohebi, S., Lehmann, F., Adamov, S., Zhang, Z., Trentini, L., Grund, D., Fuhrer, O., Hoefler, T., Mishra, S., Schemm, S., Soja, B. S., & Salzmann, M. (2026). Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.00850

How many times has this paper been cited?

9 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Fırat Özdemir, Yun Cheng, Salman Mohebi, Fanny Lehmann, Simon Adamov, Zhenyi Zhang, Leonardo Trentini, Dana Grund, Oliver Fuhrer, Torsten Hoefler, Siddhartha Mishra, Sebastian Schemm and 2 more.

What is the DOI of this paper?

10.48550/arxiv.2605.00850. The permanent link is https://doi.org/10.48550/arxiv.2605.00850.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.