Conference paper · 2026 · Open access

Subseasonal-to-Seasonal strategies for the Earth System Foundation Model (ESFM)

Piotr Wilczyński, Fanny Lehmann, Fırat Özdemir, Salman Mohebi, Yun Cheng, Oliver Fuhrer, Siddhartha Mishra, Mathieu Salzmann, Benedikt S. Soja, Sebastian Schemm, Torsten Hoefler

EGU General Assembly Conference Abstracts · Published 14 March 2026 · DOI 10.5194/egusphere-egu26-14846

Read the free full textCite this paper

In brief

“Subseasonal-to-Seasonal strategies for the Earth System Foundation Model (ESFM)” is a 2026 conference paper by Piotr Wilczyński and 10 co-authors, published in EGU General Assembly Conference Abstracts. OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at EGU General Assembly Conference Abstracts.

Citations
0
Authors
11

Abstract

Foundation models for the Earth system have gained popularity, as they are starting to surpass numerical solvers in the accuracy of predicting Earth’s condition while requiring fewer computational resources. The Earth System Foundation Model (ESFM) contributes to this research direction by further extending the foundation models' flexibility.The forecasting capabilities of ESFM are achieved in an autoregressive manner, using data from the t0 - Δt and t0 timesteps to produce a prediction for t0 + Δt. This approach is effective on weather timescales. Moreover, we find that it also delivers encouraging results for long-term forecasts, showing reasonable zero-shot subseasonal-to-seasonal (S2S) predictions (15–40 days). However, S2S predictions can be further improved while preserving weather skills. This work investigates strategies for this purpose. On such timescales, it is crucial to produce probabilistic predictions to better represent inherent uncertainty. Probabilistic predictions are realised with the introduction of multiple decoder heads (tails) for each variable. Each tail is intended to simulate a different possible trajectory, which, when combined, provides an estimate of the most probable outcome together with the spread of feasible values. To better estimate the distribution of possible values on the S2S timescale, additional trajectories are generated by running multiple predictive rollouts with different initial conditions.Another strategy to improve S2S rollouts is to fine-tune the model to produce outputs for more distant steps. To this end, we leverage LoRA adapters (Hu et al., 2022), which are trained for each subsequent rollout step. This approach effectively improves predictive performance on long horizons, without significantly affecting training complexity or inference cost.We also observe that some predictive variables of the model, such as climate forcings, are slowly evolving and can benefit from incorporating inputs from a more distant past than the t0 - Δt and t0 timesteps commonly used. To investigate this, we introduce an Attention Temporal Aggregator in the encoder, which leverages learned patch embeddings from an arbitrary number of previous timesteps and attends to those that are most informative for a given variable. In this way, for rapidly changing variables such as wind speed, the model focuses on the most recent data, whereas for slowly evolving variables such as sea surface temperature, it can utilise a broader range of inputs.Overall, our experiments provide new insights into the development of foundation models for the Earth system, enabling improved predictions on S2S timescales, while conserving performance for weather forecasts.References:E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, W. Chen, et al. Lora: Low-rank adaptation of large language models. ICLR, 1(2):3…

Cite this paper

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

APA 7

Wilczyński, P., Lehmann, F., Özdemir, F., Mohebi, S., Cheng, Y., Fuhrer, O., Mishra, S., Salzmann, M., Soja, B. S., Schemm, S., & Hoefler, T. (2026). Subseasonal-to-Seasonal strategies for the Earth System Foundation Model (ESFM). EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu26-14846

MLA 9

Wilczyński, Piotr, et al. “Subseasonal-to-Seasonal strategies for the Earth System Foundation Model (ESFM).” EGU General Assembly Conference Abstracts, 2026. https://doi.org/10.5194/egusphere-egu26-14846.

Chicago

Wilczyński, Piotr, Fanny Lehmann, Fırat Özdemir, Salman Mohebi, Yun Cheng, Oliver Fuhrer, Siddhartha Mishra, et al. 2026. “Subseasonal-to-Seasonal strategies for the Earth System Foundation Model (ESFM).” EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu26-14846.

Harvard

Wilczyński, P. et al. (2026) ‘Subseasonal-to-Seasonal strategies for the Earth System Foundation Model (ESFM)’, EGU General Assembly Conference Abstracts. doi:10.5194/egusphere-egu26-14846.

IEEE

P. Wilczyński et al., “Subseasonal-to-Seasonal strategies for the Earth System Foundation Model (ESFM),” EGU General Assembly Conference Abstracts, 2026, doi: 10.5194/egusphere-egu26-14846.

BibTeX

@inproceedings{wilczynski2026subseasonal,
  title     = {{Subseasonal-to-Seasonal strategies for the Earth System Foundation Model (ESFM)}},
  author    = {Wilczyński, Piotr and Lehmann, Fanny and Özdemir, Fırat and Mohebi, Salman and Cheng, Yun and Fuhrer, Oliver and Mishra, Siddhartha and Salzmann, Mathieu and Soja, Benedikt S. and Schemm, Sebastian and Hoefler, Torsten},
  booktitle = {EGU General Assembly Conference Abstracts},
  year      = {2026},
  doi       = {10.5194/egusphere-egu26-14846},
  url       = {https://doi.org/10.5194/egusphere-egu26-14846}
}

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

  • subseasonal-to-seasonal forecasting
  • probabilistic forecasting
  • LoRA adapters
  • long-term forecasting
  • weather forecasting
  • radiative forcing
  • sea surface temperature
  • wind speed

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?

Wilczyński, P., Lehmann, F., Özdemir, F., Mohebi, S., Cheng, Y., Fuhrer, O., Mishra, S., Salzmann, M., Soja, B. S., Schemm, S., & Hoefler, T. (2026). Subseasonal-to-Seasonal strategies for the Earth System Foundation Model (ESFM). EGU General Assembly Conference Abstracts. https://doi.org/10.5194/egusphere-egu26-14846

How many times has this paper been cited?

0 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 EGU General Assembly Conference Abstracts.

Who wrote this paper?

Piotr Wilczyński, Fanny Lehmann, Fırat Özdemir, Salman Mohebi, Yun Cheng, Oliver Fuhrer, Siddhartha Mishra, Mathieu Salzmann, Benedikt S. Soja, Sebastian Schemm, Torsten Hoefler.

What is the DOI of this paper?

10.5194/egusphere-egu26-14846. The permanent link is https://doi.org/10.5194/egusphere-egu26-14846.

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.