Journal article · 2026 · Open access

Probabilistic storyline attribution using machine learning

Frieder Loer, Maybritt Schillinger, Sebastian Sippel

Machine Learning Earth, 2(2), 02LT02 · Published 9 September 2026 · DOI 10.1088/3049-4753/aea4b7

Open PDFView at the publisherCite this paper

In brief

“Probabilistic storyline attribution using machine learning” is a 2026 journal article by Frieder Loer and 2 co-authors, published in Machine Learning Earth. OpenAlex counts 1 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at Machine Learning Earth.

Citations
1
Most cited in
2026 (1)
Field-weighted impact
1.41
References
64
Authors
3

Abstract

A fundamental goal in climate attribution is to estimate how forced climate change contributes to observed extreme weather events. The storyline attribution method compares an observed weather event, conditional on its atmospheric dynamic state (i.e., atmospheric circulation), in the current, 'factual' climate to an event with very similar circulation conditions in a hypothetical, 'counterfactual' climate. However, simulating these storylines with physical climate models across different climate forcing states is computationally costly, allowing only a limited number of storyline realizations. Statistical and machine learning techniques may overcome this limitation; yet, emulating circulation-conditional extreme events under different climate states is challenging. Here, we demonstrate distributional autoencoders (DAEs) as a versatile method for generating climate counterfactuals. They model the distribution of spatially resolved European temperature fields conditional on the atmospheric circulation state and the mean global warming level. These distributions allow for deriving meaningful conditional probability ratios, which is a particular advantage of the DAE-based storyline approach. We train DAEs on fully coupled climate model simulations and we evaluate the modelled distributions across different factual and storyline-based counterfactual climate model simulations. In an illustrative case study, we revisit the 2003 European heatwave and we generate counterfactuals for a hypothetical `2003-like European heatwave' using ERA5 circulation, which we hypothesize to occur a quarter century (2028) and a half century (2053) after 2003. The conditional intensity would increase from 28.4 °C in 2003, to 30.3 °C and 31.7 °C in 2028 and 2053, respectively, and conditional probability ratios would be 9.2 and 15.2 when compared to 2003. Overall, this study introduces a new deep learning method that complements the toolbox for extreme event attribution. DAE-based storyline attribution may provide new avenues towards distributionally explicit generation of counterfactuals and could be extended in future studies towards attributing single forcing effects or climate impacts.

Cite this paper

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

APA 7

Loer, F., Schillinger, M., & Sippel, S. (2026). Probabilistic storyline attribution using machine learning. Machine Learning Earth, 2(2), 02LT02. https://doi.org/10.1088/3049-4753/aea4b7

MLA 9

Loer, Frieder, et al. “Probabilistic storyline attribution using machine learning.” Machine Learning Earth, vol. 2, no. 2, 2026, p. 02LT02. https://doi.org/10.1088/3049-4753/aea4b7.

Chicago

Loer, Frieder, Maybritt Schillinger, and Sebastian Sippel. 2026. “Probabilistic storyline attribution using machine learning.” Machine Learning Earth 2 (2): 02LT02. https://doi.org/10.1088/3049-4753/aea4b7.

Harvard

Loer, F., Schillinger, M. and Sippel, S. (2026) ‘Probabilistic storyline attribution using machine learning’, Machine Learning Earth, 2(2), p. 02LT02. doi:10.1088/3049-4753/aea4b7.

IEEE

F. Loer, M. Schillinger, and S. Sippel, “Probabilistic storyline attribution using machine learning,” Machine Learning Earth, vol. 2, no. 2, p. 02LT02, 2026, doi: 10.1088/3049-4753/aea4b7.

BibTeX

@article{loer2026probabilistic,
  title     = {{Probabilistic storyline attribution using machine learning}},
  author    = {Loer, Frieder and Schillinger, Maybritt and Sippel, Sebastian},
  journal   = {Machine Learning Earth},
  year      = {2026},
  volume    = {2},
  number    = {2},
  pages     = {02LT02},
  doi       = {10.1088/3049-4753/aea4b7},
  url       = {https://doi.org/10.1088/3049-4753/aea4b7}
}

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

Topic and keywords

Physical Sciences › Environmental Science › Global and Planetary Change › Climate variability and models

  • extreme event attribution
  • atmospheric circulation
  • European heatwaves
  • 2003 European heatwave
  • climate change
  • ERA5 reanalysis

Work with this paper

Most-cited papers in Environmental Science

All highly cited Environmental Science papers

Questions about this paper

How do I cite this paper in APA style?

Loer, F., Schillinger, M., & Sippel, S. (2026). Probabilistic storyline attribution using machine learning. Machine Learning Earth, 2(2), 02LT02. https://doi.org/10.1088/3049-4753/aea4b7

How many times has this paper been cited?

1 times, according to OpenAlex on 20 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 at Machine Learning Earth: sign in and open the PDF from this page.

Who wrote this paper?

Frieder Loer, Maybritt Schillinger, Sebastian Sippel.

What is the DOI of this paper?

10.1088/3049-4753/aea4b7, permanently at https://doi.org/10.1088/3049-4753/aea4b7. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.