EUVIMEDEUVIMED entdecken
Crossref

Machine learning for predicting chaotic systems

Christof Schötz iD, Alistair White iD, Maximilian Gelbrecht iD, Niklas Boers iD

Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.05.2026 · 36 (5)

DOI: 10.1063/5.0313297 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 01.05.2026. Verfasst von Christof Schötz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Munich Climate Center and Earth System Modelling Group, Department of Aerospace and Geodesy, Technical University of Munich, Munich, Germany. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: HORIZON EUROPE European Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting chaotic dynamical systems is critical in many scientific fields, such as weather forecasting, but challenging due to the characteristic sensitive dependence on initial conditions. Traditional modeling approaches require extensive domain knowledge, often leading to a shift toward data-driven methods using machine learning. However, existing research provides inconclusive results on which machine learning methods are best suited for predicting chaotic systems. In this paper, we compare different lightweight and heavyweight machine learning architectures using extensive existing benchmark databases of low-dimensional systems, as well as a newly introduced database that allows for uncertainty quantification in the benchmark results. In addition to the state-of-the-art methods from the literature, we also present new advantageous variants of established methods. Hyperparameter tuning is adjusted based on computational cost, with more tuning allocated to less costly methods. Furthermore, we introduce the cumulative maximum error, a novel metric that combines desirable properties of traditional metrics and is tailored for chaotic systems. Our results show that well-tuned simple methods, as well as untuned baseline methods, often outperform the state-of-the-art deep learning models, but their performance can vary significantly with different experimental setups. These findings highlight the importance of aligning prediction methods with data characteristics and caution against the indiscriminate use of overly complex models.

Autor:innen und Institutionen

  • Munich Climate Center and Earth System Modelling Group, Department of Aerospace and Geodesy, Technical University of Munich, Munich, Germany.
  • Artificial Intelligence Group, The Potsdam Institute for Climate Impact Research, Potsdam, Germany.
  • Department of Mathematics, University of Exeter, Exeter, United Kingdom.

ORCID-Profile: Christof Schötz, Alistair White, Maximilian Gelbrecht, Niklas Boers

Förderung

  • HORIZON EUROPE European Research Council

Zitieren

APA

Schötz, C., White, A., Gelbrecht, M., & Boers, N. (2026). Machine learning for predicting chaotic systems. Chaos: An Interdisciplinary Journal of Nonlinear Science, 36(5). https://doi.org/10.1063/5.0313297

Vancouver

Schötz C, White A, Gelbrecht M, Boers N. Machine learning for predicting chaotic systems. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2026;36(5). doi:10.1063/5.0313297

BibTeX
@article{Schtz2026,
  author = {Schötz, Christof and White, Alistair and Gelbrecht, Maximilian and Boers, Niklas},
  title = {Machine learning for predicting chaotic systems},
  journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
  year = {2026},
  volume = {36},
  number = {5},
  doi = {10.1063/5.0313297}
}
Kostenlos starten →