Neural ordinary differential equations for learning and extrapolating system dynamics across bifurcations
Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.10.2025 · 35 (10)
DOI: 10.1063/5.0288264 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 22.10.2025. Verfasst von Eva van Tegelen und 3 weiteren Autor:innen. Beteiligte Einrichtung: Biometris, Wageningen University and Research, Wageningen, The Netherlands. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: Investment programme for Artificial Intelligence and Datascience at Wageningen University and Research.
Abstract (Originalsprache)
Forecasting system behavior near and across bifurcations is crucial for identifying potential shifts in dynamical systems. While machine learning has recently been used to learn critical transitions and bifurcation structures from data, most studies remain limited as they exclusively focus on discrete-time methods and local bifurcations. To address these limitations, we use neural ordinary differential equations which provide a data-driven framework for learning system dynamics. Our results show that neural ordinary differential equations can recover underlying bifurcation structures directly from time series data by learning parameter-dependent vector fields. Notably, we demonstrate that neural ordinary differential equations can forecast bifurcations even beyond the parameter regions represented in the training data. We demonstrate our approach on three test cases: the Lorenz system transitioning from non-chaotic to chaotic behavior, the Rössler system moving from chaos to period-doubling, and a predator–prey model exhibiting collapse via a global bifurcation.
Autor:innen und Institutionen
- Biometris, Wageningen University and Research, Wageningen, The Netherlands.
- Artificial Intelligence Group, Wageningen University and Research, Wageningen, The Netherlands.
ORCID-Profile: Eva van Tegelen, George van Voorn, Ioannis N Athanasiadis, Peter van Heijster
Förderung
- Investment programme for Artificial Intelligence and Datascience at Wageningen University and Research
Zitieren
APA
van Tegelen, E., van Voorn, G., Athanasiadis, I. N., & van Heijster, P. (2025). Neural ordinary differential equations for learning and extrapolating system dynamics across bifurcations. Chaos: An Interdisciplinary Journal of Nonlinear Science, 35(10). https://doi.org/10.1063/5.0288264
Vancouver
van Tegelen E, van Voorn G, Athanasiadis IN, van Heijster P. Neural ordinary differential equations for learning and extrapolating system dynamics across bifurcations. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2025;35(10). doi:10.1063/5.0288264
BibTeX
@article{vanTegelen2025,
author = {van Tegelen, Eva and van Voorn, George and Athanasiadis, Ioannis N and van Heijster, Peter},
title = {Neural ordinary differential equations for learning and extrapolating system dynamics across bifurcations},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2025},
volume = {35},
number = {10},
doi = {10.1063/5.0288264}
}
EUVIMED