Modelisation of chaotic systems with a latent Stochastic Differential Equation
Abstract
Stochastic Differential Equations (SDEs) have become a cornerstone of scientific machine learning, though they are predominantly utilized as algorithmic tools for uncertainty quantification or distribution matching. In contrast, leveraging SDEs fundamentally to model macroscopic, nonlinear physics as stochastic processes remains largely unexplored. This work introduces a probabilistic, non-intrusive reduced-order model (ROM) for chaotic dynamical systems. We argue that projecting high-dimensional nonlinear dynamics onto a low-dimensional manifold introduces irreducible uncertainty, compounded by the chaotic attractors and multi-admissible futures inherent to turbulent flows. Consequently, a chaotic system governed by a partial differential equation can be effectively modeled by an SDE in a suitable latent space. To this end, a nonlinear autoencoder is employed to map the flow field into a low-dimensional representation, within which the temporal evolution is explicitly governed by an SDE. The predictable component of the dynamics is captured by a learned drift term, while state-dependent stochasticity is absorbed by a diffusion term. We demonstrate that this probabilistic framework successfully propagates highly nonlinear states, offering a robust alternative to traditional deterministic methodologies for chaotic regimes. Ultimately, our model generates new chaotic flow trajectories that remain locally and globally consistent with the true transition kernel learned from Direct Numerical Simulation (DNS) data. Even though these generated trajectories are unique and distinct from the training set, they preserve the underlying statistics and manifolds, validating the strong generative performance and robustness of our methodology.
Related
- Chaotic dynamics in blooms of Ostreopsis cf. ovata modelled from environmental time series using ordinary differential equations systems
- Generating integrable systems from an autonomous ordinary differential equation
- Bifurcation analysis, optical soliton solutions and chaotic pattern for the stochastic DWDM topology with spatio-temporal dispersion
- Integrable turbulence and statistical properties of chaotic wave fields in the complex modified Korteweg-de Vries equation
- Universal Dynamical Response to Slow Driving in Chaotic Systems
BibTeX
@misc{zighed2026modelisation,
title = {{Modelisation of chaotic systems with a latent Stochastic Differential Equation}},
author = {Ismaël Zighed and Nicolas Thome and Patrick Gallinari and Taraneh Sayadi},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.03438},
eprint = {2608.03438},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.03438},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Modelisation of chaotic systems with a latent Stochastic Differential Equation
AU - Ismaël Zighed
AU - Nicolas Thome
AU - Patrick Gallinari
AU - Taraneh Sayadi
PY - 2026
DA - 2026/08/31
PB - arXiv
DO - 10.48550/arxiv.2608.03438
UR - https://arxiv.org/abs/2608.03438
AB - Stochastic Differential Equations (SDEs) have become a cornerstone of scientific machine learning, though they are predominantly utilized as algorithmic tools for uncertainty quantification or distribution matching. In contrast, leveraging SDEs fundamentally to model macroscopic, nonlinear physics as stochastic processes remains largely unexplored. This work introduces a probabilistic, non-intrusive reduced-order model (ROM) for chaotic dynamical systems. We argue that projecting high-dimensional nonlinear dynamics onto a low-dimensional manifold introduces irreducible uncertainty, compounded by the chaotic attractors and multi-admissible futures inherent to turbulent flows. Consequently, a chaotic system governed by a partial differential equation can be effectively modeled by an SDE in a suitable latent space. To this end, a nonlinear autoencoder is employed to map the flow field into a low-dimensional representation, within which the temporal evolution is explicitly governed by an SDE. The predictable component of the dynamics is captured by a learned drift term, while state-dependent stochasticity is absorbed by a diffusion term. We demonstrate that this probabilistic framework successfully propagates highly nonlinear states, offering a robust alternative to traditional deterministic methodologies for chaotic regimes. Ultimately, our model generates new chaotic flow trajectories that remain locally and globally consistent with the true transition kernel learned from Direct Numerical Simulation (DNS) data. Even though these generated trajectories are unique and distinct from the training set, they preserve the underlying statistics and manifolds, validating the strong generative performance and robustness of our methodology.
ER -