EUVIMEDEUVIMED entdecken
Open Access

Neural ordinary differential equations with irregular and noisy data

Pawan Goyal iD, Peter Benner iD

Royal Society Open Science · 2023-07 · 10 (7)

DOI: 10.1098/rsos.221475 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Royal Society Open Science, online erschienen am 19.07.2023. Verfasst von Pawan Goyal und 1 weiteren Autor:innen. Beteiligte Einrichtung: Max Planck Institute for Dynamics of Complex Technical Systems, Standtorstrasse 1, 39106 Magdeburg, Germany. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Measurement noise is an integral part of collecting data of a physical process. Thus, noise removal is necessary to draw conclusions from these data, and it often becomes essential to construct dynamical models using these data. We discuss a methodology to learn differential equation(s) using noisy and irregularly sampled measurements. In our methodology, the main innovation can be seen in the integration of deep neural networks with the neural ordinary differential equations (ODEs) approach. Precisely, we aim at learning a neural network that provides (approximately) an implicit representation of the data and an additional neural network that models the vector fields of the dependent variables. We combine these two networks by constraints using neural ODEs. The proposed framework to learn a model describing the vector field is highly effective under noisy measurements. The approach can handle scenarios where dependent variables are unavailable at the same temporal grid. Moreover, a particular structure, e.g. second order with respect to time, can easily be incorporated. We demonstrate the effectiveness of the proposed method for learning models using data obtained from various differential equations and present a comparison with the neural ODE method that does not make any special treatment to noise. Additionally, we discuss an ensemble approach to improve the performance of the proposed approach further.

Schlagwörter

Stichwörter der Autor:innen

dynamical systemsmachine learningneural networksneural ordinary differential equationsnoisy data

Autor:innen und Institutionen

  • Max Planck Institute for Dynamics of Complex Technical Systems, Standtorstrasse 1, 39106 Magdeburg, Germany.

ORCID-Profile: Pawan Goyal, Peter Benner

Zitieren

APA

Goyal, P., & Benner, P. (2023). Neural ordinary differential equations with irregular and noisy data. Royal Society Open Science, 10(7). https://doi.org/10.1098/rsos.221475

Vancouver

Goyal P, Benner P. Neural ordinary differential equations with irregular and noisy data. Royal Society Open Science. 2023;10(7). doi:10.1098/rsos.221475

BibTeX
@article{Goyal2023,
  author = {Goyal, Pawan and Benner, Peter},
  title = {Neural ordinary differential equations with irregular and noisy data},
  journal = {Royal Society Open Science},
  year = {2023},
  volume = {10},
  number = {7},
  doi = {10.1098/rsos.221475}
}
Kostenlos starten →