EUVIMEDEUVIMED entdecken
Open Access

Predicting rare events using neural networks and short-trajectory data

John Strahan, Justin Finkel, Aaron R Dinner, Jonathan Weare

Journal of Computational Physics · 2023-09 · 488 · 112152

DOI: 10.1016/j.jcp.2023.112152 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computational Physics, 2023-09. Verfasst von John Strahan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry and James Franck Institute, the University of Chicago, Chicago, IL 60637. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 75 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Estimating the likelihood, timing, and nature of events is a major goal of modeling stochastic dynamical systems. When the event is rare in comparison with the timescales of simulation and/or measurement needed to resolve the elemental dynamics, accurate prediction from direct observations becomes challenging. In such cases a more effective approach is to cast statistics of interest as solutions to Feynman-Kac equations (partial differential equations). Here, we develop an approach to solve Feynman-Kac equations by training neural networks on short-trajectory data. Our approach is based on a Markov approximation but otherwise avoids assumptions about the underlying model and dynamics. This makes it applicable to treating complex computational models and observational data. We illustrate the advantages of our method using a low-dimensional model that facilitates visualization, and this analysis motivates an adaptive sampling strategy that allows on-the-fly identification of and addition of data to regions important for predicting the statistics of interest. Finally, we demonstrate that we can compute accurate statistics for a 75-dimensional model of sudden stratospheric warming. This system provides a stringent test bed for our method.

Schlagwörter

Stichwörter der Autor:innen

Feynman-Kac equationHolton-Mass modeladaptive samplinghigh-dimensional PDEneural networkrare event

Autor:innen und Institutionen

  • Department of Chemistry and James Franck Institute, the University of Chicago, Chicago, IL 60637.
  • Department of Earth, Atmospheric, and Planetary Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139.
  • Committee on Computational and Applied Mathematics, the University of Chicago, Chicago, IL 60637.
  • Courant Institute of Mathematical Sciences, New York University, New York, New York 10012.

Förderung

  • NIGMS NIH HHS

Zitieren

APA

Strahan, J., Finkel, J., Dinner, A. R., & Weare, J. (2023). Predicting rare events using neural networks and short-trajectory data. Journal of Computational Physics, 488, 112152. https://doi.org/10.1016/j.jcp.2023.112152

Vancouver

Strahan J, Finkel J, Dinner AR, Weare J. Predicting rare events using neural networks and short-trajectory data. Journal of Computational Physics. 2023;488:112152. doi:10.1016/j.jcp.2023.112152

BibTeX
@article{Strahan2023,
  author = {Strahan, John and Finkel, Justin and Dinner, Aaron R and Weare, Jonathan},
  title = {Predicting rare events using neural networks and short-trajectory data},
  journal = {Journal of Computational Physics},
  year = {2023},
  volume = {488},
  pages = {112152},
  doi = {10.1016/j.jcp.2023.112152}
}
Kostenlos starten →