EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Deep learning probability flows and entropy production rates in active matter

Nicholas M Boffi, Eric Vanden-Eijnden iD

Proceedings of the National Academy of Sciences · 18.06.2024 · 121 (25)

DOI: 10.1073/pnas.2318106121 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 11.06.2024. Verfasst von Nicholas M Boffi und 1 weiteren Autor:innen. Beteiligte Einrichtung: Courant Institute of Mathematical Sciences, New York University, New York, NY 10012. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Science Foundation (NSF), Simons Foundation (SF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Active matter systems, from self-propelled colloids to motile bacteria, are characterized by the conversion of free energy into useful work at the microscopic scale. They involve physics beyond the reach of equilibrium statistical mechanics, and a persistent challenge has been to understand the nature of their nonequilibrium states. The entropy production rate and the probability current provide quantitative ways to do so by measuring the breakdown of time-reversal symmetry. Yet, their efficient computation has remained elusive, as they depend on the system’s unknown and high-dimensional probability density. Here, building upon recent advances in generative modeling, we develop a deep learning framework to estimate the score of this density. We show that the score, together with the microscopic equations of motion, gives access to the entropy production rate, the probability current, and their decomposition into local contributions from individual particles. To represent the score, we introduce a spatially local transformer network architecture that learns high-order interactions between particles while respecting their underlying permutation symmetry. We demonstrate the broad utility and scalability of the method by applying it to several high-dimensional systems of active particles undergoing motility-induced phase separation (MIPS). We show that a single network trained on a system of 4,096 particles at one packing fraction can generalize to other regions of the phase diagram, including to systems with as many as 32,768 particles. We use this observation to quantify the spatial structure of the departure from equilibrium in MIPS as a function of the number of particles and the packing fraction.

Schlagwörter

Stichwörter der Autor:innen

active mattermachine learningscientific computingstochastic thermodynamics

Autor:innen und Institutionen

  • Courant Institute of Mathematical Sciences, New York University, New York, NY 10012.

ORCID-Profile: Eric Vanden-Eijnden

Förderung

  • National Science Foundation (NSF)
  • Simons Foundation (SF)

Zitieren

APA

Boffi, N. M., & Vanden-Eijnden, E. (2024). Deep learning probability flows and entropy production rates in active matter. Proceedings of the National Academy of Sciences, 121(25). https://doi.org/10.1073/pnas.2318106121

Vancouver

Boffi NM, Vanden-Eijnden E. Deep learning probability flows and entropy production rates in active matter. Proceedings of the National Academy of Sciences. 2024;121(25). doi:10.1073/pnas.2318106121

BibTeX
@article{Boffi2024,
  author = {Boffi, Nicholas M and Vanden-Eijnden, Eric},
  title = {Deep learning probability flows and entropy production rates in active matter},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2024},
  volume = {121},
  number = {25},
  doi = {10.1073/pnas.2318106121}
}
Kostenlos starten →