Data-driven particle dynamics: Structure-preserving coarse-graining for emergent behavior in nonequilibrium systems
Proceedings of the National Academy of Sciences · 19.05.2026 · 123 (20)
DOI: 10.1073/pnas.2519631123 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 13.05.2026. Verfasst von Quercus Hernández und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical Engineering and Applied Mechanics, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA 1…. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 129 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: U.S. Department of Energy (DOE), DOD | USA | AFC | CCDC | Army Research Office (ARO), DOE | Office of Science (SC).
Abstract (Originalsprache)
Multiscale systems are ubiquitous in science and technology, but are notoriously challenging to simulate as short spatiotemporal scales must be appropriately linked to emergent bulk physics. When expensive high-dimensional dynamical systems are coarse-grained into low-dimensional models, the entropic loss of information leads to emergent physics which are dissipative, history-dependent, and stochastic. To machine learn coarse-grained dynamics from time-series observations of particle trajectories, we propose a framework using the metriplectic bracket formalism that preserves these properties by construction; most notably, the framework guarantees discrete notions of the first and second laws of thermodynamics, conservation of momentum, and a discrete fluctuation–dissipation balance crucial for capturing nonequilibrium statistics. We introduce the mathematical framework abstractly before specializing to a particle discretization. As labels are generally unavailable for entropic state variables, we introduce a self-supervised learning strategy to identify emergent structural variables. We validate the method on benchmark systems and demonstrate its utility on two challenging examples: 1) coarse-graining star polymers at challenging levels of coarse-graining while preserving nonequilibrium statistics, and 2) learning models from high-speed video of colloidal suspensions that capture coupling between local rearrangement events and emergent stochastic dynamics. We provide open-source implementations in both PyTorch and LAMMPS, enabling large-scale inference and extensibility to diverse particle-based systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mechanical Engineering and Applied Mechanics, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA 19104.
- Department of Materials Science and Engineering, Carnegie Mellon University, Pittsburgh, PA 15213.
ORCID-Profile: Paulo E Arratia, Nathaniel Trask
Förderung
- U.S. Department of Energy (DOE)
- DOD | USA | AFC | CCDC | Army Research Office (ARO)
- DOE | Office of Science (SC)
Zitieren
APA
Hernández, Q., Win, M., O'Connor, T. C., Arratia, P. E., & Trask, N. (2026). Data-driven particle dynamics: Structure-preserving coarse-graining for emergent behavior in nonequilibrium systems. Proceedings of the National Academy of Sciences, 123(20). https://doi.org/10.1073/pnas.2519631123
Vancouver
Hernández Q, Win M, O'Connor TC, Arratia PE, Trask N. Data-driven particle dynamics: Structure-preserving coarse-graining for emergent behavior in nonequilibrium systems. Proceedings of the National Academy of Sciences. 2026;123(20). doi:10.1073/pnas.2519631123
BibTeX
@article{Hernndez2026,
author = {Hernández, Quercus and Win, Max and O'Connor, Thomas C and Arratia, Paulo E and Trask, Nathaniel},
title = {Data-driven particle dynamics: Structure-preserving coarse-graining for emergent behavior in nonequilibrium systems},
journal = {Proceedings of the National Academy of Sciences},
year = {2026},
volume = {123},
number = {20},
doi = {10.1073/pnas.2519631123}
}
EUVIMED