Enregistré dans:
Détails bibliographiques
Auteurs principaux: Eldred, Christopher, Gay-Balmaz, François, Putkaradze, Vakhtang
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2509.09899
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914411973705728
author Eldred, Christopher
Gay-Balmaz, François
Putkaradze, Vakhtang
author_facet Eldred, Christopher
Gay-Balmaz, François
Putkaradze, Vakhtang
contents Much attention has recently been devoted to data-based computing of evolution of physical systems. In such approaches, information about data points from past trajectories in phase space is used to reconstruct the equations of motion and to predict future solutions that have not been observed before. However, in many cases, the available data does not correspond to the variables that define the system's phase space. We focus our attention on the important example of dissipative dynamical systems. In that case, the phase space consists of coordinates, momenta and entropies; however, the momenta and entropies cannot, in general, be observed directly. To address this difficulty, we develop an efficient data-based computing framework based exclusively on observable variables, by constructing a novel approach based on the thermodynamic Lagrangian, and constructing neural networks that respect the thermodynamics and guarantees the non-decreasing entropy evolution. We show that our network can provide an efficient description of phase space evolution based on a limited number of data points and a relatively small number of parameters in the system.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09899
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Variational Neural Networks for Observable Thermodynamics (V-NOTS)
Eldred, Christopher
Gay-Balmaz, François
Putkaradze, Vakhtang
Machine Learning
Much attention has recently been devoted to data-based computing of evolution of physical systems. In such approaches, information about data points from past trajectories in phase space is used to reconstruct the equations of motion and to predict future solutions that have not been observed before. However, in many cases, the available data does not correspond to the variables that define the system's phase space. We focus our attention on the important example of dissipative dynamical systems. In that case, the phase space consists of coordinates, momenta and entropies; however, the momenta and entropies cannot, in general, be observed directly. To address this difficulty, we develop an efficient data-based computing framework based exclusively on observable variables, by constructing a novel approach based on the thermodynamic Lagrangian, and constructing neural networks that respect the thermodynamics and guarantees the non-decreasing entropy evolution. We show that our network can provide an efficient description of phase space evolution based on a limited number of data points and a relatively small number of parameters in the system.
title Variational Neural Networks for Observable Thermodynamics (V-NOTS)
topic Machine Learning
url https://arxiv.org/abs/2509.09899