Thermodynamic properties of chemically disordered compounds via AI-driven estimation of partition function with the PULSE method

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bernard, Baptiste, Messina, Luca, Kawasaki, Eiji, Bourasseau, Emeric
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916056156602368
author Bernard, Baptiste
Messina, Luca
Kawasaki, Eiji
Bourasseau, Emeric
author_facet Bernard, Baptiste
Messina, Luca
Kawasaki, Eiji
Bourasseau, Emeric
contents In this article, we present an improved version of the PULSE method (Partition function Unsupervised Learning Sampling and Evaluation) for estimating the thermodynamic properties of chemically disordered compounds. The aim is to reduce the computational cost of Monte Carlo approaches for this type of material and to demonstrate that this generative tool can estimate thermodynamic properties by sampling and estimating the partition function of the system. To validate this innovative approach, we use the 2D Ising model as a benchmark. We demonstrate that our method accurately reproduces average properties with high precision and efficiency compared to traditional Monte Carlo sampling methods. Our results highlight the efficiency and adaptability of the PULSE method, making it a valuable tool for studying materials for which conventional methods are too inefficient to compute properties affected by chemical disorder at low cost.
format Preprint
id arxiv_https___arxiv_org_abs_2605_28594
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Thermodynamic properties of chemically disordered compounds via AI-driven estimation of partition function with the PULSE method
Bernard, Baptiste
Messina, Luca
Kawasaki, Eiji
Bourasseau, Emeric
Statistical Mechanics
Artificial Intelligence
Computational Physics
In this article, we present an improved version of the PULSE method (Partition function Unsupervised Learning Sampling and Evaluation) for estimating the thermodynamic properties of chemically disordered compounds. The aim is to reduce the computational cost of Monte Carlo approaches for this type of material and to demonstrate that this generative tool can estimate thermodynamic properties by sampling and estimating the partition function of the system. To validate this innovative approach, we use the 2D Ising model as a benchmark. We demonstrate that our method accurately reproduces average properties with high precision and efficiency compared to traditional Monte Carlo sampling methods. Our results highlight the efficiency and adaptability of the PULSE method, making it a valuable tool for studying materials for which conventional methods are too inefficient to compute properties affected by chemical disorder at low cost.
title Thermodynamic properties of chemically disordered compounds via AI-driven estimation of partition function with the PULSE method
topic Statistical Mechanics
Artificial Intelligence
Computational Physics
url https://arxiv.org/abs/2605.28594