Accelerated Machine Learning Force Field for Predicting Thermal Conductivity of Organic Liquids

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Wei, Liu, Siyuan, Wang, Hongyi, Mu, Zhenliang, Pu, Zhichen, Han, Xu, Zheng, Tianze, Yang, Zhenze, Wang, Zhi, Gao, Weihao, Cao, Yidan, Yu, Kuang, Gong, Sheng, Yan, Wen
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913177294340096
author Feng, Wei
Liu, Siyuan
Wang, Hongyi
Mu, Zhenliang
Pu, Zhichen
Han, Xu
Zheng, Tianze
Yang, Zhenze
Wang, Zhi
Gao, Weihao
Cao, Yidan
Yu, Kuang
Gong, Sheng
Yan, Wen
author_facet Feng, Wei
Liu, Siyuan
Wang, Hongyi
Mu, Zhenliang
Pu, Zhichen
Han, Xu
Zheng, Tianze
Yang, Zhenze
Wang, Zhi
Gao, Weihao
Cao, Yidan
Yu, Kuang
Gong, Sheng
Yan, Wen
contents The thermal conductivity of organic liquids is a vital parameter influencing various industrial and environmental applications, including energy conversion, electronics cooling, and chemical processing. However, atomistic simulation of thermal conductivity of organic liquids has been hindered by the limited accuracy of classical force fields and the huge computational demand of ab initio methods. In this work, we present a machine learning force field (MLFF)-based molecular dynamics simulation workflow to predict the thermal conductivity of 20 organic liquids. Here, we introduce the concept of differential attention into the MLFF architecture for enhanced learning ability, and we use density of the liquids to align the MLFF with experiments. As a result, this workflow achieves a mean absolute percentage error of 14% for the thermal conductivity of various organic liquids, significantly lower than that of the current off-the-shelf classical force field (78%). Furthermore, the MLFF is rewritten using Triton language to maximize simulation speed, enabling rapid prediction of thermal conductivity.
format Preprint
id arxiv_https___arxiv_org_abs_2512_01627
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accelerated Machine Learning Force Field for Predicting Thermal Conductivity of Organic Liquids
Feng, Wei
Liu, Siyuan
Wang, Hongyi
Mu, Zhenliang
Pu, Zhichen
Han, Xu
Zheng, Tianze
Yang, Zhenze
Wang, Zhi
Gao, Weihao
Cao, Yidan
Yu, Kuang
Gong, Sheng
Yan, Wen
Chemical Physics
Computational Physics
The thermal conductivity of organic liquids is a vital parameter influencing various industrial and environmental applications, including energy conversion, electronics cooling, and chemical processing. However, atomistic simulation of thermal conductivity of organic liquids has been hindered by the limited accuracy of classical force fields and the huge computational demand of ab initio methods. In this work, we present a machine learning force field (MLFF)-based molecular dynamics simulation workflow to predict the thermal conductivity of 20 organic liquids. Here, we introduce the concept of differential attention into the MLFF architecture for enhanced learning ability, and we use density of the liquids to align the MLFF with experiments. As a result, this workflow achieves a mean absolute percentage error of 14% for the thermal conductivity of various organic liquids, significantly lower than that of the current off-the-shelf classical force field (78%). Furthermore, the MLFF is rewritten using Triton language to maximize simulation speed, enabling rapid prediction of thermal conductivity.
title Accelerated Machine Learning Force Field for Predicting Thermal Conductivity of Organic Liquids
topic Chemical Physics
Computational Physics
url https://arxiv.org/abs/2512.01627