Efficient Long-Range Machine Learning Force Fields for Liquid and Materials Properties

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Weber, John L., Guha, Rishabh D., Agarwal, Garvit, Wei, Yujing, Fike, Aidan A., Xie, Xiaowei, Stevenson, James, Santra, Biswajit, Friesner, Richard A., Leswing, Karl, Halls, Mathew D., Abel, Robert, Jacobson, Leif D.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909717751660544
author Weber, John L.
Guha, Rishabh D.
Agarwal, Garvit
Wei, Yujing
Fike, Aidan A.
Xie, Xiaowei
Stevenson, James
Santra, Biswajit
Friesner, Richard A.
Leswing, Karl
Halls, Mathew D.
Abel, Robert
Jacobson, Leif D.
author_facet Weber, John L.
Guha, Rishabh D.
Agarwal, Garvit
Wei, Yujing
Fike, Aidan A.
Xie, Xiaowei
Stevenson, James
Santra, Biswajit
Friesner, Richard A.
Leswing, Karl
Halls, Mathew D.
Abel, Robert
Jacobson, Leif D.
contents Machine learning force fields (MLFFs) have emerged as a sophisticated tool for cost-efficient atomistic simulations approaching DFT accuracy, with recent message passing MLFFs able to cover the entire periodic table. We present an invariant message passing MLFF architecture (MPNICE) which iteratively predicts atomic partial charges, including long-range interactions, enabling the prediction of charge-dependent properties while achieving 5-20x faster inference versus models with comparable accuracy. We train direct and delta-learned MPNICE models for organic systems, and benchmark against experimental properties of liquid and solid systems. We also benchmark the energetics of finite systems, contributing a new set of torsion scans with charged species and a new set of DLPNO-CCSD(T) references for the TorsionNet500 benchmark. We additionally train and benchmark MPNICE models for bulk inorganic crystals, focusing on structural ranking and mechanical properties. Finally, we explore multi-task models for both inorganic and organic systems, which exhibit slightly decreased performance on domain-specific tasks but surprising generalization, stably predicting the gas phase structure of $\simeq500$ Pt/Ir organometallic complexes despite never training to organometallic complexes of any kind.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06462
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Long-Range Machine Learning Force Fields for Liquid and Materials Properties
Weber, John L.
Guha, Rishabh D.
Agarwal, Garvit
Wei, Yujing
Fike, Aidan A.
Xie, Xiaowei
Stevenson, James
Santra, Biswajit
Friesner, Richard A.
Leswing, Karl
Halls, Mathew D.
Abel, Robert
Jacobson, Leif D.
Chemical Physics
Materials Science
Machine learning force fields (MLFFs) have emerged as a sophisticated tool for cost-efficient atomistic simulations approaching DFT accuracy, with recent message passing MLFFs able to cover the entire periodic table. We present an invariant message passing MLFF architecture (MPNICE) which iteratively predicts atomic partial charges, including long-range interactions, enabling the prediction of charge-dependent properties while achieving 5-20x faster inference versus models with comparable accuracy. We train direct and delta-learned MPNICE models for organic systems, and benchmark against experimental properties of liquid and solid systems. We also benchmark the energetics of finite systems, contributing a new set of torsion scans with charged species and a new set of DLPNO-CCSD(T) references for the TorsionNet500 benchmark. We additionally train and benchmark MPNICE models for bulk inorganic crystals, focusing on structural ranking and mechanical properties. Finally, we explore multi-task models for both inorganic and organic systems, which exhibit slightly decreased performance on domain-specific tasks but surprising generalization, stably predicting the gas phase structure of $\simeq500$ Pt/Ir organometallic complexes despite never training to organometallic complexes of any kind.
title Efficient Long-Range Machine Learning Force Fields for Liquid and Materials Properties
topic Chemical Physics
Materials Science
url https://arxiv.org/abs/2505.06462