Machine Learning Multiscale Interactions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Solé, Àlex, Suárez-Dou, Sergio, Mosella-Montoro, Albert, Gómez-Coca, Silvia, Ruiz, Eliseo, Tkatchenko, Alexandre, Ruiz-Hidalgo, Javier
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913161449308160
author Solé, Àlex
Suárez-Dou, Sergio
Mosella-Montoro, Albert
Gómez-Coca, Silvia
Ruiz, Eliseo
Tkatchenko, Alexandre
Ruiz-Hidalgo, Javier
author_facet Solé, Àlex
Suárez-Dou, Sergio
Mosella-Montoro, Albert
Gómez-Coca, Silvia
Ruiz, Eliseo
Tkatchenko, Alexandre
Ruiz-Hidalgo, Javier
contents Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predictive machine learning (ML) models. Most scientific ML models focus on a narrow range of interactions. While machine learning force fields (MLFFs) offer near-quantum accuracy, the ubiquitous message-passing layers miss long-range many-body effects. Here we introduce the Multiscale Structural Ensemble (MuSE), a hierarchical model that uses Soft Coarse-Graining Pooling to construct coarse representations from smooth fractional assignments of atoms to coarse nodes, enabling MLFF modules to operate across multiple scales. MuSE is architecture-agnostic and coupled with SO3krates, MACE, and PaiNN MLFFs for both molecules and materials. We demonstrate the power of MuSE through Hessian-based benchmarks, folding trajectories for biomolecules, and energy profiles in molecule-graphene nanostructures, where MuSE accurately captures quantum-mechanical interactions at relevant scales -- unlike other recent long-range ML models.
format Preprint
id arxiv_https___arxiv_org_abs_2605_25710
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Machine Learning Multiscale Interactions
Solé, Àlex
Suárez-Dou, Sergio
Mosella-Montoro, Albert
Gómez-Coca, Silvia
Ruiz, Eliseo
Tkatchenko, Alexandre
Ruiz-Hidalgo, Javier
Chemical Physics
Materials Science
Machine Learning
Computational Physics
Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predictive machine learning (ML) models. Most scientific ML models focus on a narrow range of interactions. While machine learning force fields (MLFFs) offer near-quantum accuracy, the ubiquitous message-passing layers miss long-range many-body effects. Here we introduce the Multiscale Structural Ensemble (MuSE), a hierarchical model that uses Soft Coarse-Graining Pooling to construct coarse representations from smooth fractional assignments of atoms to coarse nodes, enabling MLFF modules to operate across multiple scales. MuSE is architecture-agnostic and coupled with SO3krates, MACE, and PaiNN MLFFs for both molecules and materials. We demonstrate the power of MuSE through Hessian-based benchmarks, folding trajectories for biomolecules, and energy profiles in molecule-graphene nanostructures, where MuSE accurately captures quantum-mechanical interactions at relevant scales -- unlike other recent long-range ML models.
title Machine Learning Multiscale Interactions
topic Chemical Physics
Materials Science
Machine Learning
Computational Physics
url https://arxiv.org/abs/2605.25710