2026-04-20T09:48:38Z https://archive.materialscloud.org/oai2d

oai:materialscloud.org:1924 2026-01-30T15:01:22Z openaire_data community-mcarchive

Ceriotti, Michele Huguenin-Dumittan, Kevin K. Loche, Philip Ni, Haoran Ceriotti, Michele 2023-10-03 One essential ingredient in many machine learning (ML) based methods for atomistic modeling of materials and molecules is the use of locality. While allowing better system-size scaling, this systematically neglects long-range (LR) effects, such as electrostatics or dispersion interaction. We present an extension of the long distance equivariant (LODE) framework that can handle diverse LR interactions in a consistent way, and seamlessly integrates with preexisting methods by building new sets of atom centered features. We provide a direct physical interpretation of these using the multipole expansion, which allows for simpler and more efficient implementations. The framework is applied to simple toy systems as proof of concept, and a heterogeneous set of molecular dimers to push the method to its limits. By generalizing LODE to arbitrary asymptotic behaviors, we provide a coherent approach to treat arbitrary two- and many-body non-bonded interactions in the data-driven modeling of matter. application/octet-stream application/octet-stream chemical/x-xyz chemical/x-xyz chemical/x-xyz chemical/x-xyz chemical/x-xyz text/markdown https://doi.org/10.24435/materialscloud:23-99 oai:materialscloud.org:1924 mcid:2023.151 eng Materials Cloud https://doi.org/10.1021/acs.jpclett.3c02375 https://doi.org/10.1063/1.5128375 https://doi.org/10.1063/5.0251713 https://archive.materialscloud.org/communities/mcarchive https://doi.org/10.24435/materialscloud:je-rd info:eu-repo/semantics/openAccess Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode ERC machine learning long-range interactions electrostatics dispersion Physics-inspired equivariant descriptors of non-bonded interactions info:eu-repo/semantics/other