← Search

Data · dataset · 2023

Physics-inspired equivariant descriptors of non-bonded interactions

Listed in Materials Cloud Archive

One essential ingredient in many machine learning (ML) based methods for atomistic modeling of materials and molecules is the use of locality.

Description

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.

Links

Where it is published

Catalogue records · 1

Topics

Provenance · 1 source records, 13 field assertions
SourceKeyLast seenRaw
Materials Cloud Archive405an-d81832 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0
concepts[field].anzsrc:group:4611mapping · archive materialscloud orgvocabulary-mapper@1.0.0keywords['machine learning']
concepts[field].local:field:computer-science-aimapping · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0
concepts[topic].invenio_subject:archive_materialscloud_org:dispersionsource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0
concepts[topic].invenio_subject:archive_materialscloud_org:electrostaticssource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0
concepts[topic].invenio_subject:archive_materialscloud_org:ercsource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0
concepts[topic].invenio_subject:archive_materialscloud_org:long-range-interactionssource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0
concepts[topic].invenio_subject:archive_materialscloud_org:machine-learningsource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0
descriptionsource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0/metadata/description
licensesource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0
publication_datesource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0
titlesource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0/metadata/title
updated_datesource · archive materialscloud orgconnector:archive_materialscloud_org@1.0.0