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
- Materials Cloud Archive record archive.materialscloud.org/records/405an-d8183 ↗
landing page · from archive materialscloud org
- DOI doi.org/10.24435/materialscloud:23-99 ↗
DOI / persistent id · from archive materialscloud org
Catalogue records · 1
- InvenioRDM API archive.materialscloud.org/api/records/405an-d8183 ↗
metadata API · from archive materialscloud org
Topics
- Stated by source
- dispersion · Electrostatics · ERC · long-range interactions · Machine-learning
- From keywords
- Computer Science & AI · Machine learning
Provenance · 1 source records, 13 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Materials Cloud Archive | 405an-d8183 | 2 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | |
| concepts[field].anzsrc:group:4611 | mapping · archive materialscloud org | vocabulary-mapper@1.0.0 | keywords['machine learning'] |
| concepts[field].local:field:computer-science-ai | mapping · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | |
| concepts[topic].invenio_subject:archive_materialscloud_org:dispersion | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | |
| concepts[topic].invenio_subject:archive_materialscloud_org:electrostatics | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | |
| concepts[topic].invenio_subject:archive_materialscloud_org:erc | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | |
| concepts[topic].invenio_subject:archive_materialscloud_org:long-range-interactions | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | |
| concepts[topic].invenio_subject:archive_materialscloud_org:machine-learning | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | |
| description | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | /metadata/description |
| license | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | |
| publication_date | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | |
| title | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 | /metadata/title |
| updated_date | source · archive materialscloud org | connector:archive_materialscloud_org@1.0.0 |