Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations

We develop a framework for on-the-fly machine learned force field molecular dynamics simulations based on the multipole featurization scheme that overcomes the bottleneck with the number of chemical elements. Considering bulk systems with up to 6 elements, we demonstrate that the number of density f...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Timmerman, Lucas R, Kumar, Shashikant, Suryanarayana, Phanish, Medford, Andrew J
Format:	Artikel
Sprache:	eng
Schlagworte:	Physics - Chemical Physics Physics - Computational Physics Physics - Materials Science
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page
container_issue
container_start_page
container_title
container_volume
creator	Timmerman, Lucas R Kumar, Shashikant Suryanarayana, Phanish Medford, Andrew J
description	We develop a framework for on-the-fly machine learned force field molecular dynamics simulations based on the multipole featurization scheme that overcomes the bottleneck with the number of chemical elements. Considering bulk systems with up to 6 elements, we demonstrate that the number of density functional theory calls remains approximately independent of the number of chemical elements, in contrast to the increase in the smooth overlap of atomic positions scheme.
doi_str_mv	10.48550/arxiv.2404.07961
format	Article
fullrecord	<record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2404_07961</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2404_07961</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-30e9527eafb10159a00d961840889cba1fa409bea24fce276c8fddb436b5fce73</originalsourceid><addsrcrecordid>eNotj8tOwzAURL1hgQofwKr3BxLsxHktUcVLqtRN99G1c00MtlM5oWr-HlNYjXQ0Gs1h7EHwXLZVxR8xXuw5LySXOW-6Wtyyz8OZop68DR-wjAR6JG81Okjs5OhilxXUtCyOAukvsAGmkKViZtwKHvVoA4EjjIEG8JMj_e0wwrAGTDszzNYnsNgpzHfsxqCb6f4_N-z48nzcvWX7w-v77mmfYd2IrOTUVUVDaJTgouqQ8yE9bSVv204rFAYl7xRhIY2moql1a4ZBybJWVQJNuWHbv9mrbH-K1mNc-1_p_ipd_gCV3FUG</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations</title><source>arXiv.org</source><creator>Timmerman, Lucas R ; Kumar, Shashikant ; Suryanarayana, Phanish ; Medford, Andrew J</creator><creatorcontrib>Timmerman, Lucas R ; Kumar, Shashikant ; Suryanarayana, Phanish ; Medford, Andrew J</creatorcontrib><description>We develop a framework for on-the-fly machine learned force field molecular dynamics simulations based on the multipole featurization scheme that overcomes the bottleneck with the number of chemical elements. Considering bulk systems with up to 6 elements, we demonstrate that the number of density functional theory calls remains approximately independent of the number of chemical elements, in contrast to the increase in the smooth overlap of atomic positions scheme.</description><identifier>DOI: 10.48550/arxiv.2404.07961</identifier><language>eng</language><subject>Physics - Chemical Physics ; Physics - Computational Physics ; Physics - Materials Science</subject><creationdate>2024-04</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2404.07961$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2404.07961$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Timmerman, Lucas R</creatorcontrib><creatorcontrib>Kumar, Shashikant</creatorcontrib><creatorcontrib>Suryanarayana, Phanish</creatorcontrib><creatorcontrib>Medford, Andrew J</creatorcontrib><title>Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations</title><description>We develop a framework for on-the-fly machine learned force field molecular dynamics simulations based on the multipole featurization scheme that overcomes the bottleneck with the number of chemical elements. Considering bulk systems with up to 6 elements, we demonstrate that the number of density functional theory calls remains approximately independent of the number of chemical elements, in contrast to the increase in the smooth overlap of atomic positions scheme.</description><subject>Physics - Chemical Physics</subject><subject>Physics - Computational Physics</subject><subject>Physics - Materials Science</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAURL1hgQofwKr3BxLsxHktUcVLqtRN99G1c00MtlM5oWr-HlNYjXQ0Gs1h7EHwXLZVxR8xXuw5LySXOW-6Wtyyz8OZop68DR-wjAR6JG81Okjs5OhilxXUtCyOAukvsAGmkKViZtwKHvVoA4EjjIEG8JMj_e0wwrAGTDszzNYnsNgpzHfsxqCb6f4_N-z48nzcvWX7w-v77mmfYd2IrOTUVUVDaJTgouqQ8yE9bSVv204rFAYl7xRhIY2moql1a4ZBybJWVQJNuWHbv9mrbH-K1mNc-1_p_ipd_gCV3FUG</recordid><startdate>20240411</startdate><enddate>20240411</enddate><creator>Timmerman, Lucas R</creator><creator>Kumar, Shashikant</creator><creator>Suryanarayana, Phanish</creator><creator>Medford, Andrew J</creator><scope>GOX</scope></search><sort><creationdate>20240411</creationdate><title>Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations</title><author>Timmerman, Lucas R ; Kumar, Shashikant ; Suryanarayana, Phanish ; Medford, Andrew J</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-30e9527eafb10159a00d961840889cba1fa409bea24fce276c8fddb436b5fce73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Physics - Chemical Physics</topic><topic>Physics - Computational Physics</topic><topic>Physics - Materials Science</topic><toplevel>online_resources</toplevel><creatorcontrib>Timmerman, Lucas R</creatorcontrib><creatorcontrib>Kumar, Shashikant</creatorcontrib><creatorcontrib>Suryanarayana, Phanish</creatorcontrib><creatorcontrib>Medford, Andrew J</creatorcontrib><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Timmerman, Lucas R</au><au>Kumar, Shashikant</au><au>Suryanarayana, Phanish</au><au>Medford, Andrew J</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations</atitle><date>2024-04-11</date><risdate>2024</risdate><abstract>We develop a framework for on-the-fly machine learned force field molecular dynamics simulations based on the multipole featurization scheme that overcomes the bottleneck with the number of chemical elements. Considering bulk systems with up to 6 elements, we demonstrate that the number of density functional theory calls remains approximately independent of the number of chemical elements, in contrast to the increase in the smooth overlap of atomic positions scheme.</abstract><doi>10.48550/arxiv.2404.07961</doi><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	DOI: 10.48550/arxiv.2404.07961
ispartof
issn
language	eng
recordid	cdi_arxiv_primary_2404_07961
source	arXiv.org
subjects	Physics - Chemical Physics Physics - Computational Physics Physics - Materials Science
title	Overcoming the chemical complexity bottleneck in on-the-fly machine learned molecular dynamics simulations
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T03%3A49%3A26IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Overcoming%20the%20chemical%20complexity%20bottleneck%20in%20on-the-fly%20machine%20learned%20molecular%20dynamics%20simulations&rft.au=Timmerman,%20Lucas%20R&rft.date=2024-04-11&rft_id=info:doi/10.48550/arxiv.2404.07961&rft_dat=%3Carxiv_GOX%3E2404_07961%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true