Zitieren Sie bitte immer diesen URN: urn:nbn:de:kobv:b43-647829

A foundation model for atomistic materials chemistry

  • Atomistic simulations of matter, especially those that leverage first-principles (ab initio) electronic structure theory, provide a microscopic view of the world, underpinning much of our understanding of chemistry and materials science. Over the last decade or so, machine-learned force fields have transformed atomistic modeling by enabling simulations of ab initio quality over unprecedented time and length scales. However, early machine-learning (ML) force fields have largely been limited by (i) the substantial computational and human effort required to develop and validate potentials for each particular system of interest and (ii) a general lack of transferability from one chemical system to the next. Here, we show that it is possible to create a general-purpose atomistic ML model, trained on a public dataset of moderate size, that is capable of running stable molecular dynamics for a wide range of molecules and materials. We demonstrate the power of the MACE-MP-0 model—and itsAtomistic simulations of matter, especially those that leverage first-principles (ab initio) electronic structure theory, provide a microscopic view of the world, underpinning much of our understanding of chemistry and materials science. Over the last decade or so, machine-learned force fields have transformed atomistic modeling by enabling simulations of ab initio quality over unprecedented time and length scales. However, early machine-learning (ML) force fields have largely been limited by (i) the substantial computational and human effort required to develop and validate potentials for each particular system of interest and (ii) a general lack of transferability from one chemical system to the next. Here, we show that it is possible to create a general-purpose atomistic ML model, trained on a public dataset of moderate size, that is capable of running stable molecular dynamics for a wide range of molecules and materials. We demonstrate the power of the MACE-MP-0 model—and its qualitative and at times quantitative accuracy—on a diverse set of problems in the physical sciences, including properties of solids, liquids, gases, chemical reactions, interfaces, and even the dynamics of a small protein. The model can be applied out of the box as a starting or “foundation” model for any atomistic system of interest and, when desired, can be fine-tuned on just a handful of application-specific data points to reach ab initio accuracy. Establishing that a stable force-field model can cover almost all materials changes atomistic modeling in a fundamental way: experienced users obtain reliable results much faster, and beginners face a lower barrier to entry. Foundation models thus represent a step toward democratizing the revolution in atomic-scale modeling that has been brought about by ML force fields.zeige mehrzeige weniger

Volltext Dateien herunterladen

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar Anzahl der Zugriffe auf dieses Dokument
Metadaten
Autor*innen:Ilyes BatatiaORCiD, Philipp BennerORCiD, Yuan ChiangORCiD, Alin M. ElenaORCiD, Dávid P. KovácsORCiD, Janosh RiebesellORCiD, Xavier R. AdvinculaORCiD, Mark AstaORCiD, Matthew Avaylon, William J. BaldwinORCiD, Fabian BergerORCiD, Noam BernsteinORCiD, Arghya BhowmikORCiD, Filippo BigiORCiD, Samuel M. BlauORCiD, Vlad CărareORCiD, Michele CeriottiORCiD, Sanggyu ChongORCiD, James P. DarbyORCiD, Sandip DeORCiD, Flaviano Della PiaORCiD, Volker L. DeringerORCiD, Rokas ElijošiusORCiD, Zakariya El-MachachiORCiD, Edvin FakoORCiD, Fabio FalcioniORCiD, Andrea C. FerrariORCiD, John L. A. GardnerORCiD, Mikołaj J. GawkowskiORCiD, Annalena Genreith-SchrieverORCiD, Janine GeorgeORCiD, Rhys E. A. GoodallORCiD, Jonas GrandelORCiD, Clare P. GreyORCiD, Petr GrigorevORCiD, Shuang HanORCiD, Will HandleyORCiD, Hendrik H. HeenenORCiD, Kersti HermanssonORCiD, Cheuk Hin HoORCiD, Stephan HofmannORCiD, Christian HolmORCiD, Jad JaafarORCiD, Konstantin S. JakobORCiD, Hyunwook JungORCiD, Venkat KapilORCiD, Aaron D. KaplanORCiD, Nima KarimitariORCiD, Aakash A. Naik, Gábor CsányiORCiD
Dokumenttyp:Zeitschriftenartikel
Veröffentlichungsform:Verlagsliteratur
Sprache:Englisch
Titel des übergeordneten Werkes (Englisch):The Journal of Chemical Physics
Jahr der Erstveröffentlichung:2025
Organisationseinheit der BAM:6 Materialchemie
6 Materialchemie / 6.6 Digitale Materialchemie
VP Vizepräsident
VP Vizepräsident / VP.1 eScience
Veröffentlichende Institution:Bundesanstalt für Materialforschung und -prüfung (BAM)
Verlag:AIP Publishing
Jahrgang/Band:163
Ausgabe/Heft:18
Aufsatznummer:184110
Erste Seite:1
Letzte Seite:89
DDC-Klassifikation:Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Ingenieurwissenschaften und zugeordnete Tätigkeiten
Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Angewandte Physik
Freie Schlagwörter:Batteries; Materials Design; Nanoparticles; Thermal Conducitivity
Themenfelder/Aktivitätsfelder der BAM:Energie
Energie / Elektrische Energiespeicher und -umwandlung
Material
Material / Advanced Materials
Material / Materialdesign
DOI:10.1063/5.0297006
URN:urn:nbn:de:kobv:b43-647829
ISSN:0021-9606
Verfügbarkeit des Dokuments:Datei für die Öffentlichkeit verfügbar ("Open Access")
Lizenz (Deutsch):License LogoCreative Commons - CC BY - Namensnennung 4.0 International
Datum der Freischaltung:20.11.2025
Referierte Publikation:Ja
Datum der Eintragung als referierte Publikation:01.12.2025
Schriftenreihen ohne Nummerierung:Wissenschaftliche Artikel der BAM
Einverstanden
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.