Robust Data Generation, Heuristics and Machine Learning for Materials Design

  • Despite significant progress, computational materials design still faces challenges, especially when simulating large systems needed to describe defects, interfaces, or amorphous states with the accuracy of density functional theory (DFT) or beyond.[1] To address these limitations, machine learning (ML) methods have become increasingly popular in recent years. In this talk, I will present how we’ve developed robust data generation strategies that support the creation and benchmarking of new ML models.[2] I’ll focus on methods for large-scale quantum-chemical bonding analysis and workflows for ML interatomic potentials. We’ve shown that quantum-chemical bonding properties can be used in ML models to predict phononic properties.[3] This enables us to validate several expected correlations— such as the link between bonding strength and force constants—on a large scale. Additionally, we’ve built an automated training framework for machine-learned interatomic potentials (autoplex).[4]Despite significant progress, computational materials design still faces challenges, especially when simulating large systems needed to describe defects, interfaces, or amorphous states with the accuracy of density functional theory (DFT) or beyond.[1] To address these limitations, machine learning (ML) methods have become increasingly popular in recent years. In this talk, I will present how we’ve developed robust data generation strategies that support the creation and benchmarking of new ML models.[2] I’ll focus on methods for large-scale quantum-chemical bonding analysis and workflows for ML interatomic potentials. We’ve shown that quantum-chemical bonding properties can be used in ML models to predict phononic properties.[3] This enables us to validate several expected correlations— such as the link between bonding strength and force constants—on a large scale. Additionally, we’ve built an automated training framework for machine-learned interatomic potentials (autoplex).[4] Initial workflows include random structure searches, which are well-suited for general-purpose potentials, as well as workflows tailored to ML potentials with accurate phonon properties. While atomistic simulations are highly effective for certain material properties, others— like magnetism or synthesizability—remain difficult. In these cases, it’s promising to benchmark established ab initio methods against chemical heuristics or to develop new ML models based primarily on experimental data.[5,6]zeige mehrzeige weniger

Volltext Dateien herunterladen

  • Dresden_2025_September_final.pdf
    eng

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar Anzahl der Zugriffe auf dieses Dokument
Metadaten
Autor*innen:Janine GeorgeORCiD
Dokumenttyp:Vortrag
Veröffentlichungsform:Präsentation
Sprache:Englisch
Jahr der Erstveröffentlichung:2025
Organisationseinheit der BAM:6 Materialchemie
6 Materialchemie / 6.6 Digitale Materialchemie
DDC-Klassifikation:Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Ingenieurwissenschaften und zugeordnete Tätigkeiten
Freie Schlagwörter:Automation; Machine Learned Interatomic Potentials; Magnetism; Materials Acceleration Platforms; Materials Design; Synthesizability; Workflows
Themenfelder/Aktivitätsfelder der BAM:Material
Material / Materialdesign
Veranstaltung:SusML (Sustainable Machine Learning Workshop)
Veranstaltungsort:Dresden, Germany
Beginndatum der Veranstaltung:29.09.2025
Enddatum der Veranstaltung:01.10.2025
Verfügbarkeit des Dokuments:Datei im Netzwerk der BAM verfügbar ("Closed Access")
Datum der Freischaltung:01.10.2025
Referierte Publikation:Nein
Eingeladener Vortrag (wissenschaftliche Konferenzen):Ja
Einverstanden
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.