Crystal structure prediction by combining graph network and optimization algorithm

Crystal structure prediction is a long-standing challenge in condensed matter and chemical science. Here we report a machine-learning approach for crystal structure prediction, in which a graph network (GN) is employed to establish a correlation model between the crystal structure and formation enth...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Nature communications Jg. 13; H. 1; S. 1492 - 8
Hauptverfasser: Cheng, Guanjian, Gong, Xin-Gao, Yin, Wan-Jian
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group UK 21.03.2022
Nature Publishing Group
Nature Portfolio
Schlagworte:
119/118
639/301/1034/1037
639/638/563/980
639/638/563/983
Algorithms
Atomic properties
Bayesian analysis
Comparative studies
Computer applications
Crystal structure
Density functional theory
Enthalpy
Humanities and Social Sciences
Learning algorithms
Machine learning
multidisciplinary
Optimization algorithms
Particle swarm optimization
Performance prediction
Predictions
Science
Science (multidisciplinary)
ISSN:2041-1723, 2041-1723
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Crystal structure prediction is a long-standing challenge in condensed matter and chemical science. Here we report a machine-learning approach for crystal structure prediction, in which a graph network (GN) is employed to establish a correlation model between the crystal structure and formation enthalpies at the given database, and an optimization algorithm (OA) is used to accelerate the search for crystal structure with lowest formation enthalpy. The framework of the utilized approach (a database + a GN model + an optimization algorithm) is flexible. We implemented two benchmark databases, i.e ., the open quantum materials database (OQMD) and Matbench (MatB), and three OAs, i.e ., random searching (RAS), particle-swarm optimization (PSO) and Bayesian optimization (BO), that can predict crystal structures at a given number of atoms in a periodic cell. The comparative studies show that the GN model trained on MatB combined with BO, i.e ., GN(MatB)-BO, exhibit the best performance for predicting crystal structures of 29 typical compounds with a computational cost three orders of magnitude less than that required for conventional approaches screening structures through density functional theory calculation. The flexible framework in combination with a materials database, a graph network, and an optimization algorithm may open new avenues for data-driven crystal structural predictions. Predicting crystal structure prior to experimental synthesis is highly desirable. Here the authors propose a machine-learning framework combining graph network and optimization algorithms for crystal structure prediction, which is about three orders of magnitude faster than DFT-based approach.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-022-29241-4