On-the-Fly Machine Learning of Atomic Potential in Density Functional Theory Structure Optimization

被引:112
作者
Jacobsen, T. L.
Jorgensen, M. S.
Hammer, B. [1 ]
机构
[1] Aarhus Univ, Dept Phys & Astron, DK-8000 Aarhus C, Denmark
关键词
LOWEST-ENERGY STRUCTURES; EVOLUTIONARY ALGORITHMS; GEOMETRY OPTIMIZATION; GENETIC ALGORITHMS; GLOBAL MINIMUM; SURFACE; CLUSTERS; SEARCH;
D O I
10.1103/PhysRevLett.120.026102
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Machine learning (ML) is used to derive local stability information for density functional theory calculations of systems in relation to the recently discovered SnO2(110)-(4x1) reconstruction. The ML model is trained on (structure, total energy) relations collected during global minimum energy search runs with an evolutionary algorithm (EA). While being built, the ML model is used to guide the EA, thereby speeding up the overall rate by which the EA succeeds. Inspection of the local atomic potentials emerging from the model further shows chemically intuitive patterns.
引用
收藏
页数:5
相关论文
共 45 条
[1]   Search for the Lin0/+1/-1 (n=5-7) lowest-energy structures using the ab initio Gradient Embedded Genetic Algorithm (GEGA).: Elucidation of the chemical bonding in the lithium clusters [J].
Alexandrova, AN ;
Boldyrev, AI .
JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2005, 1 (04) :566-580
[2]   The SnO2(110)(4 x 1) structure determined by LEED intensity analysis [J].
Atrei, A ;
Zanazzi, E ;
Bardi, U ;
Rovida, G .
SURFACE SCIENCE, 2001, 475 (1-3) :L223-L228
[3]   On representing chemical environments [J].
Bartok, Albert P. ;
Kondor, Risi ;
Csanyi, Gabor .
PHYSICAL REVIEW B, 2013, 87 (18)
[4]   Surface morphologies of SnO2(110) [J].
Batzill, M ;
Katsiev, K ;
Diebold, U .
SURFACE SCIENCE, 2003, 529 (03) :295-311
[5]   Packing Defects into Ordered Structures: Strands on TiO2 [J].
Bechstein, R. ;
Kristoffersen, H. H. ;
Vilhelmsen, L. B. ;
Rieboldt, F. ;
Stausholm-Moller, J. ;
Wendt, S. ;
Hammer, B. ;
Besenbacher, F. .
PHYSICAL REVIEW LETTERS, 2012, 108 (23)
[6]   Generalized neural-network representation of high-dimensional potential-energy surfaces [J].
Behler, Joerg ;
Parrinello, Michele .
PHYSICAL REVIEW LETTERS, 2007, 98 (14)
[7]   Stability and Metastability of Clusters in a Reactive Atmosphere: Theoretical Evidence for Unexpected Stoichiometries of MgMOx [J].
Bhattacharya, Saswata ;
Levchenko, Sergey V. ;
Ghiringhelli, Luca M. ;
Scheffler, Matthias .
PHYSICAL REVIEW LETTERS, 2013, 111 (13)
[8]   Adaptive machine learning framework to accelerate ab initio molecular dynamics [J].
Botu, Venkatesh ;
Ramprasad, Rampi .
INTERNATIONAL JOURNAL OF QUANTUM CHEMISTRY, 2015, 115 (16) :1074-1083
[9]   Global minimum structure searches via particle swarm optimization [J].
Call, Seth T. ;
Zubarev, Dmitry Yu. ;
Boldyrev, Alexander I. .
JOURNAL OF COMPUTATIONAL CHEMISTRY, 2007, 28 (07) :1177-1186
[10]   MOLECULAR-GEOMETRY OPTIMIZATION WITH A GENETIC ALGORITHM [J].
DEAVEN, DM ;
HO, KM .
PHYSICAL REVIEW LETTERS, 1995, 75 (02) :288-291