High-dimensional neural network potentials for magnetic systems using spin-dependent atom-centered symmetry functions

被引:60
作者
Eckhoff, Marco [1 ]
Behler, Joerg [1 ,2 ]
机构
[1] Univ Gottingen, Theoret Chem, Inst Phys Chem, Tammannstr 6, D-37077 Gottingen, Germany
[2] Univ Gottingen, Int Ctr Adv Studies Energy Convers ICASEC, Tammannstr 6, D-37077 Gottingen, Germany
关键词
ENERGY SURFACES; DYNAMICS; MNO; TRANSITION; SUSCEPTIBILITY; COMPLEXES; CHEMISTRY; EXCHANGE; WAVES;
D O I
10.1038/s41524-021-00636-z
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Machine learning potentials have emerged as a powerful tool to extend the time and length scales of first-principles quality simulations. Still, most machine learning potentials cannot distinguish different electronic spin arrangements and thus are not applicable to materials in different magnetic states. Here we propose spin-dependent atom-centered symmetry functions as a type of descriptor taking the atomic spin degrees of freedom into account. When used as an input for a high-dimensional neural network potential (HDNNP), accurate potential energy surfaces of multicomponent systems can be constructed, describing multiple collinear magnetic states. We demonstrate the performance of these magnetic HDNNPs for the case of manganese oxide, MnO. The method predicts the magnetically distorted rhombohedral structure in excellent agreement with density functional theory and experiment. Its efficiency allows to determine the Neel temperature considering structural fluctuations, entropic effects, and defects. The method is general and is expected to be useful also for other types of systems such as oligonuclear transition metal complexes.
引用
收藏
页数:11
相关论文
共 94 条
[1]   Toward reliable density functional methods without adjustable parameters: The PBE0 model [J].
Adamo, C ;
Barone, V .
JOURNAL OF CHEMICAL PHYSICS, 1999, 110 (13) :6158-6170
[2]   High-dimensional neural network potentials for metal surfaces: A prototype study for copper [J].
Artrith, Nongnuch ;
Behler, Joerg .
PHYSICAL REVIEW B, 2012, 85 (04)
[3]   High-dimensional neural-network potentials for multicomponent systems: Applications to zinc oxide [J].
Artrith, Nongnuch ;
Morawietz, Tobias ;
Behler, Joerg .
PHYSICAL REVIEW B, 2011, 83 (15)
[4]  
Ashcroft N. W., 1976, Solid state physics
[5]   Support vector machine regression (LS-SVM)-an alternative to artificial neural networks (ANNs) for the analysis of quantum chemistry data? [J].
Balabin, Roman M. ;
Lomakina, Ekaterina I. .
PHYSICAL CHEMISTRY CHEMICAL PHYSICS, 2011, 13 (24) :11710-11718
[6]   Machine learning unifies the modeling of materials and molecules [J].
Bartok, Albert P. ;
De, Sandip ;
Poelking, Carl ;
Bernstein, Noam ;
Kermode, James R. ;
Csanyi, Gabor ;
Ceriotti, Michele .
SCIENCE ADVANCES, 2017, 3 (12)
[7]   On representing chemical environments [J].
Bartok, Albert P. ;
Kondor, Risi ;
Csanyi, Gabor .
PHYSICAL REVIEW B, 2013, 87 (18)
[8]   Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons [J].
Bartok, Albert P. ;
Payne, Mike C. ;
Kondor, Risi ;
Csanyi, Gabor .
PHYSICAL REVIEW LETTERS, 2010, 104 (13)
[9]   Representing potential energy surfaces by high-dimensional neural network potentials [J].
Behler, J. .
JOURNAL OF PHYSICS-CONDENSED MATTER, 2014, 26 (18)
[10]  
Behler J, 2019, RUNNER