1
|
Unke O, Chmiela S, Sauceda HE, Gastegger M, Poltavsky I, Schütt KT, Tkatchenko A, Müller KR. Machine Learning Force Fields. Chem Rev 2021; 121:10142-10186. [PMID: 33705118 PMCID: PMC8391964 DOI: 10.1021/acs.chemrev.0c01111] [Citation(s) in RCA: 371] [Impact Index Per Article: 123.7] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2020] [Indexed: 12/27/2022]
Abstract
In recent years, the use of machine learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising applications is the construction of ML-based force fields (FFs), with the aim to narrow the gap between the accuracy of ab initio methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail, and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.
Collapse
Affiliation(s)
- Oliver
T. Unke
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
- DFG
Cluster of Excellence “Unifying Systems in Catalysis”
(UniSysCat), Technische Universität Berlin, 10623 Berlin, Germany
| | - Stefan Chmiela
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
| | - Huziel E. Sauceda
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
- BASLEARN,
BASF-TU Joint Lab, Technische Universität
Berlin, 10587 Berlin, Germany
| | - Michael Gastegger
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
- DFG
Cluster of Excellence “Unifying Systems in Catalysis”
(UniSysCat), Technische Universität Berlin, 10623 Berlin, Germany
- BASLEARN,
BASF-TU Joint Lab, Technische Universität
Berlin, 10587 Berlin, Germany
| | - Igor Poltavsky
- Department
of Physics and Materials Science, University
of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Kristof T. Schütt
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
| | - Alexandre Tkatchenko
- Department
of Physics and Materials Science, University
of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Klaus-Robert Müller
- Machine
Learning Group, Technische Universität
Berlin, 10587 Berlin, Germany
- BIFOLD−Berlin
Institute for the Foundations of Learning and Data, Berlin, Germany
- Department
of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, Korea
- Max Planck
Institute for Informatics, Stuhlsatzenhausweg, 66123 Saarbrücken, Germany
- Google
Research, Brain Team, Berlin, Germany
| |
Collapse
|
2
|
Sauceda HE, Vassilev-Galindo V, Chmiela S, Müller KR, Tkatchenko A. Dynamical strengthening of covalent and non-covalent molecular interactions by nuclear quantum effects at finite temperature. Nat Commun 2021; 12:442. [PMID: 33469007 PMCID: PMC7815839 DOI: 10.1038/s41467-020-20212-1] [Citation(s) in RCA: 24] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2020] [Accepted: 11/12/2020] [Indexed: 11/08/2022] Open
Abstract
Nuclear quantum effects (NQE) tend to generate delocalized molecular dynamics due to the inclusion of the zero point energy and its coupling with the anharmonicities in interatomic interactions. Here, we present evidence that NQE often enhance electronic interactions and, in turn, can result in dynamical molecular stabilization at finite temperature. The underlying physical mechanism promoted by NQE depends on the particular interaction under consideration. First, the effective reduction of interatomic distances between functional groups within a molecule can enhance the n → π* interaction by increasing the overlap between molecular orbitals or by strengthening electrostatic interactions between neighboring charge densities. Second, NQE can localize methyl rotors by temporarily changing molecular bond orders and leading to the emergence of localized transient rotor states. Third, for noncovalent van der Waals interactions the strengthening comes from the increase of the polarizability given the expanded average interatomic distances induced by NQE. The implications of these boosted interactions include counterintuitive hydroxyl-hydroxyl bonding, hindered methyl rotor dynamics, and molecular stiffening which generates smoother free-energy surfaces. Our findings yield new insights into the versatile role of nuclear quantum fluctuations in molecules and materials.
Collapse
Affiliation(s)
- Huziel E Sauceda
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg.
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany.
- BASLEARN, BASF-TU joint Lab, Technische Universität Berlin, 10587, Berlin, Germany.
| | - Valentin Vassilev-Galindo
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg
| | - Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany
| | - Klaus-Robert Müller
- Machine Learning Group, Technische Universität Berlin, 10587, Berlin, Germany.
- Department of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul, 02841, Korea.
- Max Planck Institute for Informatics, Stuhlsatzenhausweg, 66123, Saarbrücken, Germany.
- Google Research, Brain team, Berlin, Germany.
| | - Alexandre Tkatchenko
- Department of Physics and Materials Science, University of Luxembourg, L-1511, Luxembourg City, Luxembourg.
| |
Collapse
|
3
|
Ashcheulov AA, Manyk ON, Manyk TO, Bilynskyi-Slotylo VR, Izotov AD, Fedorchenko IV. Theoretical Models of Chemical Bond in Molten Binary Cadmium and Zinc Antimonides in AIIBV Semiconductors. RUSS J INORG CHEM+ 2020. [DOI: 10.1134/s0036023620090028] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
|
4
|
Viennois R, Esmilaire R, Perrière L, Haidoux A, Alleno E, Beaudhuin M. Crystal Structure, Stability, and Physical Properties of Metastable Electron-Poor Narrow-Gap AlGe Semiconductor. Inorg Chem 2017; 56:11591-11602. [PMID: 28892366 DOI: 10.1021/acs.inorgchem.7b01318] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
We report for the first time the full crystal structure, the electronic structure, the lattice dynamics, and the elastic constants of metastable monoclinic AlGe. In addition to ultrarapid cooling techniques such as melt spinning, we show the possibility of obtaining monoclinic AlGe by water-quenching in a quartz tube. Monoclinic AlGe and rhombohedral Al6Ge5 are competing phases with similar stability since they both begin to decompose above 230 °C. The crystal structure and electronic bonding of monoclinic AlGe are similar to those of ZnSb and comply with its 3.5 valence electrons per atom: besides classical two electron-two center Al-Ge and Ge-Ge covalent bonds, Al2Ge2 parallelogram rings are formed by uncommon multicenter bonds. Monoclinic AlGe could be used in various applications since it is found theoretically to be an electron-poor semiconductor with a narrow indirect energy bandgap of about 0.5 eV. The lattice dynamics calculations show the presence of low energy optical phonons, which should lead to a low thermal conductivity.
Collapse
Affiliation(s)
- Romain Viennois
- Institut Charles Gerhardt Montpellier, UMR 5253, CNRS-UM-ENSCM, Université de Montpellier , cc 1504, Place Eugéne Bataillon, F-34095 Montpellier Cedex 5, France
| | - Roseline Esmilaire
- Institut Charles Gerhardt Montpellier, UMR 5253, CNRS-UM-ENSCM, Université de Montpellier , cc 1504, Place Eugéne Bataillon, F-34095 Montpellier Cedex 5, France.,Institut Européen des Membranes, UMR5635 Université Montpellier, CNRS, ENSCM , Montpellier, France
| | - Loïc Perrière
- Université Paris Est, Institut de Chimie et des Matériaux Paris-Est, UMR 7182 CNRS-UPEC , 2-8 rue H. Dunant, 94320 Thiais, France
| | - Abel Haidoux
- Institut Charles Gerhardt Montpellier, UMR 5253, CNRS-UM-ENSCM, Université de Montpellier , cc 1504, Place Eugéne Bataillon, F-34095 Montpellier Cedex 5, France
| | - Eric Alleno
- Université Paris Est, Institut de Chimie et des Matériaux Paris-Est, UMR 7182 CNRS-UPEC , 2-8 rue H. Dunant, 94320 Thiais, France
| | - Mickael Beaudhuin
- Institut Charles Gerhardt Montpellier, UMR 5253, CNRS-UM-ENSCM, Université de Montpellier , cc 1504, Place Eugéne Bataillon, F-34095 Montpellier Cedex 5, France
| |
Collapse
|