1
|
Martí C, Devereux C, Najm HN, Zádor J. Evaluation of Rate Coefficients in the Gas Phase Using Machine-Learned Potentials. J Phys Chem A 2024. [PMID: 38427974 DOI: 10.1021/acs.jpca.3c07872] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/03/2024]
Abstract
We assess the capability of machine-learned potentials to compute rate coefficients by training a neural network (NN) model and applying it to describe the chemical landscape on the C5H5 potential energy surface, which is relevant to molecular weight growth in combustion and interstellar media. We coupled the resulting NN with an automated kinetics workflow code, KinBot, to perform all necessary calculations to compute the rate coefficients. The NN is benchmarked exhaustively by evaluating its performance at the various stages of the kinetics calculations: from the electronic energy through the computation of zero point energy, barrier heights, entropic contributions, the portion of the PES explored, and finally the overall rate coefficients as formulated by transition state theory.
Collapse
Affiliation(s)
- Carles Martí
- Combustion Research Facility, Sandia National Laboratories, Livermore, California 94551, United States
| | - Christian Devereux
- Combustion Research Facility, Sandia National Laboratories, Livermore, California 94551, United States
| | - Habib N Najm
- Combustion Research Facility, Sandia National Laboratories, Livermore, California 94551, United States
| | - Judit Zádor
- Combustion Research Facility, Sandia National Laboratories, Livermore, California 94551, United States
| |
Collapse
|
2
|
Allen AEA, Dusson G, Ortner C, Csányi G. Atomic permutationally invariant polynomials for fitting molecular force fields. MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2021. [DOI: 10.1088/2632-2153/abd51e] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
|
3
|
Ho TH, Dong HC, Bui VQ, Kawazoe Y, Le HM. Reaction probability and kinetics of water splitting on the penta-NiAs 2 monolayer from an ab initio molecular dynamics investigation. Phys Chem Chem Phys 2020; 22:18149-18154. [PMID: 32766624 DOI: 10.1039/d0cp02418j] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
The reaction probability and kinetics of the water splitting process on the penta-NiAs2 monolayer are studied using ab initio molecular dynamics simulations. A total of 100 trajectories are investigated, in which a H2O molecule is set to strike the surface with a translational energy of 1 eV or 2 eV. The results show that the NiAs2 monolayer is an excellent candidate for the activation of water splitting with a reaction probability of 94% for both energy levels. Interestingly, the kinetics of two O-H dissociation stages varies greatly with respect to the inletting translational energy. Interpreting the reaction data for the 1 eV case, we conclude that O-H1 and O-H2 dissociations are first-order processes. However, such dissociation steps become pseudo-zeroth order in the 2 eV case. At the time of the dissociation, the force acting on atoms and the principal component analysis suggest that the two OH breaking stages behave like harmonic springs until reaching the dissociation.
Collapse
Affiliation(s)
- Thi H Ho
- Division of Computational Physics, Institute for Computational Science, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam. and Faculty of Applied Sciences, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam
| | - Hieu C Dong
- Future Materials and Devices Laboratory, Institute of Fundamental and Applied Sciences, Duy Tan University, Ho Chi Minh City 700000, Vietnam and The Faculty of Natural Sciences, Duy Tan University, Da Nang 550000, Vietnam
| | - Viet Q Bui
- Department of Chemistry, Sungkyunkwan University (SKKU), Suwon, 16419, Republic of Korea
| | - Yoshiyuki Kawazoe
- New Industry Creation Hatchery Center, Tohoku University, Sendai, 980-8579, Japan and Department of Physics and Nanotechnology, SRM Institute of Science and Technology, Kattankulathur 603203, Tamil Nadu, India and School of Physics, Institute of Science, Suranaree University of Technology, 111 University Avenue, Nakhon Ratchasima 30000, Thailand
| | - Hung M Le
- Institute of Research and Development, Duy Tan University, Danang 550000, Vietnam
| |
Collapse
|
4
|
Herr JE, Yao K, McIntyre R, Toth DW, Parkhill J. Metadynamics for training neural network model chemistries: A competitive assessment. J Chem Phys 2018; 148:241710. [PMID: 29960377 DOI: 10.1063/1.5020067] [Citation(s) in RCA: 39] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/31/2022] Open
Abstract
Neural network model chemistries (NNMCs) promise to facilitate the accurate exploration of chemical space and simulation of large reactive systems. One important path to improving these models is to add layers of physical detail, especially long-range forces. At short range, however, these models are data driven and data limited. Little is systematically known about how data should be sampled, and "test data" chosen randomly from some sampling techniques can provide poor information about generality. If the sampling method is narrow, "test error" can appear encouragingly tiny while the model fails catastrophically elsewhere. In this manuscript, we competitively evaluate two common sampling methods: molecular dynamics (MD), normal-mode sampling, and one uncommon alternative, Metadynamics (MetaMD), for preparing training geometries. We show that MD is an inefficient sampling method in the sense that additional samples do not improve generality. We also show that MetaMD is easily implemented in any NNMC software package with cost that scales linearly with the number of atoms in a sample molecule. MetaMD is a black-box way to ensure samples always reach out to new regions of chemical space, while remaining relevant to chemistry near kbT. It is a cheap tool to address the issue of generalization.
Collapse
Affiliation(s)
- John E Herr
- Department of Chemistry and Biochemistry, The University of Notre Dame du Lac, 251 Nieuwland Science Hall, Notre Dame, Indiana 46556, USA
| | - Kun Yao
- Department of Chemistry and Biochemistry, The University of Notre Dame du Lac, 251 Nieuwland Science Hall, Notre Dame, Indiana 46556, USA
| | - Ryker McIntyre
- Department of Chemistry and Biochemistry, The University of Notre Dame du Lac, 251 Nieuwland Science Hall, Notre Dame, Indiana 46556, USA
| | - David W Toth
- Department of Chemistry and Biochemistry, The University of Notre Dame du Lac, 251 Nieuwland Science Hall, Notre Dame, Indiana 46556, USA
| | - John Parkhill
- Department of Chemistry and Biochemistry, The University of Notre Dame du Lac, 251 Nieuwland Science Hall, Notre Dame, Indiana 46556, USA
| |
Collapse
|
5
|
Smith JS, Nebgen B, Lubbers N, Isayev O, Roitberg AE. Less is more: Sampling chemical space with active learning. J Chem Phys 2018; 148:241733. [DOI: 10.1063/1.5023802] [Citation(s) in RCA: 278] [Impact Index Per Article: 46.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022] Open
Affiliation(s)
- Justin S. Smith
- Department of Chemistry, University of Florida, Gainesville, Florida 32611, USA
| | - Ben Nebgen
- Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
| | - Nicholas Lubbers
- Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
| | - Olexandr Isayev
- UNC Eshelman School of Pharmacy, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599, USA
| | - Adrian E. Roitberg
- Department of Chemistry, University of Florida, Gainesville, Florida 32611, USA
| |
Collapse
|
6
|
Jiang T, Simko S, Bulo RE. Accurate Quantum Mechanics/Molecular Mechanics Simulation of Aqueous Solutions with Tailored Molecular Mechanics Models. J Chem Theory Comput 2018; 14:3943-3954. [DOI: 10.1021/acs.jctc.7b01218] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Tao Jiang
- Laboratoire de chimie, École Normale Supérieure de lyon, 46 allée d’italie, 69007 Lyon, France
| | - Stanislav Simko
- Inorganic Chemistry and Catalysis Group, Debye Institute for Nanomaterials Science, Utrecht University, Universiteitsweg 99, 3584 CG, Utrecht, The Netherlands
| | - Rosa E. Bulo
- Inorganic Chemistry and Catalysis Group, Debye Institute for Nanomaterials Science, Utrecht University, Universiteitsweg 99, 3584 CG, Utrecht, The Netherlands
| |
Collapse
|
7
|
Smith JS, Isayev O, Roitberg AE. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chem Sci 2017; 8:3192-3203. [PMID: 28507695 PMCID: PMC5414547 DOI: 10.1039/c6sc05720a] [Citation(s) in RCA: 818] [Impact Index Per Article: 116.9] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2016] [Accepted: 02/07/2017] [Indexed: 01/14/2023] Open
Abstract
Deep learning is revolutionizing many areas of science and technology, especially image, text, and speech recognition. In this paper, we demonstrate how a deep neural network (NN) trained on quantum mechanical (QM) DFT calculations can learn an accurate and transferable potential for organic molecules. We introduce ANAKIN-ME (Accurate NeurAl networK engINe for Molecular Energies) or ANI for short. ANI is a new method designed with the intent of developing transferable neural network potentials that utilize a highly-modified version of the Behler and Parrinello symmetry functions to build single-atom atomic environment vectors (AEV) as a molecular representation. AEVs provide the ability to train neural networks to data that spans both configurational and conformational space, a feat not previously accomplished on this scale. We utilized ANI to build a potential called ANI-1, which was trained on a subset of the GDB databases with up to 8 heavy atoms in order to predict total energies for organic molecules containing four atom types: H, C, N, and O. To obtain an accelerated but physically relevant sampling of molecular potential surfaces, we also proposed a Normal Mode Sampling (NMS) method for generating molecular conformations. Through a series of case studies, we show that ANI-1 is chemically accurate compared to reference DFT calculations on much larger molecular systems (up to 54 atoms) than those included in the training data set.
Collapse
Affiliation(s)
- J S Smith
- University of Florida , Department of Chemistry , PO Box 117200 , Gainesville , FL , USA 32611-7200 .
| | - O Isayev
- University of North Carolina at Chapel Hill , Division of Chemical Biology and Medicinal Chemistry , UNC Eshelman School of Pharmacy , Chapel Hill , NC , USA 27599 .
| | - A E Roitberg
- University of Florida , Department of Chemistry , PO Box 117200 , Gainesville , FL , USA 32611-7200 .
| |
Collapse
|