Benchmarking of machine learning interatomic potentials for reactive hydrogen dynamics at metal surfaces

被引:0
|
作者
Stark, Wojciech G. [1 ]
van der Oord, Cas [2 ]
Batatia, Ilyes [2 ]
Zhang, Yaolong [3 ]
Jiang, Bin [4 ,5 ]
Csanyi, Gabor [2 ]
Maurer, Reinhard J. [1 ,6 ]
机构
[1] Univ Warwick, Dept Chem, Gibbet Hill Rd, Coventry CV4 7AL, England
[2] Dept Engn, Inst Mfg, Dept Engn, Cambridge CB2 1PZ, England
[3] Univ New Mexico, Ctr Computat Chem, Dept Chem & Chem Biol, Albuquerque, NM 87131 USA
[4] Univ Sci & Technol China, Dept Chem Phys, Key Lab Precis & Intelligent Chem, Hefei, Anhui, Peoples R China
[5] Univ Sci & Technol China, Hefei Natl Lab, Hefei 230088, Peoples R China
[6] Univ Warwick, Dept Phys, Gibbet Hill Rd, Coventry CV4 7AL, England
来源
基金
英国工程与自然科学研究理事会;
关键词
molecular dynamics simulations; electronic structure theory; gas surface dynamics; machine learning model inference performance; reactive scattering; hydrogen surface chemistry; MODIFIED SHEPARD INTERPOLATION; ENERGY SURFACES; DISSOCIATIVE CHEMISORPTION; H-2; ADSORPTION; MOLECULE; CU(111); TEMPERATURE; SCATTERING;
D O I
10.1088/2632-2153/ad5f11
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Simulations of chemical reaction probabilities in gas surface dynamics require the calculation of ensemble averages over many tens of thousands of reaction events to predict dynamical observables that can be compared to experiments. At the same time, the energy landscapes need to be accurately mapped, as small errors in barriers can lead to large deviations in reaction probabilities. This brings a particularly interesting challenge for machine learning interatomic potentials, which are becoming well-established tools to accelerate molecular dynamics simulations. We compare state-of-the-art machine learning interatomic potentials with a particular focus on their inference performance on CPUs and suitability for high throughput simulation of reactive chemistry at surfaces. The considered models include polarizable atom interaction neural networks (PaiNN), recursively embedded atom neural networks (REANN), the MACE equivariant graph neural network, and atomic cluster expansion potentials (ACE). The models are applied to a dataset on reactive molecular hydrogen scattering on low-index surface facets of copper. All models are assessed for their accuracy, time-to-solution, and ability to simulate reactive sticking probabilities as a function of the rovibrational initial state and kinetic incidence energy of the molecule. REANN and MACE models provide the best balance between accuracy and time-to-solution and can be considered the current state-of-the-art in gas-surface dynamics. PaiNN models require many features for the best accuracy, which causes significant losses in computational efficiency. ACE models provide the fastest time-to-solution, however, models trained on the existing dataset were not able to achieve sufficiently accurate predictions in all cases.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] Machine Learning Classical Interatomic Potentials for Molecular Dynamics from First-Principles Training Data
    Chan, Henry
    Narayanan, Badri
    Cherukara, Mathew J.
    Sen, Fatih G.
    Sasikumar, Kiran
    Gray, Stephen K.
    Chan, Maria K. Y.
    Sankaranarayanan, Subramanian K. R. S.
    [J]. JOURNAL OF PHYSICAL CHEMISTRY C, 2019, 123 (12): : 6941 - 6957
  • [32] Uncertainty-driven dynamics for active learning of interatomic potentials
    Maksim Kulichenko
    Kipton Barros
    Nicholas Lubbers
    Ying Wai Li
    Richard Messerly
    Sergei Tretiak
    Justin S. Smith
    Benjamin Nebgen
    [J]. Nature Computational Science, 2023, 3 : 230 - 239
  • [33] Uncertainty-driven dynamics for active learning of interatomic potentials
    Kulichenko, Maksim
    Barros, Kipton
    Lubbers, Nicholas
    Li, Ying Wai
    Messerly, Richard
    Tretiak, Sergei
    Smith, Justin S.
    Nebgen, Benjamin
    [J]. NATURE COMPUTATIONAL SCIENCE, 2023, 3 (03): : 230 - +
  • [34] Performance Comparisons of NequIP and DPMD Machine Learning Interatomic Potentials for Tobermorites
    Zhu, Keming
    [J]. COMPUTATIONAL MATERIALS SCIENCE, 2024, 244
  • [35] Cross-platform hyperparameter optimization for machine learning interatomic potentials
    du Toit, Daniel Thomas F.
    Deringer, Volker L.
    [J]. JOURNAL OF CHEMICAL PHYSICS, 2023, 159 (02):
  • [36] Extending machine learning beyond interatomic potentials for predicting molecular properties
    Nikita Fedik
    Roman Zubatyuk
    Maksim Kulichenko
    Nicholas Lubbers
    Justin S. Smith
    Benjamin Nebgen
    Richard Messerly
    Ying Wai Li
    Alexander I. Boldyrev
    Kipton Barros
    Olexandr Isayev
    Sergei Tretiak
    [J]. Nature Reviews Chemistry, 2022, 6 : 653 - 672
  • [37] Extending machine learning beyond interatomic potentials for predicting molecular properties
    Fedik, Nikita
    Zubatyuk, Roman
    Kulichenko, Maksim
    Lubbers, Nicholas
    Smith, Justin S.
    Nebgen, Benjamin
    Messerly, Richard
    Li, Ying Wai
    Boldyrev, Alexander, I
    Barros, Kipton
    Isayev, Olexandr
    Tretiak, Sergei
    [J]. NATURE REVIEWS CHEMISTRY, 2022, 6 (09) : 653 - 672
  • [38] Accessing thermal conductivity of complex compounds by machine learning interatomic potentials
    Korotaev, Pavel
    Novoselov, Ivan
    Yanilkin, Aleksey
    Shapeev, Alexander
    [J]. PHYSICAL REVIEW B, 2019, 100 (14)
  • [39] Multiscale machine-learning interatomic potentials for ferromagnetic and liquid iron
    Byggmastar, J.
    Nikoulis, G.
    Fellman, A.
    Granberg, F.
    Djurabekova, F.
    Nordlund, K.
    [J]. JOURNAL OF PHYSICS-CONDENSED MATTER, 2022, 34 (30)
  • [40] Machine learning interatomic potentials in engineering perspective for developing cathode materials
    Kwon, Dohyeong
    Kim, Duho
    [J]. JOURNAL OF MATERIALS CHEMISTRY A, 2024, 12 (35) : 23837 - 23847