Improving stability and transferability of machine learned interatomic potentials using physically informed bounding potentials

被引:1
作者
Zhou, H. [1 ]
Dickel, D. [1 ]
Barrett, C. D. [1 ]
机构
[1] Mississippi State Univ, Dept Mech Engn, Starkville, MS 39759 USA
关键词
Machine learning; Zinc; Interatomic potentials;
D O I
10.1557/s43578-023-01174-8
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
While machine-learning techniques have shown great progress in advancing the frontier of accuracy and scope in interatomic potentials, they still suffer from a number of drawbacks. Principle among these is an inability to extrapolate outside of the training data which can result in poor transferability or stability issues limiting their usefulness outside of specific scenarios. This is in contrast to traditional potential formalisms such as the Embedded Atom Method (EAM), which have shown excellent transferability thanks to the physical intuition which motivated their creation. We introduce here a modification to the machine-learned Rapid Artificial Neural Network (RANN) formalism which uses an EAM potential to bound the prediction of the energies. This constrains the predicted energies outside the training space, resulting in more stable and transferable potentials. Using zinc as an example, we demonstrate the improved stability and show that this bounding potential improves the quality of the potential within the training data.
引用
收藏
页码:5106 / 5113
页数:8
相关论文
共 50 条
[41]   Prediction of the melting curve and phase diagram for CaO using newly developed interatomic potentials [J].
Wang, Xin-Wei ;
Sun, Xiao-Wei ;
Song, Ting ;
Tian, Jun -Hong ;
Liu, Zi-Jiang .
VACUUM, 2023, 209
[42]   Local Structures of Ex-Solved Nanoparticles Identified by Machine-Learned Potentials [J].
Kang, Sungwoo ;
Kim, Jun Kyu ;
Kim, Hyunah ;
Son, You-Hwan ;
Chang, Jaehee ;
Kim, Jinwoo ;
Kim, Dong-Wook ;
Lee, Jong-Min ;
Kwon, Hyuk Jae .
NANO LETTERS, 2024, 24 (14) :4224-4232
[43]   Transferability of interatomic potentials with insights into the structure-property relationship of SiO2-CaO-MgO-Al2O3 melts [J].
Li, Kejiang ;
Li, Hongtao ;
Jiang, Chunhe ;
Zhang, Jianliang ;
Liu, Zhengjian ;
Ren, Shan .
MOLECULAR SIMULATION, 2020, 46 (04) :289-299
[44]   Developing Machine-Learned Potentials for Coarse-Grained Molecular Simulations: Challenges and Pitfalls [J].
Ricci, Eleonora ;
Giannakopoulos, George ;
Karkaletsis, Vangelis ;
Theodorou, Doros N. ;
Vergadou, Niki .
PROCEEDINGS OF THE 12TH HELLENIC CONFERENCE ON ARTIFICIAL INTELLIGENCE, SETN 2022, 2022,
[45]   Predicting Glycerol Electrochemical Oxidation Potentials Using Machine Learning [J].
Soares, Joao M. L. ;
von Zuben, Theodora W. ;
Salles Jr, Airton G. ;
Barbon Junior, Sylvio ;
Bonacin, Juliano A. .
JOURNAL OF THE BRAZILIAN CHEMICAL SOCIETY, 2025, 36 (08)
[46]   Molecular dynamics simulation using pair and many body interatomic potentials: ultrashort laser ablation of Fe [J].
Imamova, SE ;
Atanasov, PA ;
Nedialkov, NN ;
Dausinger, F ;
Berger, P .
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION B-BEAM INTERACTIONS WITH MATERIALS AND ATOMS, 2005, 227 (04) :490-498
[47]   Using diverse potentials and scoring functions for the development of improved machine-learned models for protein–ligand affinity and docking pose prediction [J].
Omar N. A. Demerdash .
Journal of Computer-Aided Molecular Design, 2021, 35 :1095-1123
[48]   Ultrahigh strength and negative thermal expansion and low thermal conductivity in graphyne nanosheets confirmed by machine-learning interatomic potentials [J].
Mortazavi, Bohayra ;
Zhuang, Xiaoying .
FLATCHEM, 2022, 36
[49]   First-Principles Multiscale Modeling of Mechanical Properties in Graphene/Borophene Heterostructures Empowered by Machine-Learning Interatomic Potentials [J].
Mortazavi, Bohayra ;
Silani, Mohammad ;
Podryabinkin, Evgeny, V ;
Rabczuk, Timon ;
Zhuang, Xiaoying ;
Shapeev, Alexander, V .
ADVANCED MATERIALS, 2021, 33 (35)
[50]   Study on Variation of Interatomic Potentials of Ni-Al-Fe Alloy Using Microscopic Phase-Field [J].
Dong Weiping ;
Chen Zheng ;
Wang Yongxin ;
Zhang Jing ;
Lu Yanli ;
Yang Kun .
RARE METAL MATERIALS AND ENGINEERING, 2011, 40 (06) :1055-1059