Efficient Selection of Linearly Independent Atomic Features for Accurate Machine Learning Potentials  

高效选取线性独立的原子特征构建精确机器学习势函数

作　　者：Jun-fan Xia Yao-long Zhang Bin Jiang 夏俊凡;张耀龙;蒋彬(中国科学技术大学化学物理系,合肥微尺度物质科学国家研究中心,安徽省教育厅表界面化学与能源催化重点实验室,合肥230026)

机构地区：[1]Hefei National Laboratory for Physical Science at the Microscale,Department of Chemical Physics,Key Laboratory of Surface and Interface Chemistry and Energy Catalysis of Anhui Higher Education Institutes,University of Science and Technology of China,Hefei 230026,China

出　　处：《Chinese Journal of Chemical Physics》2021年第6期695-703,I0001,共10页化学物理学报（英文）

基　　金：supported by CAS Project for Young Scientists in Basic Research(YSBR-005);the National Natural Science Foundation of China(No.22073089 and No.22033007);Anhui Initiative in Quantum Information Technologies(AHY090200);the Fundamental Research Funds for Central Universities(WK2060000017)。

摘　　要：Machine learning potentials are promising in atomistic simulations due to their comparable accuracy to first-principles theory but much lower computational cost.However,the reliability,speed,and transferability of atomistic machine learning potentials depend strongly on the way atomic configurations are represented.A wise choice of descriptors used as input for the machine learning program is the key for a successful machine learning representation.Here we develop a simple and efficient strategy to automatically select an optimal set of linearly-independent atomic features out of a large pool of candidates,based on the correlations that are intrinsic to the training data.Through applications to the construction of embedded atom neural network potentials for several benchmark molecules with less redundant linearly-independent embedded density descriptors,we demonstrate the efficiency and accuracy of this new strategy.The proposed algorithm can greatly simplify the initial selection of atomic features and vastly improve the performance of the atomistic machine learning potentials.

关 键 词：Linearly independent Feature selection Atomic descriptor Machine learning Embedded atom neural network 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] O562[自动化与计算机技术—控制科学与工程]