文献类型：期刊文献

英文题名：Identifying the composition and atomic distribution of Pt-Au bimetallic nanoparticle with machine learning and genetic algorithm

作者：Zhang, Jiawei[1,2];Chen, Jianfu[1,2];Hu, Peijun[1,2,3];Wang, Haifeng[1,2]

机构：[1]East China Univ Sci & Technol, Sch Chem & Mol Engn, Res Inst Ind Catalysis, Key Lab Adv Mat, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Sch Chem & Mol Engn, Ctr Computat Chem, Shanghai 200237, Peoples R China;[3]Queens Univ Belfast, Sch Chem & Chem Engn, Belfast BT9 5AG, Antrim, North Ireland

年份：2020

卷号：31

期号：3

起止页码：890

外文期刊名：CHINESE CHEMICAL LETTERS

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000527915100059)】；

基金：This project was supported by National Key R&D Program of China (No. 2018YFA0208602), NSFC (Nos. 21622305, 21873028, 21703067), National Ten Thousand Talent Program for Young Topnotch Talents in China, Shanghai ShuGuang project (No. 17SG30).

语种：英文

外文关键词：Density functional theory calculation; Machine learning; Genetic algorithm; Bimetallic nanoparticle; PtAu cluster

摘要：Bimetallic nanoparticles (A(m)B(n)) usually exhibit rich catalytic chemistry and have drawn tremendous attention in heterogeneous catalysis. However, challenged by the huge configuration space, the understanding toward their composition and distribution of A/B element is known little at the atomic level, which hinders the rational synthesis. Herein, we develop an on-the-fly training strategy combing the machine learning model (SchNet) with the genetic algorithm (GA) search technique, which achieve the fast and accurate energy prediction of complex bimetallic clusters at the DFT level. Taking the 38-atom PtmAu38-m nanoparticle as example, the element distribution identification problem and the stability trend as a function of Pt/Au composition is quantitatively resolved. Specifically, results show that on the Pt-rich cluster Au atoms prefer to occupy the low-coordinated surface corner sites and form patch-like surface segregation patterns, while for the Au-rich ones Pt atoms tend to site in the core region and form the core-shell (Pt@Au) configuration. The thermodynamically most stable PtmAu38-m cluster is Pt6Au32, with all the core-region sites occupied by Pt, rationalized by the stronger Pt-Pt bond in comparison with Pt-Au and Au-Au bonds. This work exemplifies the potent application of rapid global search enabled by machine learning in exploring the high-dimensional configuration space of bimetallic nanocatalysts. (C) 2019 Chinese Chemical Society and Institute of Materia Medica, Chinese Academy of Medical Sciences. Published by Elsevier B.V. All rights reserved.