文献类型：期刊文献

英文题名：Perspective on computational reaction prediction using machine learning methods in heterogeneous catalysis

作者：Xu, Jiayan[1,2,3,4];Cao, Xiao-Ming[1,2,3];Hu, P.[1,2,3,4]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Mat, Sch Chem & Mol Engn, 130 Meilong Rd, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Joint Int Res Lab Precis Chem & Mol Engn, Sch Chem & Mol Engn,Ctr Computat Chem, Feringa Nobel Prize Scientist Joint Res Ctr,Front, 130 Meilong Rd, Shanghai 200237, Peoples R China;[3]East China Univ Sci & Technol, Res Inst Ind Catalysis, Sch Chem & Mol Engn, 130 Meilong Rd, Shanghai 200237, Peoples R China;[4]Queens Univ Belfast, Sch Chem & Chem Engn, Belfast BT9 5AG, Antrim, North Ireland

年份：2021

卷号：23

期号：19

起止页码：11155

外文期刊名：PHYSICAL CHEMISTRY CHEMICAL PHYSICS

收录：;EI(收录号：20212210437726);WOS:【SCI-EXPANDED(收录号:WOS:000648898600001)】；

基金：This work was financially supported by National Key Research and Development Program of China (2018YFA0208600), National Natural Science Foundation of China (22022302, 91845111, 92045303), Shanghai Municipal Science and Technology Major Project (Grant No. 2018SHZDZX03), the Program of Introducing Talents of Discipline to Universities (B16017) and the Fundamental Research Funds for the Central Universities. Jiayan Xu acknowledges the financial support from Queen's University Belfast and China Scholarship Council.

语种：英文

外文关键词：Calculations - Thermodynamics - Reaction intermediates - Chemical industry - Catalysts - Forecasting - Regression analysis - Learning algorithms - Surface reactions

摘要：Heterogeneous catalysis plays a significant role in the modern chemical industry. Towards the rational design of novel catalysts, understanding reactions over surfaces is the most essential aspect. Typical industrial catalytic processes such as syngas conversion and methane utilisation can generate a large reaction network comprising thousands of intermediates and reaction pairs. This complexity not only arises from the permutation of transformations between species but also from the extra reaction channels offered by distinct surface sites. Despite the success in investigating surface reactions at the atomic scale, the huge computational expense of ab initio methods hinders the exploration of such complicated reaction networks. With the proliferation of catalysis studies, machine learning as an emerging tool can take advantage of the accumulated reaction data to emulate the output of ab initio methods towards swift reaction prediction. Here, we briefly summarise the conventional workflow of reaction prediction, including reaction network generation, ab initio thermodynamics and microkinetic modelling. An overview of the frequently used regression models in machine learning is presented. As a promising alternative to full ab initio calculations, machine learning interatomic potentials are highlighted. Furthermore, we survey applications assisted by these methods for accelerating reaction prediction, exploring reaction networks, and computational catalyst design. Finally, we envisage future directions in computationally investigating reactions and implementing machine learning algorithms in heterogeneous catalysis.