Open AccessAccelerated Discovery of Single‐Atom Catalysts for Nitrogen Fixation via Machine Learning
Author(s) -
Zhang Sheng,
Lu Shuaihua,
Zhang Peng,
Tian Jianxiong,
Shi Li,
Ling Chongyi,
Zhou Qionghua,
Wang Jinlan
Publication year - 2023
Publication title -
energy and environmental materials
Language(s) - English
Resource type - Journals
ISSN - 2575-0356
DOI - 10.1002/eem2.12304
Subject(s) - catalysis , generalizability theory , nitrogen atom , atom (system on chip) , computer science , graphene , nitrogen , feature (linguistics) , reduction (mathematics) , artificial intelligence , materials science , combinatorial chemistry , biological system , chemistry , biochemical engineering , machine learning , nanotechnology , mathematics , organic chemistry , engineering , statistics , parallel computing , biology , linguistics , philosophy , geometry , group (periodic table)
Developing high‐performance catalysts using traditional trial‐and‐error methods is generally time consuming and inefficient. Here, by combining machine learning techniques and first‐principle calculations, we are able to discover novel graphene‐supported single‐atom catalysts for nitrogen reduction reaction in a rapid way. Successfully, 45 promising catalysts with highly efficient catalytic performance are screened out from 1626 candidates. Furthermore, based on the optimal feature sets, new catalytic descriptors are constructed via symbolic regression, which can be directly used to predict single‐atom catalysts with good accuracy and good generalizability. This study not only provides dozens of promising catalysts and new descriptors for nitrogen reduction reaction but also offers a potential way for rapid screening of new electrocatalysts.