期刊
ENERGY & ENVIRONMENTAL MATERIALS
卷 6, 期 1, 页码 -出版社
WILEY
DOI: 10.1002/eem2.12304
关键词
catalytic descriptor; electrocatalytic nitrogen reduction; first-principles calculations; machine learning
This study combines machine learning techniques and first-principle calculations to rapidly discover novel graphene-supported single-atom catalysts for nitrogen reduction reaction. By optimizing feature sets and constructing new catalytic descriptors, accurate predictions of high-performance single-atom catalysts can be made. This research is of great significance for the development of catalysts for nitrogen reduction reaction and rapid screening of new electrocatalysts.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据