From Single Metals to High‐Entropy Alloys: How Machine Learning Accelerates the Development of Metal Electrocatalysts

作者：Xinyu Fan, Letian Chen, Dulin Huang, Yun Tian, Xu Zhang, Menggai Jiao, Zhen Zhou · 发表于：Advanced Functional Materials · 年份：2024 · DOI：10.1002/adfm.202401887 · 被引用次数：65 · 研究领域：Machine Learning in Materials Science、Electrocatalysts for Energy Conversion、Fuel Cells and Related Materials

Abstract The rapid advancement of high‐performance computing and artificial intelligence technology has opened up novel avenues for the development of various metal electrocatalysts. In particular, dilute and high‐entropy alloys have garnered significant attention owing to their unique electronic and spatial structures, as well as their exceptional electrocatalytic performance. Commencing with the exploration of single‐atom alloy catalysts, the latest advancements in machine learning (ML) techniques are presented for the efficient screening of a broad spectrum of metal spaces. Subsequently, the review delves into the prevailing trend in alloy research, focusing specifically on rare‐metal alloy electrocatalysts, and offers an overview of the progress and outcomes achieved through the application of ML in these domains. Finally, high‐entropy alloys are highlighted as a promising category of electrocatalysts and underscore the importance and potential applications of ML in addressing complex and challenging research issues are underscored.