High-entropy alloy catalysts: high-throughput and machine learning-driven design

Abstract

High-entropy alloy (HEA) catalysts have recently attracted worldwide research interest due to their promising catalytic performance. Most current studies focus on designing HEA catalysts through trial-and-error methods. This produces scattered data and is not conducive to obtaining a fundamental understanding of the structure-property-performance relationships for HEA catalysts, thereby hindering their rational design. High-throughput (HT) techniques and machine learning (ML) methods show significant potential in generating, processing and analyzing databases with a vast amount of data, providing a new strategy for the further development of HEA catalysts. In this review, we summarize the recent literature on HT techniques for HEA synthesis, characterization and performance testing. We also review the ML models that are used to process and analyze existing databases to accelerate the discovery of HEA catalysts. Finally, the potential challenges and perspectives of HT techniques and ML models are presented to accelerate the discovery of new HEA catalysts and promote their development.

Theoretical Calculation Assisted by Machine Learning Accelerate Optimal Electrocatalyst Finding for Hydrogen Evolution Reaction

“…It sustains long‐term stability upon HER and OER, [78] demonstrating the feasibility of HEA and MEA in electrocatalytic fields. Similar studies are also reported in FeCoNiMnW, [79] NiCoFeMoMn, [80] CuAlNiMoFe [27] ect [76,81] . By implementing machine learning and DFT calculations, Saidi et al [82] .…”

“…But with the increase of the metal elements in the HEA, the constructed systems tend to increase sharply, thus enlarging the potential candidates for them in various functional materials fields. ML strategy offers a convenient method to search for excellent candidates among a vast of constructed data, which has been widely utilized in recent years for high throughput screening [73–77] . For the HER, the constructed HAE and MEA reduce the usage of Pt and offer diverse adsorption sites for H, thus leading to various sites exhibiting different adsorption energy for HER, which enhances the HER activities.…”

“…ML strategy offers a convenient method to search for excellent candidates among a vast of constructed data, which has been widely utilized in recent years for high throughput screening. [73][74][75][76][77] For the HER, the constructed HAE and MEA reduce the usage of Pt and offer diverse adsorption sites for H, thus leading to various sites exhibiting different adsorption energy for HER, which enhances the HER activities. For example, by constructing FeCoNiRu HEA, the catalyst performs high activities for HER and OER.…”

Future prospects of high-entropy alloys as next-generation industrial electrode materials

“…HT techniques can achieve more automated, parallel, and efficient HEA research. 224 Singh et al employed ML and DFT to predict the adsorption free energy of key reaction intermediates on HEAs, thereby quantitatively unifying the ligand (element identity) and coordination (surface structures) effects for HEA catalysts. A neural network (NN) model was utilized to evaluate the OH* adsorption energy over the IrPdPtRhRu HEA catalyst.…”

Combinatorial Design of Novel Multiprincipal Element Alloys Using Experimental Techniques

“…It is also worth noting that the experimentally studied compositional libraries are often narrowed by preliminary theoretical calculations using DFT, MD, ML, or CALPHAD methods. [16][17][18][19][20][21][66][67][68][69] However, this study focuses on the experimental part of the combinatorial design of MPEAs; therefore, only a brief overview of this theoretical field is given here. The high-throughput computational techniques can help to identify the compositions promising from the point of view of application demands, thereby reducing the time and effort invested in the experimental investigations.…”