Machine Learning-Based High Entropy Alloys-Algorithms and Workflow: A Review

High-entropy alloys (HEAs) have attracted considerable attention because of their excellent properties and broad compositional design space. However, traditional trial-and-error methods for screening HEAs are costly and inefficient, thereby limiting the development of new materials. Although density functional theory (DFT), molecular dynamics (MD), and thermodynamic modeling have improved the design efficiency, their indirect connection to properties has led to limitations in calculation and prediction. With the awarding of the Nobel Prize in Physics and Chemistry to artificial intelligence (AI) related researchers, there has been a renewed enthusiasm for the application of machine learning (ML) in the field of alloy materials. In this study, common and advanced ML models and strategies in HEA design were introduced, and the mechanism by which ML can play a role in composition optimization and performance prediction was investigated through case studies. The general workflow of ML application in material design was also introduced from the programmer’s point of view, including data preprocessing, feature engineering, model training, evaluation, optimization, and interpretability. Furthermore, data scarcity, multi-model coupling, and other challenges and opportunities at the current stage were analyzed, and an outlook on future research directions was provided.