Recent Applications of Machine Learning and Deep Learning in Identifying Alloys with Specific Conductivity

Nowadays, machine learning and deep learning are transforming the way researchers discover and optimize alloys with specific electrical conductivity. These advanced computational techniques can move forward the search for the mentioned alloys by analyzing large datasets, identifying hidden patterns, and predicting properties more efficiently than traditional trial-and-error methods. Having analyzed the numerous recent works, the applications of the machine learning and deep learning in identifying alloys with specific conductivity are determined. Accordingly, predicting electrical conductivity of alloys, accelerated discovery of new alloys, optimization of alloy composition and processing, understanding the structure-property relationship and identifying the new metals, data-driven experimental design, high-quality analyzing experimental and simulation data, and developing industrial applications are the main areas developed by the machine learning and deep learning techniques. Besides, the regression algorithms are utilized in predicting electrical conductivity and estimating conductivity. On the other hands, the classifying algorithms are applied in identifying suitable alloys and classifying alloys. Furthermore, clustering alloys and finding new material categories can be done mostly by K-Means Clustering, and DBSCAN algorithms. It also was conducted, PCA and t-SNE are broadly used in simplifying complex alloy composition data and visualizing conductivity trends. Eventually, deep learning can be applied in predicting conductivity changes, modeling thermal effects on alloy, suggesting new high-conductivity alloy, simulating alloy conductivity, and optimizing alloys.