Compositional Design And Phase Formation Capability Of High-entropy Rare-earth Disilicates From Machine Learning And Decision Fusion

This article discusses the use of machine learning models to predict the phase stability of multicomponent RE disilicates. The models use features obtained directly from a database and are normalized to improve convergence. A random splitting technique is used to divide the data into training and testing sets, and the performance of each model is assessed at different proportions of training and testing data. The article also highlights the importance of selecting appropriate hyper-parameters for the models.