Title: Coupling Materials Physics with Data Science to Predict New Materials and Properties
The screening of novel materials with good performance and the modeling of quantitative structure-property relationships are interesting topics in the field of condensed matter and materials science. Traditional computational modeling often consume tremendous time and resources and are limited by their theoretical foundations. Thus, it is interesting to develop new methods of accelerating the discovery and design of novel materials. Recently, materials discovery and design using machine learning have been receiving increasing attention and have achieved great improvements in both time efficiency and prediction accuracy. For the long term we intend to introduce machine learning for rare earth-containing materials and propose possible algorithms to predict new materials. By directly combining computational studies with available experimental data, we hope to provide insights into the parameters that affect the properties of materials, thereby enabling more efficient and target-oriented research on materials discovery and design.