Analysis and evaluation of machine learning applications in materials design and discovery

Machine Learning (ML) appears to have become the main and foremost approach to both tackle the hurdles and exploit the opportunities of The Information Age. We present our analytical review of the past years applications of the developed ML models in Materials Science. We begin our analysis by highlighting the similarities and the basic difference between Machine Learning and Screening approaches, and focus our work on direct ML applications only. The general ML procedure to develop a successful ML model for materials is illustrated and explained. We also present charts and tables summarizing the relevant literature works into categories based on ML techniques, materials classes, and materials predicted properties. Details and reasons of the most successful applications are explored and discussed based on sample cases. The information, data, and suggested guidelines in this work would be useful to interested researchers in the field of Materials Science.