Predicting Materials Behavior with Atomistic Simulations and Machine Learning

Data driven approaches based on machine learning (ML) algorithms are very popular in the domain of physical sciences for the determination of yet unknown structure- properties-performance relationships for a wide range of different material families. This dissertation focuses on studying a number of such cases where various ML algorithms and statistical techniques, coupled with appropriate materials data obtained from experiments and atomistic simulations, are employed to build comprehensive ML-based frameworks capable of predicting complex materials behavior. The materials spaces investigated encompass isolated organic molecules, polymer crystals, inorganic multiferroics and actinides, while the target system characteristics or functionalities include molecular crystallization propensity, ferroelectricity and magnetism, which are in turn connected to the structural and electronic properties of the considered materials. In order to gain electronic-level understanding (Human Learning) of functionalities, such as ferroelectricity and magnetism, we have examined four different systems using density functional theory (DFT) approaches. These studies provided sufficient introductory knowledge for construction of targeted, data-driven ML-based frameworks — described in this dissertation — for further evaluation of the materials properties of interest, as well as for prediction of novel materials with similar or advanced characteristics