A computational framework accompanied by machine learning techniques for designing two-dimensional/organic hybrid quantum materials

Due to their exotic and tunable optoelectronic properties, two-dimensional (2D)/organic hybrid materials formed by intercalating conjugated organic molecules within the van der Waals gap of 2D-based transition metal chalcogenides are promising quantum materials. Nonetheless, developing and screening a database of millions of such potential materials remains a difficult task. We have created a computational framework that allows us to design molecular intercalated 2D material families, model such hybrid materials in a high-throughput manner, and analyze their properties using first-principles methods. We have also developed a machine learning algorithm that exploits and analyzes the designed hybrid material database based on several metrics such as the intercalation energy in order to identify promising quantum materials for further computational and experimental investigation.