Perspective—Accelerated Discovery of Organic-Inorganic Hybrid Materials via Machine Learning

Abstract

Hybrid organic-inorganic nanomaterials have ushered new and multifunctional applications in the fields but not limited to, Internet of Things (IoT), microelectronics, optical materials, housing, environment, transport, health and diagnosis, energy, and energy storage. However, fast discovery of organic-inorganic nanomaterials has an inherent challenge, because the conventional trial-and-error strategies are incompetent when millions of potential materials are processed. Machine learning (ML) aims to expedite screening of the hybrid materials based on the end applications. Therefore, employing machine-learning methods will support future experiments in material discovery in such a way that there are fewer chances of error and misinterpretations.