The Application of Novel Functional Materials to Machine Learning

Abstract

Due to the numerous challenges associated with traditional methods of developing energy materials, such as low success probabilities, high time consumption, and high computational cost, screening advanced materials coupled with modeling of their quantitative structural-activity relationships has recently become one of the hot and trending topics in next-generation functional materials. As a result, new research concepts and technologies are required to promote the study and development of functional materials. With the recent advances in artificial intelligence and machine learning, there is a growing hope that data-driven materials research will change scientific findings and lead to the establishment of new paradigms for energy materials development. Machine learning (ML) is a powerful tool for extracting insights from multidimensional data quickly and efficiently. It provides a much-needed pathway for speeding up the research and investigation of novel materials in order to solve time-sensitive global concerns like climate change. Large datasets have made it possible to build machine learning algorithms for a variety of applications, such as experimental/device optimization and material discovery, in recent years. Furthermore, contemporary breakthroughs in data-driven materials engineering show that machine learning technology can help with not just the design and development of advanced energy materials, but also the discovery and deployment of these materials. The need and necessity of developing new energy materials in order to contribute to global carbon neutrality are discussed in this chapter. Following that, the most recent advancements in data-driven materials research and engineering are reviewed, including alkaline ion battery materials, photovoltaic materials, catalytic materials, and carbon dioxide capture materials. Finally, the remaining obstacles in the creation of new energy materials are discussed, as well as significant pointers to effective machine learning applications.