Machine learning for advanced energy materials

Abstract

The screening of advanced materials coupled with the modeling of their quantitative structural-activity relationships has recently become one of the hot and trending topics in energy materials due to the diverse challenges, including low success probabilities, high time consumption, and high computational cost associated with the traditional methods of developing energy materials. Following this, new research concepts and technologies to promote the research and development of energy materials become necessary. The latest advancements in artificial intelligence and machine learning have therefore increased the expectation that data-driven materials science would revolutionize scientific discoveries towards providing new paradigms for the development of energy materials. Furthermore, the current advances in data-driven materials engineering also demonstrate that the application of machine learning technology would not only significantly facilitate the design and development of advanced energy materials but also enhance their discovery and deployment. In this article, the importance and necessity of developing new energy materials towards contributing to the global carbon neutrality are presented. A comprehensive introduction to the fundamentals of machine learning is also provided, including open-source databases, feature engineering, machine learning algorithms, and analysis of machine learning model. Afterwards, the latest progress in data-driven materials science and engineering, including alkaline ion battery materials, photovoltaic materials, catalytic materials, and carbon dioxide capture materials, is discussed. Finally, relevant clues to the successful applications of machine learning and the remaining challenges towards the development of advanced energy materials are highlighted.