Machine learning-guided property prediction of energetic materials: Recent advances, challenges, and perspectives
Xiaolan Tian, Siwei Song, Fang Chen, Xiujuan Qi, Yi Wang, Qinghua Zhang
Abstract
Predicting chemical properties is one of the most important applications of machine learning. In recent years, the prediction of the properties of energetic materials using machine learning has been receiving more attention. This review summarized recent advances in predicting energetic compounds’ properties (e.g., density, detonation velocity, enthalpy of formation, sensitivity, the heat of the explosion, and decomposition temperature) using machine learning. Moreover, it presented general steps for applying machine learning to the prediction of practical chemical properties from the aspects of data, molecular representation, algorithms, and general accuracy. Additionally, it raised some controversies specific to machine learning in energetic materials and its possible development directions. Machine learning is expected to become a new power for driving the development of energetic materials soon.