Recent progress on discovery and properties prediction of energy materials: Simple machine learning meets complex quantum chemistry

In nature, the properties of matter are ultimately governed by the electronic structures. Quantum chemistry (QC) at electronic level matches well with a few simple physical assumptions in solving simple problems. To date, machine learning (ML) algorithm has been migrated to this field to simplify calculations and improve fidelity. This review introduces the basic information on universal electron structures of emerging energy materials and ML algorithms involved in the prediction of material properties. Then, the structure-property relationships based on ML algorithm and QC theory are reviewed. Especially, the summary of recently reported applications on classifying crystal structure, modeling electronic structure, optimizing experimental method, and predicting performance is provided. Last, an outlook on ML assisted QC calculation towards identifying emerging energy materials is also presented.