and research of materials. Generally speaking, experimental measurement is an easy and intuitive method of materials research. However, it is usually conducted in an inefficient manner over a long time period, including synthetic experiments, property measurement, microstructure, and property analysis. And those approaches require highly in terms of equipment, experimental environment, and expertise of researcher. Computational simulation, including the electronic structure calculations based on density functional theory (DFT), molecular dynamics, Monte Carlo techniques, and the phase-field method, is expected to guide the discovery of new materials and reduce cost in materials development. Nevertheless, it strongly depends on the microstructures of materials and usually required highperformance computing equipment. Therefore, new materials generally require approximately 20-30 years from discovery to practical application. To accelerate the research of new materials, the "Materials Genome Initiative" (MGI) is proposed in 2011, [6] whose critical idea is the combination of "experiment", "calculation", and "data". [7] With the development of MGI, the era of materials big data arrives. Extensive experiment and computation materials databases are built, such as the Inorganic Crystal Structure Database (ICSD), [8] Cambridge Structure Database, [9] Pauling File Database, [10] Materials Project (MP), [11] and Open Quantum Materials Database. [12] Using those big data is an effective way to accelerate the discovery and design of new materials for LBs.Machine learning (ML) is a powerful tool for the discovery and performance prediction of new materials in highdimensional data. [13,14] It is divided into three parts: input, model, and output. ML model can be trained via training data through optimization algorithms and then automatically build the relationship between the input and output without any physical conditions. The trained ML model would rapidly predict the properties of new samples and determine the expected materials. [15] Recently, ML has been successfully applied in crystal structure prediction, electronic characteristics, experimental procedures, materials performance searches, and the discovery of new materials. [16] In recent years, there have been many successful examples of using ML in LB materials. [17] For example, Ceder et al. employed a computational framework to evaluate and screen 104082 Li-containing materials as cathode coatings, where the data were obtained from the ICSD. [18] Based on the nudged Lithium batteries (LBs) have many high demands regarding their application in portable electronic devices, electric vehicles, and smart grids. Machine learning (ML) can effectively accelerate the discovery of materials and predict their performances for LBs, which is thus able to markedly enhance the development of advanced LBs. In recent years, there have been many successful examples of using ML for advanced LBs. In this review, the basic procedure and representative methods of ML are briefly introdu...

No abstract