Traditional methods of discovering new materials, such as the empirical trial and error method and the density functional theory (DFT)‐based method, are unable to keep pace with the development of materials science today due to their long development cycles, low efficiency, and high costs. Accordingly, due to its low computational cost and short development cycle, machine learning is coupled with powerful data processing and high prediction performance and is being widely used in material detection, material analysis, and material design. In this article, we discuss the basic operational procedures in analyzing material properties via machine learning, summarize recent applications of machine learning algorithms to several mature fields in materials science, and discuss the improvements that are required for wide‐ranging application.

Advancing of the lead halide perovskite solar cells towards photovoltaic market demands large-scale devices of high-power conversion efficiency, high reproducibility and stability via low-cost fabrication technology, and in particular resistance to humid environment for long-time operation. Here we achieve uniform perovskite film based on a novel polymer-scaffold architecture via a mild-temperature process. These solar cells exhibit efficiency of up to ∼16% with small variation. The unencapsulated devices retain high output for up to 300 h in highly humid environment (70% relative humidity). Moreover, they show strong humidity resistant and self-healing behaviour, recovering rapidly after removing from water vapour. Not only the film can self-heal in this case, but the corresponding devices can present power conversion efficiency recovery after the water vapour is removed. Our work demonstrates the value of cheap, long chain and hygroscopic polymer scaffold in perovskite solar cells towards commercialization.

This paper summarizes the ideas, operations and workflows of how machine learning has driven the discovery of new materials.