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.

Magnetic two-dimensional materials have attracted considerable attention for their significant potential application in spintronics. In this study, we present a high-quality Fe-doped SnS₂ monolayer exfoliated using a micromechanical cleavage method. Fe atoms were doped at the Sn atom sites, and the Fe contents are ∼2.1%, 1.5%, and 1.1%. The field-effect transistors based on the Fe_0.021Sn_0.979S₂ monolayer show n-type behavior and exhibit high optoelectronic performance. Magnetic measurements show that pure SnS₂ is diamagnetic, whereas Fe_0.021Sn_0.979S₂ exhibits ferromagnetic behavior with a perpendicular anisotropy at 2 K and a Curie temperature of ~31 K. Density functional theory calculations show that long-range ferromagnetic ordering in the Fe-doped SnS₂ monolayer is energetically stable, and the estimated Curie temperature agrees well with the results of our experiment. The results suggest that Fe-doped SnS₂ has significant potential in future nanoelectronic, magnetic, and optoelectronic applications.

The mixtures of cations and anions used in hybrid halide perovskites for high-performance solar cells often undergo element and phase segregation, which limits device lifetime. We adapted Schelling’s model of segregation to study individual cation migration and found that the initial film inhomogeneity accelerates materials degradation. We fabricated perovskite films (FA _1–x Cs _x PbI ₃ ; where FA is formamidinium) through the addition of selenophene, which led to homogeneous cation distribution that retarded cation aggregation during materials processing and device operation. The resultant devices achieved enhanced efficiency and retained >91% of their initial efficiency after 3190 hours at the maximum power point under 1 sun illumination. We also observe prolonged operational lifetime in devices with initially homogeneous FACsPb(Br _0.13 I _0.87 ) ₃ absorbers.