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.

Monolayer Bi ₂ O ₂ Se is a promising post-silicon-era semiconductor candidate because of its simultaneous excellent device performance and high ambient stability.

Tungsten disulphide (WS₂), which exhibits excellent saturable absorption properties, has attracted much attention in the applications of photonic devices. In this paper, WS₂ is applied for the preparation of a saturable absorber (SA). Using the pulsed laser deposition (PLD) method, WS₂ is deposited on the side surface of the tapered fiber. In order to obtain larger non-linearity of the SAs with evanescent wave interaction, the tapered fiber had a smaller waist diameter and longer fused zone. Gold film was deposited on the fiber-taper WS₂ SAs to improve their reliability and avoid oxidation and corrosion. Employing the balanced twin-detector method, the modulation depth of the fiber-taper WS₂ SAs was measured to be 17.2%. With the fiber-taper WS₂ SA, a generated pulse with 246 fs duration and a 57 nm bandwidth was obtained at 1561 nm. The electrical signal to noise ratio was better than 92 dB. To our knowledge, the pulse duration was the shortest among the reported all-fiber lasers with transition metal dichalcogenide (TMD) SAs. These results indicate that fiber-taper WS₂ SAs with smaller waist diameter and longer fused zone are promising photonic devices for ultrashort pulse generation in all-fiber lasers.

A kind of pollution known as electromagnetic interference (EMI), which results from ubiquitous usage of various electronic communication and military radar equipment, has been receiving increasing attention recently. However, large-area EMI shielding on transparent and/or curved surfaces, including building windows, curved glass wall, and special requirements spaces (SRSs), remains hard to achieve. In this paper, a silver nanofiber (AgNF) based flexible and transparent EMI shielding film was successfully assembled via a room-temperature roll-to-roll production method. For transparent application scenario, AgNF with 89% transmittance in visible range and 1 μm thickness shows ~20 dB shielding efficiency (EMI SE). On the other hand, total shielding (>50 dB) is obtained when the thickness of AgNF increases to 10 μm, while its transmittance in visible range remains higher than 75%. Considering the facile and scale-free production technology, this material can be readily applied in large-scale, transparent, and/or SRSs EMI shielding.