Recent advancements and major breakthroughs in machine learning (ML) technologies in the past decade have made it possible to collect, analyze, and interpret an unprecedented amount of sensory information. A new era for “smart” sensor systems is emerging that changes the way that conventional sensor systems are used to understand the world. Smart sensor systems have taken advantage of classic and emerging ML algorithms and modern computer hardware to create sophisticated “smart” models that are tailored specifically for sensing applications and fusing diverse sensing modalities to gain a more holistic appreciation of the system being monitored. Herein, a review of the recent sensing applications, which harness ML enabled smart sensor systems, is presented. First well‐known ML algorithms implemented in smart sensor systems for practical sensing applications are discussed. Subsequent sections summarize the practical sensing applications under two major categories: physical and chemical sensing and visual imaging sensing describing how the sensor technologies are coupled with ML “smart” models and how these systems achieve practical benefits. Finally, an outlook on the current trajectory and challenges that will be faced by future smart sensing systems and the opportunities that may be unlocked is provided.

Atomically thin two-dimensional (2D) metal oxides exhibit unique optical, electrical, magnetic, and chemical properties, rendering them a bright application prospect in high-performance smart devices. Given the large variety of both layered and non-layered 2D metal oxides, the controllable synthesis is the critical prerequisite for enabling the exploration of their great potentials. In this review, recent progress in the synthesis of 2D metal oxides is summarized and categorized. Particularly, a brief overview of categories and crystal structures of 2D metal oxides is firstly introduced, followed by a critical discussion of various synthesis methods regarding the growth mechanisms, advantages, and limitations. Finally, the existing challenges are presented to provide possible future research directions regarding the synthesis of 2D metal oxides. This work can provide useful guidance on developing innovative approaches for producing both 2D layered and non-layered nanostructures and assist with the acceleration of the research of 2D metal oxides.

The adverse effects of NO₂ on the environment and human health promote the development of high-performance gas sensors to address the need for monitoring. Two-dimensional (2D) metal chalcogenides have been considered an emerging group of NO₂-sensitive materials, while incomplete recovery and low long-term stability are the two major hurdles for their practical implementation. The transformation into oxychalcogenides is an effective strategy to alleviate these drawbacks, but usually requires multiple-step synthesis and lacks controllability. Here, we prepare tailorable 2D p-type gallium oxyselenide with the thicknesses of 3-4 nm, through a single-step mechanochemical synthesis that combines the in-situ exfoliation and oxidation of bulk crystals. The optoelectronic NO₂ sensing performances of such 2D gallium oxyselenide with different oxygen contents are investigated at room temperature, in which 2D GaSe_0.58O_0.42 exhibits the largest response magnitude of 82.2% towards 10 ppm NO₂ at the irradiation of UV, with full reversibility, excellent selectivity, and long term stability for at least one month. Such overall performances are significantly improved over those of reported oxygen-incorporated metal chalcogenide-based NO₂ sensors. This work provides a feasible approach to prepare 2D metal oxychalcogenides in a single-step manner and demonstrates their great potential for room-temperature fully reversible gas sensing.

Room temperature (RT) gas sensors based on low-dimensional materials that mainly included three strategies. (1) Nanostructures optimisation; (2) driven by voltage biasing; (3) assisting with light illumination.