Single-atom catalysts (SACs) attract widespread attention in heterogeneous catalysis due to their maximum atomic utilization efficiency and unique physical and chemical properties. However, their applications in chemical sensing keep huge potential but remain unclear. Herein, a Ni-N₄-C SAC was synthesized for the trace detection of dopamine (DA) and uric acid (UA). The Ni-N₄-C SAC exhibited superior sensing performance compared to the Ni clusters. The detection range for DA and UA were 0.05 µM ~ 75 µM and 5 µM ~ 90 µM with detection limits of 0.027 µM and 0.82 µM, respectively. Density functional theory (DFT) computations indicate that Ni-N₄-C has a lower reaction barrier during electrochemical process, indicating that the atomic Ni sites possess higher intrinsic activity than Ni clusters. Moreover, DA and UA show strong potential dependency on the Ni-N₄-C catalyst, indicating its applicability for their concurrent detection. This work extends the application of SACs in chemical sensing.

Herein we proposed a data-driven high-throughput principle to screen high-performance single-atom materials for hydrogen evolution reaction (HER) and hydrogen sensing by combing the theoretical computations and a topology-based multi-scale convolution kernel machine learning algorithm. After the rational training by 25 groups of data and prediction of all 168 groups of single-atom materials for HER and sensing, respectively, a high prediction accuracy (> 0.931 R² score) was achieved by our model. Results show that the promising HER catalysts include Pt atoms in C₄ and Sc atoms in C₁N₃ coordination environment. Moreover, Y atoms in C₄ coordination environment and Cd atoms in C₂N₂-ortho coordination environment were predicted with great potential as hydrogen sensing materials. This method provides a way to accelerate the discovery of innovative materials by avoiding the time-consuming empirical principles in experiments.

Currently, the machine learning (ML)-based scanning transmission electron microscopy (STEM) analysis is limited in the simulative stage, its application in experimental STEM is needed but challenging. Herein, we built up a universal model to analyze the vacancy defects and single atoms accurately and rapidly in experimental STEM images using a full convolution network. In our model, the unavoidable interference factors of noise, aberration, and carbon contamination were fully considered during the training, which were difficult to be considered in the past. Even toward the simultaneous identification of various vacancy types and low-contrast single atoms in the low-quality STEM images, our model showed rapid process speed (45 images per second) and high accuracy (> 95%). This work represents an improvement in experimental STEM image analysis by ML.