Two-dimensional MoS₂ photoelectric sensing array has shown great application potential in the image sensing field, and the fabrication of the pattern structure is the foundation for the construction of MoS₂ array devices. However, the traditional ion etching patterning technology easily leads to the shedding and residue of MoS₂ materials, which affects the quality of the pattern structure and the performance of the devices. Here, through a simple laser direct patterning method, we investigate the etching-free fabrication of the two-dimensional MoS₂ pattern structure and the construction of the photoelectric sensing array. The research results show that for monolayer MoS₂ materials, the removal rate of the laser direct patterning method can reach about 98%, the structural density of the fabricated array pattern can reach 107 units/mm², and the size of each pattern unit is about 3.5μm. Moreover, this fabrication method rarely introduces ion trap defects, and the photoelectric response of the MoS₂ sensing array has no obvious trailing effect. This work provides a reference for high-quality patterning of two-dimensional materials into array devices without etching.

As the basis of machine vision, the biomimetic image sensing devices are the eyes of artificial intelligence. In recent years, with the development of two-dimensional (2D) materials, many new optoelectronic devices are developed for their outstanding performance. However, there are still little sensing arrays based on 2D materials with high imaging quality, due to the poor uniformity of pixels caused by material defects and fabrication technique. Here, we propose a 2D MoS₂ sensing array based on artificial neural network (ANN) learning. By equipping the MoS₂ sensing array with a “brain” (ANN), the imaging quality can be effectively improved. In the test, the relative standard deviation (RSD) between pixels decreased from about 34.3% to 6.2% and 5.49% after adjustment by the back propagation (BP) and Elman neural networks, respectively. The peak signal to noise ratio (PSNR) and structural similarity (SSIM) of the image are improved by about 2.5 times, which realizes the re-recognition of the distorted image. This provides a feasible approach for the application of 2D sensing array by integrating ANN to achieve high quality imaging.