中国科学院长春光学精密机械物理研究所李绍娟团队研究了基于Ta₂NiSe₅/SnS₂异质结的紫外至近红外物理吸附辅助光电突触晶体管。2025年3月17日，《光：科学与应用》杂志发表了这一成果。

神经形态计算视觉是克服机器视觉应用中算法瓶颈的最有前景的技术解决方案。一体式神经形态传感器越来越受到关注，因为它们可以将视觉感知、处理和记忆功能集成到一个设备中。然而，一体式神经形态传感器的有限响应性和数据保留时间通常会阻碍其在多光谱机器视觉中的潜力，特别是在包含模式识别关键信息的近红外（NIR）波段。

研究组展示了基于Ta₂NiSe₅/SnS₂异质结的物理吸附辅助光电突触晶体管，该晶体管在宽带（375-1310 nm）内具有可调的突触功能。他们提出了一种关于物理吸附辅助持久光电导（PAPPC）效应的策略，以有效解决检测和存储近红外光信息的问题。根据这一策略，该设备的响应率和数据保留时间在375至1310 nm的宽带范围内得到了显著提高和延长。

此外，这些器件通过调制几个光学和背栅信号来实现多级非易失性光电存储器，以模拟情绪控制的学习和记忆过程、光学写入电擦除和联想学习。此外，还开发了一个简化的人类视觉系统来模拟颜色认知感知和记忆功能。该方法为创建先进的一体式神经形态传感器和开发神经形态计算视觉提供了一条途径。

附：英文原文

Title: Physisorption-assistant optoelectronic synaptic transistors based on Ta2NiSe5/SnS2 heterojunction from ultraviolet to near-infrared

Author: Tan, Fan, Chang, Chunlu, Zhang, Nan, An, Junru, Liu, Mingxiu, Zhao, Xingyu, Che, Mengqi, Liu, Zhilin, Shi, Yaru, Li, Yahui, Feng, Yanze, Lin, Chao, Zheng, Yuquan, Li, Dabing, Lanza, Mario, Li, Shaojuan

Issue&Volume: 2025-03-17

Abstract: Neuromorphic computing vision is the most promising technological solution to overcome the arithmetic bottleneck in machine vision applications. All-in-one neuromorphic sensors have been attracting increased attention because they can integrate visual perception, processing, and memory functionalities into one single device. However, the limited responsivity and data retention time of all-in-one neuromorphic sensors usually hinder their potential in multispectral machine vision, especially in the near-infrared (NIR) band which contains critical information for pattern recognition. Here, we demonstrate physisorption-assistant optoelectronic synaptic transistors based on Ta2NiSe5/SnS2 heterojunction, which present tunable synaptic functionality in broadband (375–1310nm). We propose a strategy about the physisorption-assistant persistent photoconductivity (PAPPC) effect to effectively solve the problem in detecting and storing the NIR light information. Under this strategy, the responsivity and data retention time of our devices were significantly enhanced and prolonged in broadband from 375 to 1310nm. Further, the devices realize multilevel non-volatile optoelectronic memory through the modulation of several optical and back-gate signals to simulate emotion-controlled learning and memory processes, optical writing-electric erasing, and associative learning. Moreover, we developed a simplified human visual system to simulate color-cognitive perception and memory functions. Our approach offers a route for creating advanced all-in-one neuromorphic sensors and developing neuromorphic computing vision.

DOI: 10.1038/s41377-025-01792-3

Source: https://www.nature.com/articles/s41377-025-01792-3