This study investigated the optoelectronic synaptic properties of amorphous gallium oxide (GaOx) thin films for low-power physical reservoir computing (PRC) applications. The fabricated devices were irradiated with time series UV-C light to characterize the paired pulse facilitation (PPF) index, a fundamental synaptic property governed by transient photocurrent dynamics. Furthermore, the short-term memory (STM) capacity and parity check (PC) nonlinearity were quantitatively evaluated as essential PRC performance metrics, alongside a practical demonstration using a handwritten digit recognition task. The experimental results revealed a high PPF index when the width and interval of the input light pulses were comparable to or shorter than the inherent photocurrent time constants of the device. Although the evaluated nonlinearity was lower than that of conventional optoelectronic artificial synapses based on other semiconductor materials, the GaOx device exhibited a comparable short-term memory capacity. Consequently, the reservoir layer achieved a high classification accuracy of approximately 90% in the handwritten digit recognition task. As these performance metrics were higher than those of the annealed sample, the device without annealing proved to be more suitable for PRC applications. These findings indicate that the amorphous GaOx thin film device holds significant potential to serve as a robust, UV-C-responsive edge artificial intelligence (AI) sensor in harsh environments, such as outer space.
Takanashi et al. (Sat,) studied this question.