Proceedings of Asia-Pacific International Conference on Perovskite, Organic Photovoltaics and Optoelectronics (IPEROP27)
Publication date: 22nd October 2026
A wave of digital transformation not only propels social service and commercial production, but also reenergizes a method of material science research that has traditionally relied on personal experience/idea, serendipitous findings, and trial-and-error experiments. Machine learning (ML), which makes use of ever-expanding artificial intelligence (AI) technology, provides an alternative path to a target material and broadens the region of chemical spaces explored. We have explored organic photovoltaic (OPV) materials and reported ML-based virtual screening and experimental validation. We developed an automated robot-embedded measurement system that performs photoabsorption spectroscopy, optical microscopy, and white-light-flash time-resolved microwave conductivity (TRMC). This system is applied to exploration of lead halide perovskite solar cell (PSC) and non-lead solution-processed semiconductors. In particular, fabrication of the perovskite photoactive layer remains highly intricate, with film formation strongly modulated by various processing and environmental factors. We report an environment-controlled, robot-assisted platform for automated thin-film fabrication designed to quantify and visualize perovskite crystallization in situ. This work establishes a practical route to stable, quantitative, and mechanistically informed investigation of solution-processed photovoltaic films.
