Advances in automation and artificial intelligence are transforming how new materials are discovered and developed. By combining high-throughput experimental platforms with data-driven tools, researchers can rapidly test hundreds of material variations, precisely control processing conditions, and generate large, high-quality datasets. This approach not only speeds up optimization but also provides deeper insight into how materials form and function.

In this talk, I will share how our team at the University of Tennessee is integrating AI across the entire research workflow—from generating new ideas and designing experiments to analyzing data and guiding next steps. These systems can efficiently explore complex design spaces, helping identify promising materials faster and with greater confidence. I will highlight applications in halide perovskites, a class of materials with strong potential for energy and optoelectronic technologies.

Looking forward, the combination of automation, machine learning, and intelligent decision-making is enabling a new paradigm of “smart labs” that continuously learn and improve. These capabilities have the potential to significantly reduce development timelines, lower costs, and accelerate the transition of advanced materials from the lab to real-world applications.