Artificial Intelligence (AI) may prove very useful in determining the best recipe for spray-on solar technology.
Jayan Thomas is an associate professor at the NanoScience Technology Center from the University of Central Florida and lead author on a study that used machine learning, or AI, to optimize the materials used to make perovskite solar cells (PSC). The AI assists identify formulas for creating liquid solar cells, which potentially could allow them to be painted on bridges, houses, and skyscrapers.
Perovskite solar cells were one of the top ten science breakthroughs in 2013. They offer amazing potential in improved efficiency along with cheaper materials and manufacturing costs. PSC converts photovoltaic power into consumable energy using both organic and inorganic halide perovskite materials.
Perovskite can be processed in solid or liquid states, which offers engineers a lot of flexibility. The downfall of perovskite solar cells is they are not easy to make. It takes scientists a lot of time to figure out the right mixture to produce the best efficiency, stability, flexibility, and cost.
For their experiments, the team analyzed more than 2,000 peer-reviewed publications about perovskites, collecting more than 300 data points, before feeding that information into an AI system the team created. The system then analyzed that data to predict which combination of perovskites would perform the best.

This is where Thomas and his team’s use of AI comes into play, he explains here:
Our results demonstrate that machine learning tools can be used for crafting perovskite materials and investigating the physics behind developing highly efficient PSCs. This can be a guide to design new materials as evidenced by our experimental demonstration.
The team is confident that this discovery of using AI can help to advance this perovskite technology at a much faster rate, than humans alone. As Thomas adds:
This is a promising finding because we use data from real experiments to predict and obtain a similar trend from the theoretical calculation, which is new for PSCs. We also predicted the best recipe to make PSC with different bandgap perovskites.
Graduate student, and first author of the paper, Jinxin Li, also comments: “Perovskites have been a hot research topic for the past 10 years, but we think we really have something here that can move us forward.”
Spray-on solar technology has been a revolutionary concept and hot topic since it’s first discovery as a possibility. This new AI technology and lead-free perovskite hybrid cells recently created, lead me to think this is something we will surely see, possibly sooner rather than later.
