Artificial Intelligence Can Assist Scientists in Manufacturing Solar Cells

2019-12-17

Artificial intelligence may be the key to accelerating the spray coating technology of solar cells, which will completely change the way consumers use energy. A research team has used machine learning, specifically artificial intelligence, to optimize the materials used in manufacturing perovskite solar cells (PSCs). The organic-inorganic halide perovskite materials used in PSCs convert photovoltaic energy into consumable energy. A research team at the University of Central Florida conducted the aforementioned study on solar cells using machine learning. Perovskite can be processed in solid or liquid form and has great flexibility. It is a feasible concept to spray paint this material on bridges, buildings, and skyscrapers to capture light, convert it into energy, and input it into the grid. So far, the solar cell industry has relied on silicon, mainly because of its high efficiency. However, this is a limited and outdated technology. Perovskite can overcome this limitation, but there is a major obstacle in using perovskite: it is difficult to produce usable and stable materials. Scientists have spent a lot of time trying to find the right formula to achieve all the benefits and eliminate the drawbacks. This is where artificial intelligence comes into play. The work of this team is significant and was published as the cover story in the journal "Advanced Energy Materials" on December 13th. The team reviewed over 2,000 peer-reviewed publications on perovskite, collected over 300 data points, and inputted them into their created artificial intelligence system. This system is able to analyze information and predict which perovskite formula is most effective. "Our research shows that machine learning tools can be used to produce perovskite materials and study the physics behind the development of efficient PSCs," said Dr. Yang Thomas, the first author of the study and an associate professor at the Nanoscience Technology Center, who collaborated with multiple institutions. "Our experiments demonstrate that this can serve as a guide for designing new materials." If this model is confirmed, it means that researchers can find the best formula to establish a world standard. Researchers say that spray-on solar cells may appear in our lifetime. "This is a promising discovery because we use data from real experiments to make predictions and obtain similar trends from theoretical calculations, which is new for PSCs. In addition, we also predict the optimal formula for making PSCs with different bandgap perovskites. Perovskite has been a hot research topic for the past decade, and we believe that we do have something that can drive progress in related research."

RECENT AI NEWS

RECENT AI TOOLS