Machine learning approach could help advance perovskite-based solar cells
Scientists at the U.S. Department of Energy's (DOE) Argonne National Laboratory and Purdue University have developed a machine learning method for screening many thousands of compounds as solar absorbers. Argonne's Maria Chan and Purdue's Arun Mannodi-Kanakkithodi, who led the study, chose to work with a form of artificial intelligence (AI) that uses a combination of large data sets and algorithms to imitate the way that humans learn. It learns from training with sample data and past experience to make ever better predictions.
The team used their machine learning method to assess the solar energy properties of halide perovskites. "Unlike silicon or cadmium telluride, the possible variations of halides combined with perovskites are essentially unlimited," said Chan. "There is thus an urgent need to develop a method that can narrow the promising candidates to a manageable number. To that end, machine learning is a perfect tool."