Machine learning accelerates discovery of solar-cell perovskites

Researchers at EPFL have developed a method using machine learning to accelerate the discovery of perovskite materials for solar cells. By creating a high-quality dataset of band-gap values for 246 perovskite materials using advanced computational techniques, they trained a machine learning model to identify promising candidates from a database of 15,000 materials. This approach led to the discovery of 14 new perovskite materials with optimal properties for photovoltaic applications, potentially enhancing the efficiency and cost-effectiveness of solar panels.

For more details, read the full article here: