EPFL turns to AI for the development of new solar cells

24 May 2024 09:43

Greater Geneva Bern

Supporting partner

Lausanne - Researchers from the Swiss Federal Institute of Technology Lausanne (EPFL) have used Artificial Intelligence to identify new materials for use in solar cells. In total, 14 highly promising materials were uncovered.

A research project carried out by the Swiss Federal Institute of Technology Lausanne (EPFL) has led to the development of a method that allows large databases to be searched for potential materials to be used in new solar cells. According to a press release, by leveraging the benefits of machine learning (ML), the researchers were able to identify several promising halide perovskites. ML is a subfield of Artificial Intelligence (AI), where computers are able to learn from data sets or databases made available to them.

Perovskites represent a promising new group of materials for future photovoltaic applications due to their straightforward, low-cost manufacturing processes. In order for perovskites to make optimal use of solar energy, it is vital that the new materials have a suitable band gap. These band gaps are capable of absorbing photons with certain energy values and then converting them into electricity.

The EPFL team led by Haiyuan Wang and Alfredo Pasquarello developed an ML model that was able to identify 14 totally new perovskites from 15,000 candidate materials. These are said to be excellent candidates for highly efficient solar cells of the future. With this, the researchers successfully demonstrated that the use of ML models can significantly speed up the process of discovery and validation of new photovoltaic materials. ce/eb

Supporting partner

Swiss Pavilion Digital

Previous newsletters