The University of New South Wales (UNSW) has developed an artificial intelligence-driven workflow that replaces slow iterative materials discovery with a targeted, data-driven approach.
According to UNSW, designing advanced materials remains largely trial and error. Small molecular changes can “radically” alter performance, but with millions of possible combinations, identifying viable candidates is a major bottleneck.
Hybrid perovskites are semiconductors used in applications such as dollar cells and LEDs and are built by combining inorganic layers and organic molecules.
The UNSW says that these organic components play a key role in determining how the material behaves, particularly how it transports electrical charge.
Unlike previous trial-and-error approaches, the UNSW team’s systems work backwards from a desired outcome — such as how a material should handle electrical charge — to identify molecules that could deliver it.
The UNSW says that it then screens large numbers of candidates and filters out those unlikely to be practical to make.
Applied across millions of possibilities, the approach narrowed the field to a small set of ‘promising’ candidates. It is then checked using detailed simulations to confirm their performance.
The work tackles a time-consuming problem in the field, where researchers have typically made incremental changes to known materials rather than exploring new ones systematically.
Candidates have not been tested yet in the lab. However, researchers say the approach could help speed up the development of new materials for electronics and clean energy technologies by making the search process far more efficient.
Write to Aaliyah Rogan at Mining.com.au
Images: Unsplash
