Scientists at the Advanced Institute for Materials Research found that machine learning accelerates the design and optimization of multicomponent catalysts, saving considerable time and resources. The technology significantly advanced the discovery and optimization of multicomponent metal oxide electrocatalysts for the oxygen reduction reaction (ORR). This could potentially revolutionize the efficiency and affordability of renewable energy technologies such as hydrogen fuel cells and batteries. They published their findings in the Journal of Materials Chemistry A.
The study analyzed 7,798 distinct metal oxide ORR catalysts from high-throughput experiments containing elements such as nickel, iron, manganese, magnesium, calcium, lanthanum, yttrium, and indium. Using the XGBoost machine learning method, the researchers built a predictive model to identify potential new compositions. They found that a high number of itinerant electrons and high configuration entropy are critical features for achieving high current density in ORR.
CREDIT: Xue Jia et al.
“This research underscores the incredible potential of artificial intelligence in accelerating catalyst design and materials discovery,” says Xue Jia, Assistant Professor at the Advanced Institute for Materials Research. “Our findings will hopefully make future breakthroughs in sustainable energy technologies possible, which are crucial for addressing global energy challenges.”
