Machine learning links material composition and performance in catalysts |

By: University of Michigan

Machine learning was used by researchers at the University of Michigan to foretell how the contents of metal alloys and metal oxides influence their electrical properties.  

Researchers at the University of Michigan used machine learning to forecast how the compositions of metal alloys and metal oxides affect their electrical structures, paving the door for cleaner fuels and more sustainable chemical industry. Understanding how the material will operate as a mediator, or catalyst, of chemical reactions, relies heavily on its electrical structure. The principal component analysis is a well-known machine learning technique that is covered in introductory data science classes. The model divides the density of states into two halves, which are referred to as major components. The oxygen stability of metal oxides and perovskites, a type of metal oxide, was accurately described by the model. 



Subscribe to our newsletter