Uncovering electronic and geometric descriptors of chemical activity for metal alloys and oxides using unsupervised machine learning

We show that unsupervised machine learning (ML) using principal-component (PC) analysis provides a straightforward pathway for developing accurate and interpretable electronic-structure descriptors of the chemical and catalytic properties of materials. We demonstrate the approach by finding chemisorption descriptors for metal alloys and surface oxygens on metals and metal oxides. In both cases, the PC descriptors yield ML models that predict the material's chemical properties with competitive accuracy compared with ML models built using established descriptors. Importantly, interpreting the electronic-structure patterns captured by each PC descriptor via signal reconstruction suggests potential design motifs for future electronic-structure descriptor design and allows us to identify links between a material's geometric and catalytic properties. Ultimately, we show that the unsupervised ML approach provides a route to find electronic-structure descriptors of the catalytic properties of materials that readily connect to geometric structure and composition.