469485 Machine-Learning-Augmented Chemisorption Model for Metal Oxides

Wednesday, November 16, 2016
Grand Ballroom B (Hilton San Francisco Union Square)
Zheng Li and Hongliang Xin, Department of Chemical Engineering, Virginia Polytechnic Institute and State University, Blacksburg, VA

Perovskites with the ABO3 type structure have attracted enormous research efforts in recent years due to their high activity for catalyzing oxygen evolution in (photo)-electrochemical systems. The thermodynamically and kinetically unfavorable oxygen evolution reaction (OER) is considered as a bottleneck for many energy conversion processes such as metal-air batteries and photocatalytic water splitting cells1. We aim to design cost-effective metal oxides for catalyzing the sluggish OER. It is, however, very time-consuming and costly to search for highly optimized metal oxides by high-throughput experiments and/or quantum-chemical calculations due to the vast materials space of composition and geometry.

In this poster, we extend our previous study2 on metal catalysis to metal oxides by developing a machine-learning-augmented chemisorption model that captures adsorption properties of active sites on metal oxides. To design effective features that the machine-learning algorithms can use to ‘learn’ and predict properties of metal oxides, we applied a feature engineering process on the catalyst database. We explore electronic based features such as the B-site metal eg band filling, d-band upper edge, oxidation state, d-orbital splitting, ligand strength, and easily accessible structural based features such as the coordination number, together with the intrinsic properties of metal atoms. Using those features, the machine-learning model optimized with available ab initioadsorption energies on perovskite (001) surfaces can capture adsorption energies of *O, *OH, and *OOH intermediates with the root mean squared errors (RMSE) smaller than the DFT-GGA calculation error of 0.2 eV. Compared with the traditional high-throughput computational and experimental trial-and-error approach, the machine-learning chemisorption models exhibit great potential in accelerating the discovery of high-performance oxide materials for electrocatalysis.

1. Suntivich, J., May, K. J., Gasteiger, H. A., Goodenough, J. B. & Shao-Horn, Y. A Perovskite Oxide Optimized for Oxygen Evolution Catalysis from Molecular Orbital Principles. Science 334,1383–1385 (2011).

2. Ma, X., Li, Z., Achenie, L. E. K. & Xin, H. Machine-Learning-Augmented Chemisorption Model for CO2 Electroreduction Catalyst Screening. J. Phys. Chem. Lett. 6, 3528–3533 (2015).

Extended Abstract: File Not Uploaded