(544ei) A Machine Learning Model for Accelerating Biomimetic Electrocatalyst Discovery

The oxygen reduction reaction (ORR) is a key obstacle preventing several energy storage devices (e.g., fuel cells, batteries) from being efficient. The reaction can be very slow and thus various catalysts have been used. Currently platinum is the catalyst which has given the best results for this reaction, however platinum is a very scarce and expensive material. Therefore, looking for cheaper materials which can efficiently catalyze the ORR is a crucial step in using fuel cells.1 Metal organic frameworks (MOFs) have shown potential as a catalyst for ORR by combining the high surface area provided by MOFs and the catalytic activity of functional groups in metalloporphyrins, enzyme-like complexes.2,3

Porphyrinic MOFs are created through the combination of inorganic nodes and organic linkers. Additionally the porphyrinic linkers themselves can be further functionalized in both meso and beta positions. Therefore an extremely broad range of combinations exists, and each MOF structures can have very different catalytic properties. By combining data-driven techniques such as genetic algorithms (GA) and machine learning (ML) with computational chemistry methods such as density functional theory (DFT), we aim to develop a high-throughput approach to designing optimal structures of MOFs for oxygen reduction.

(1) Xin, H.; Holewinski, A.; Linic, S. Predictive Structure–Reactivity Models for Rapid Screening of Pt-Based Multimetallic Electrocatalysts for the Oxygen Reduction Reaction. ACS Catal. 2012, 2 (1), 12–16.

(2) Miner, E. M.; Fukushima, T.; Sheberla, D.; Sun, L.; Surendranath, Y.; Dincă, M. Electrochemical Oxygen Reduction Catalysed by Ni3(hexaiminotriphenylene)2. Nat. Commun. 2016, 7, 10942.

(3) Usov, P. M.; Huffman, B.; Epley, C. C.; Kessinger, M. C.; Zhu, J.; Maza, W. A.; Morris, A. J. Study of Electrocatalytic Properties of Metal-Organic Framework PCN-223 for the Oxygen Reduction Reaction. ACS Appl. Mater. Interfaces 2017, 9 (39), 33539–33543.