Enabling Catalyst Discovery through Machine Learning and High-Throughput Experimentation

Machine learning is an avenue to unravel multi-dimensional relationships present in catalytic systems. We describe a novel framework that incorporates machine learning algorithms with experimental high-throughput catalytic data and elemental properties to discovery new materials. The framework uses a small experimental data set coupled with chemi-cally descriptive features to predict future catalyst performance and guide synthesis. This led to the discovery of several novel catalyst compositions for ammonia decomposition, which were experimentally validated against “state-of-the-art” ammonia decomposition catalysts and were found to have exceptional low-temperature performance at substantially lower weight loadings of Ru.