Learning design rules for selective oxidation catalysts from high-throughput experimentation and artificial intelligence

The design of heterogeneous catalysts is challenged by the complexity of materials and processes that govern reactivity and by the fact that the number of good catalysts is very small. Here, we show how the subgroup-discovery (SGD) artificial-intelligence local approach[1] can be applied to an experimental plus theoretical data set to identify constraints or rules on key physicochemical parameters that exclusively describe materials and reaction conditions with outstanding catalytic performance.[2] By using high-throughput experimentation, 120 SiO₂-supported catalysts containing Ru, W and P were synthesized and tested in propylene oxidation. As candidate descriptive parameters, the temperature and ten calculated parameters related to the composition and chemical nature of elements in the catalyst materials, were offered. The temperature, the P content, and the composition-weighted electronegativity are identified as key parameters describing high yields of value-added oxygenate products. The SG rules reflect the underlying processes associated to high performance, and guide catalyst design.