High throughput experimentation gives us the unique ability to generate massive, multidimensional datasets that are not typical for heterogeneous catalysis studies. Here, we show the synthesis and catalytic screening of over 100 different Ru based bimetallic catalyst combinations using 33 different metals that were synthesized via incipient wetness impregnation. The catalysts were analyzed using Wide Angle X-ray Scattering (WAXS) for phase identification. Catalysts were screened for ammonia decomposition activity using a 16-channel parallel plug flow reactor. Fourier transform infrared (FT-IR) imaging was used to analyze all 16 effluent streams in parallel in under one minute.
All results obtained from WAXS characterization and catalyst screening were fed into a machine learning algorithm to extract the activity descriptors and elemental characteristics that are responsible for ammonia decomposition activity at different operating temperatures. The knowledge extracted from this materials agnostic machine learning algorithm was used to design a second iteration of catalysts, where features that contributed to the greatest change in activity were accentuated.