Learning Design Rules for Selective Oxidation Catalysts from High-Throughput Experimentation and Artificial Intelligence.

Lucas Foppa,Sandip De,Luca M Ghiringhelli,Ansgar Schäfer,Stephan A Schunk,Christopher Sutton,Patricia Löser,Matthias Scheffler

doi:10.1021/acscatal.1c04793

Abstract

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 in comparison to the number of possible materials. Here, we show how the subgroup-discovery (SGD) artificial-intelligence approach can be applied to an experimental plus theoretical data set to identify constraints on key physicochemical parameters, the so-called SG rules, which exclusively describe materials and reaction conditions with outstanding catalytic performance. By using high-throughput experimentation, 120 SiO2-supported catalysts containing ruthenium, tungsten, and phosphorus were synthesized and tested in the catalytic oxidation of propylene. As candidate descriptive parameters, the temperature and 10 parameters related to the composition and chemical nature of the catalyst materials, derived from calculated free-atom properties, were offered. The temperature, the phosphorus content, and the composition-weighted electronegativity are identified as key parameters describing high yields toward the value-added oxygenate products acrolein and acrylic acid. The SG rules not only reflect the underlying processes particularly associated with high performance but also guide the design of more complex catalysts containing up to five elements in their composition.

Highlights

Heterogeneous catalysis is governed by an intricate interplay of multiple processes[1] such as the surface reaction networks and the typically unknown dynamic restructuring of the catalyst material under the reaction conditions
Our results demonstrate the ability of the highthroughput experimentation (HTE) and theory SGD approach to detect interpretable, chemically meaningful, and complex patterns associated with very few data points presenting exceptional catalytic performance
The yield of value-added oxygenate product measured by HTE was used as a target, and parameters obtained from density functional theory (DFT)-calculated free-atom properties were offered as candidate descriptive parameters

Summary

■ INTRODUCTION

Heterogeneous catalysis is governed by an intricate interplay of multiple processes[1] such as the surface reaction networks and the typically unknown dynamic restructuring of the catalyst material under the reaction conditions. The five-component catalyst corresponding to the highest yield of oxygenates (59.60% at 400 °C) contains tantalum as the E2 element and the composition-averaged electronegativity for this material is 3.947 eV Such an EN value lies within the threshold defined by the SG rule (Figure 4D). This is because different mechanisms may operate on these materials that could lead to exceptional performance. The SGD analysis might need to be performed by including new data points covering such far unexplored portions of the materials space to enlarge the domain in which the SG rules can detect exceptional catalysts and reaction conditions

■ CONCLUSIONS

■ ACKNOWLEDGMENTS

Findings

■ REFERENCES