Integrating high-throughput characterization into combinatorial heterogeneous catalysis: unsupervised construction of quantitative structure/property relationship models

This paper presents a novel approach in the framework of heterogeneous combinatorial catalysis, which integrates into the global discovery strategy the use of inexpensive high-throughput characterization of libraries of catalysts, as multivariate spectral descriptors for catalytic quantitative structure/property relationship (QSPR) modeling. Moreover, QSPR models can be used to assist the design of new libraries and for extraction of rules and relationships, yielding knowledge about catalysis. This approach can be of special interest when experimental evaluation of catalytic behavior is very expensive or time-consuming, as, for instance, for catalyst deactivation studies, for testing under very severe conditions, or when high amounts of catalyst are demanded. This methodology has been applied to modeling of the behavior of epoxidation catalysts, with the composition vector of the starting synthesis gel and XRD spectra as descriptors. Dimensional reduction was conducted by principal components analysis, clustering, and Kohonen networks, and predictive models were obtained with the use of logistic equations, artificial neural networks, and decision tree techniques. The use of spectral descriptors made it possible to markedly improve the prediction performance obtained with synthesis descriptors alone.