Using Artificial Neural Networks to Boost High‐throughput Discovery in Heterogeneous Catalysis

Abstract

Full PaperThe work presents for the first time a detailed methodology which enable to scrutinize and identify solids that are relevant to be tested in a high throughput program. In the present case study, Artificial Neural Networks (ANN) are used to predict performances of catalysts for the Water Gas Shift reaction. In contrast to previous studies, it is shown that the quantitative prediction by ANN of performances is not adapted to a primary screening stage.On the contrary, ANN used as classifier tool within the course of an Evolutionary Strategy are well performing and well suited for high throughput heterogeneous catalysis. The virtual screening enables to pre-select candidates to be screened experimentally with a very high rate of relevance at an early stage of a high throughput experimentation program, thus reducing significantly the number of trials.

Bayesian migration of Gaussian process regression for rapid process modeling and optimization

“…While this is cost-effective in many applications, it may be desired to design multiple experiments at each iteration when, e.g., a parallel automatic reaction system is available for high-throughput experimentation [36]. A possible solution is to search for all local maxima of the EI as candidates for experiments.…”

Application of Artificial Neural Networks for Catalysis: A Review

“…However, with a well-trained ANN classifier as a filter that could help define the "good" and "bad" catalysts, WGS catalysts could be rationally designed with a GA-assisted HTS method. Being similar to Reference [56], their framework is summarized and reconstructed in Figure 5. know that ANNs can precisely predict the catalytic performances of various catalytic systems, we may want to design and generate new inputs of new expected catalysts, and acquire their predicted performances from a well-trained ANN.…”

“…However, with a welltrained ANN classifier as a filter that could help define the "good" and "bad" catalysts, WGS catalysts could be rationally designed with a GA-assisted HTS method. Being similar to Reference [56], their framework is summarized and reconstructed in Figure 5. A framework of the methodology proposed for boosting primary screening in heterogeneous catalysis [56].…”

“…Being similar to Reference [56], their framework is summarized and reconstructed in Figure 5. A framework of the methodology proposed for boosting primary screening in heterogeneous catalysis [56]. GA: genetic algorithm.…”

“…However, both DFT and MD are limited by the high computational cost with a relatively large catalytic system, which dramatically hinders the further developments of the computer-aided catalyst design and its relevant mechanism study. To address this problem, Nørskov and his co- A framework of the methodology proposed for boosting primary screening in heterogeneous catalysis [56]. GA: genetic algorithm.…”