High-throughput experimentation meets artificial intelligence: a new pathway to catalyst discovery
- 28 May 2020
- journal article
- review article
- Published by Royal Society of Chemistry (RSC) in Physical Chemistry Chemical Physics
- Vol. 22 (20), 11174-11196
- https://doi.org/10.1039/d0cp00972e
Abstract
High throughput experimentation in heterogeneous catalysis provides an efficient solution to the generation of large datasets under reproducible conditions. Knowledge extraction from these datasets has mostly been performed using statistical methods, targeting the optimization of catalyst formulations. The combination of advanced machine learning methodologies with high-throughput experimentation has enormous potential to accelerate the predictive discovery of novel catalyst formulations that do not exist with current statistical design of experiments. This perspective describes selective examples ranging from statistical design of experiments for catalyst synthesis to genetic algorithms applied to catalyst optimization, and finally random forest machine learning using experimental data for the discovery of novel catalysts. Lastly, this perspective also provides an outlook on advanced machine learning methodologies as applied to experimental data for materials discovery.Funding Information
- Division of Graduate Education (1250052)
- Advanced Research Projects Agency - Energy (DE-AR0000931)
This publication has 153 references indexed in Scilit:
- Statistical Analysis of Past Catalytic Data on Oxidative Methane Coupling for New Insights into the Composition of High‐Performance CatalystsChemCatChem, 2011
- Metal catalyzed ethylene epoxidation: A comparative density functional theory studyJournal of Natural Gas Chemistry, 2011
- Palladium–silver bimetallic catalysts with improved activity and selectivity for ethylene epoxidationApplied Catalysis A: General, 2011
- The detailed kinetics and mechanism of ethylene epoxidation on an oxidised Ag/α-Al2O3 catalystCatalysis Today, 2010
- Virtual screening of materials using neuro-genetic approach: Concepts and implementationComputational Materials Science, 2009
- Support Vector Machines for Predictive Modeling in Heterogeneous Catalysis: A Comprehensive Introduction and Overfitting Investigation Based on Two Real ApplicationsJournal of Combinatorial Chemistry, 2006
- Integrating high-throughput characterization into combinatorial heterogeneous catalysis: unsupervised construction of quantitative structure/property relationship modelsJournal of Catalysis, 2005
- Design of Discovery Libraries for Solids Based on QSAR ModelsQSAR & Combinatorial Science, 2005
- Combinatorial and conventional development of novel dehydrogenation catalystsApplied Catalysis A: General, 2003
- Application of Artificial Neural Networks to Combinatorial Catalysis: Modeling and Predicting ODHE CatalystsChemphyschem, 2002