Rapid estimation of activation energy in heterogeneous catalytic reactions via machine learning

Estimation of activation energies within heterogeneous catalytic reactions is performed using machine learning and catalysts dataset. In particular, descriptors for determining activation energy are revealed within the 788 activation energy dataset. With the implementation of machine learning and chosen descriptors, activation energy can be instantly predicted with over 90% accuracy during cross‐validation. Thus, rapid estimation of activation energies within heterogeneous catalytic reactions can be made achievable via machine learning, leading toward the acceleration of catalysts design and characterization. © 2018 Wiley Periodicals, Inc.

[1]  M. Mavrikakis,et al.  Hydrogen adsorption, absorption and diffusion on and in transition metal surfaces: A DFT study , 2012 .

[2]  Yuzuru Tanaka,et al.  Materials informatics: a journey towards material design and synthesis. , 2016, Dalton transactions.

[3]  Ahmed H. Zewail,et al.  Direct Observation of the Transition State , 1995 .

[4]  G. Ertl.  Reactions at Solid Surfaces , 2009 .

[5]  J. Nørskov,et al.  Universal transition state scaling relations for (de)hydrogenation over transition metals. , 2011, Physical chemistry chemical physics : PCCP.

[6]  D. Wales,et al.  Perspective: Insight into reaction coordinates and dynamics from the potential energy landscape. , 2015, The Journal of chemical physics.

[7]  Martin Holena,et al.  Developing catalytic materials for the oxidative coupling of methane through statistical analysis of literature data , 2015 .

[8]  Zachary W. Ulissi,et al.  To address surface reaction network complexity using scaling relations machine learning and DFT calculations , 2017, Nature Communications.

[9]  Gadi Rothenberg,et al.  Predicting adsorption on metals: simple yet effective descriptors for surface catalysis. , 2013, Physical chemistry chemical physics : PCCP.

[10]  H. Grönbeck,et al.  Methane Oxidation over PdO(101) Revealed by First-Principles Kinetic Modeling. , 2015, Journal of the American Chemical Society.

[11]  J. Vybíral,et al.  Big data of materials science: critical role of the descriptor. , 2014, Physical review letters.

[12]  G. Henkelman,et al.  A climbing image nudged elastic band method for finding saddle points and minimum energy paths , 2000 .

[13]  Nathan S. Lewis,et al.  Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO2 Reduction , 2017 .

[14]  G. Mercurio,et al.  Probing the transition state region in catalytic CO oxidation on Ru , 2015, Science.

[15]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[16]  Michael J. Janik,et al.  Interaction trends between single metal atoms and oxide supports identified with density functional theory and statistical learning , 2018, Nature Catalysis.

[17]  P. Hu,et al.  Methane transformation to carbon and hydrogen on Pd(100): Pathways and energetics from density functional theory calculations , 2002 .

[18]  Jens K Nørskov,et al.  The catalyst genome. , 2013, Angewandte Chemie.

[19]  G. Henkelman,et al.  Optimization methods for finding minimum energy paths. , 2008, The Journal of chemical physics.

[20]  Ichigaku Takigawa,et al.  Toward Effective Utilization of Methane: Machine Learning Prediction of Adsorption Energies on Metal Alloys , 2018 .

[21]  J. Nørskov,et al.  Fundamental Concepts in Heterogeneous Catalysis , 2014 .

[22]  Andrew A. Peterson,et al.  Global Optimization of Adsorbate–Surface Structures While Preserving Molecular Identity , 2014, Topics in Catalysis.

[23]  G. Henkelman,et al.  Improved tangent estimate in the nudged elastic band method for finding minimum energy paths and saddle points , 2000 .

[24]  Matthew Neurock,et al.  Reactivity theory of transition-metal surfaces: a Brønsted-Evans-Polanyi linear activation energy-free-energy analysis. , 2010, Chemical reviews.

[25]  G. Somorjai.  Modern Surface Science and Surface Technologies: An Introduction. , 1996, Chemical reviews.

[26]  Koji Tsuda,et al.  Machine-learning prediction of the d-band center for metals and bimetals , 2016 .