Unveiling Hidden Catalysts for the Oxidative Coupling of Methane based on Combining Machine Learning with Literature Data

Catalysts for oxidative coupling of methane (OCM) are explored using data science and 1868 OCM catalysts from literature data. Machine learning reveals the descriptors responsible for determining the C2 yield produced during the OCM reaction. Trained machine predicts 56 undiscovered catalysts with corresponding conditions for OCM reactions achieving a C2 yield over 30 %. First principle calculations are implemented to evaluate the predicted catalysts where the activation of CH4, CH3, and O2 are confirmed with the predicted catalysts for the OCM reaction. Thus, machine learning is proven to be an effective approach for discovering hidden catalysts and should accelerate the catalyst design process in general.

[1]  S. Suram,et al.  High-throughput bubble screening method for combinatorial discovery of electrocatalysts for water splitting. , 2014, ACS combinatorial science.

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

[3]  Anubhav Jain,et al.  Finding Nature’s Missing Ternary Oxide Compounds Using Machine Learning and Density Functional Theory , 2010 .

[4]  Guy Marin,et al.  Economics of the oxidative coupling of methane as an add-on unit for naphtha cracking , 1995 .

[5]  Charlie Tsai,et al.  Mechanistic insights into heterogeneous methane activation. , 2017, Physical chemistry chemical physics : PCCP.

[6]  Xinhe Bao,et al.  Direct Conversion of Methane to Value-Added Chemicals over Heterogeneous Catalysts: Challenges and Prospects. , 2017, Chemical reviews.

[7]  J. Lunsford,et al.  Oxidative dimerization of methane over a lithium-promoted magnesium oxide catalyst , 1985 .

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

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

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

[11]  K. Jacobsen,et al.  Real-space grid implementation of the projector augmented wave method , 2004, cond-mat/0411218.

[12]  Edward Sanville,et al.  Improved grid‐based algorithm for Bader charge allocation , 2007, J. Comput. Chem..

[13]  Burke,et al.  Generalized Gradient Approximation Made Simple. , 1996, Physical review letters.

[14]  Martin Kumar Patel,et al.  Steam cracking and methane to olefins: Energy use, CO2 emissions and production costs , 2008 .

[15]  G. E. Keller,et al.  Synthesis of ethylene via oxidative coupling of methane: I. Determination of active catalysts , 1982 .

[16]  H. Monkhorst,et al.  SPECIAL POINTS FOR BRILLOUIN-ZONE INTEGRATIONS , 1976 .

[17]  W. H. Weinberg,et al.  High throughput experimental and theoretical predictive screening of materials : A comparative study of search strategies for new fuel cell anode catalysts , 2003 .

[18]  Svante Wold,et al.  MULTIVARIATE DATA ANALYSIS OF SUBSTITUENT DESCRIPTORS , 1983 .

[19]  Martin Holena,et al.  Statistical Analysis of Past Catalytic Data on Oxidative Methane Coupling for New Insights into the Composition of High‐Performance Catalysts , 2011 .

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

[21]  Jens K Nørskov,et al.  Understanding trends in C-H bond activation in heterogeneous catalysis. , 2017, Nature materials.

[22]  G. Henkelman,et al.  A fast and robust algorithm for Bader decomposition of charge density , 2006 .

[23]  Marco Buongiorno Nardelli,et al.  The high-throughput highway to computational materials design. , 2013, Nature materials.

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

[25]  Ilkeun Lee,et al.  Oxygen adsorption and oxide formation on V(100) surfaces , 2007 .

[26]  Michael J. Gradassi,et al.  Economics of natural gas conversion processes , 1995 .

[27]  G. Kresse,et al.  The structure of the oxygen induced (1×5) reconstruction of V(100) , 2001 .

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

[29]  Graham J. Hutchings,et al.  Oxidative coupling of methane using oxide catalysts , 1989 .