To address surface reaction network complexity using scaling relations machine learning and DFT calculations
Surface reaction networks involving hydrocarbons exhibit enormous complexity with thousands of species and reactions for all but the very simplest of chemistries. We present a framework for optimization under uncertainty for heterogeneous catalysis reaction networks using surrogate models that are trained on the fly. The surrogate model is constructed by teaching a Gaussian process adsorption energies based on group additivity fingerprints, combined with transitionstate scaling relations and a simple classifier for determining the ratelimiting step. The surrogate model is iteratively used to predict the most important reaction step to be calculated explicitly with computationally demanding electronic structure theory. Applying these methods to the reaction of syngas on rhodium(111), we identify the most likely reaction mechanism. Lastly, propagating uncertainty throughout this process yields the likelihood that the final mechanism is complete given measurements on only a subset of the entire network and uncertainty in the underlying density functional theory calculations.
 Authors:

^{[1]};
^{[2]};
^{[3]};
^{[1]}
 Stanford Univ., Stanford, CA (United States)
 Georgia Inst. of Technology, Atlanta, GA (United States)
 SLAC National Accelerator Lab., Menlo Park, CA (United States)
 Publication Date:
 Grant/Contract Number:
 AC0276SF00515
 Type:
 Accepted Manuscript
 Journal Name:
 Nature Communications
 Additional Journal Information:
 Journal Volume: 8; Journal ID: ISSN 20411723
 Publisher:
 Nature Publishing Group
 Research Org:
 SLAC National Accelerator Lab., Menlo Park, CA (United States)
 Sponsoring Org:
 USDOE
 Country of Publication:
 United States
 Language:
 English
 Subject:
 97 MATHEMATICS AND COMPUTING; catalytic mechanism; density functional theory; heterogeneous catalysis; reaction mechanisms
 OSTI Identifier:
 1352168
Ulissi, Zachary W., Medford, Andrew J., Bligaard, Thomas, and Nørskov, Jens K.. To address surface reaction network complexity using scaling relations machine learning and DFT calculations. United States: N. p.,
Web. doi:10.1038/ncomms14621.
Ulissi, Zachary W., Medford, Andrew J., Bligaard, Thomas, & Nørskov, Jens K.. To address surface reaction network complexity using scaling relations machine learning and DFT calculations. United States. doi:10.1038/ncomms14621.
Ulissi, Zachary W., Medford, Andrew J., Bligaard, Thomas, and Nørskov, Jens K.. 2017.
"To address surface reaction network complexity using scaling relations machine learning and DFT calculations". United States.
doi:10.1038/ncomms14621. https://www.osti.gov/servlets/purl/1352168.
@article{osti_1352168,
title = {To address surface reaction network complexity using scaling relations machine learning and DFT calculations},
author = {Ulissi, Zachary W. and Medford, Andrew J. and Bligaard, Thomas and Nørskov, Jens K.},
abstractNote = {Surface reaction networks involving hydrocarbons exhibit enormous complexity with thousands of species and reactions for all but the very simplest of chemistries. We present a framework for optimization under uncertainty for heterogeneous catalysis reaction networks using surrogate models that are trained on the fly. The surrogate model is constructed by teaching a Gaussian process adsorption energies based on group additivity fingerprints, combined with transitionstate scaling relations and a simple classifier for determining the ratelimiting step. The surrogate model is iteratively used to predict the most important reaction step to be calculated explicitly with computationally demanding electronic structure theory. Applying these methods to the reaction of syngas on rhodium(111), we identify the most likely reaction mechanism. Lastly, propagating uncertainty throughout this process yields the likelihood that the final mechanism is complete given measurements on only a subset of the entire network and uncertainty in the underlying density functional theory calculations.},
doi = {10.1038/ncomms14621},
journal = {Nature Communications},
number = ,
volume = 8,
place = {United States},
year = {2017},
month = {3}
}