Prediction of energies for reaction intermediates and transition states on catalyst surfaces using graph-based machine learning models

Wang, Baochuan; Gu, Tangjie; Lu, Yijun; Yang, Bo

doi:10.1016/j.mcat.2020.111266

Cited by 6 publications

(7 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As expected, the accuracy of the ensemble model was improved with a mean absolute error of 0.94 kcal/mol C , which is lower than any other individual regressor. It exemplifies that more reliable estimation can be attained through the voting ensemble method for most species by complementing independent individual models with each other. , …”

Section: Results and Discussionmentioning

confidence: 91%

“…It exemplifies that more reliable estimation can be attained through the voting ensemble method for most species by complementing independent individual models with each other. 5,74 The performance of the ensemble model for subsets of the data can be found in Figure S12, where C n species (n = 2, 3, 4, 5, and 6) are highlighted against the whole dataset as well as cyclic/acyclic species. No significant differences are observed in prediction accuracy as a function of carbon number, with predictions within each group roughly consistent with the dataset as a whole.…”

Section: Prediction Of Individual Species Across Iterationsmentioning

confidence: 99%

See 1 more Smart Citation

Predicting the Enthalpy of Hydrocarbon Radicals Adsorbed on Pt(111) Using Molecular Fingerprints and Machine Learning

Nam,

Ramasamy,

Raser

et al. 2024

J. Phys. Chem. C

View full text Add to dashboard Cite

The reliable prediction of properties for the adsorbates, including their enthalpy, has been a long-standing challenge as a first key step in studying surface reactions. It is especially difficult when large adsorbates are involved as the interactions between the adsorbates and surface atoms are complex. Here, we developed machine learning (ML) models for the prediction of the formation enthalpy of various C 2 to C 6 hydrocarbon adsorbates on the Pt(111) surface based on 384 density functional theory calculations. Focusing on larger and more intricate adsorbates, two-thirds of the total species were C 6 species. Four molecular descriptors that represent the valency and bonding of individual carbons within the adsorbates were generated without intensive computation. They were subsequently used as the features of the ML models with three linear and four nonlinear algorithms. The models were developed with 30 different samplings of train/test sets, and their results were statistically analyzed to ensure the performance of the models. Nonlinear models, especially kernel ridge regression and extreme gradient boosting, outperformed linear models with lower absolute errors. The top two accurate models, based on these algorithms, also displayed remarkable robustness in predicting various species. Employing ensemble average voting with these two models, we achieved the lowest mean absolute error of 0.94 kcal/mol C . Finally, ML was used to estimate the formation enthalpy of 3115 hydrocarbon adsorbates on Pt(111), highlighting the promise of these methods to study more complicated reaction networks.

show abstract

Section: Results and Discussionmentioning

confidence: 91%

Section: Prediction Of Individual Species Across Iterationsmentioning

confidence: 99%

Predicting the Enthalpy of Hydrocarbon Radicals Adsorbed on Pt(111) Using Molecular Fingerprints and Machine Learning

Nam,

Ramasamy,

Raser

et al. 2024

J. Phys. Chem. C

View full text Add to dashboard Cite

show abstract

“…As an alternative to traditional scaling relations, Baochuan et al. 168 proposed the use of graph-based machine learning models to estimate the binding energies and activation energies of elementary steps in ethanol synthesis from syngas on Rh catalyst. The parity plot of graph neural network and BEP relation-predicted activation energy barriers against the DFT-calculated activation energies were presented.…”

Section: Kinetic Parameter Estimationmentioning

confidence: 99%

“…They suggested this method to be much more reliable in predicting the activation energies over a broader range of activation barriers compared to scaling relations. 168 The kinetic linear scaling relationships such as BEP relationships are usually developed to predict the activation energies for specific reaction steps on catalyst surfaces as they are mostly single-parameter-dependent (Reaction energies) correlations. The universal/linear scaling relationships developed for simple metal systems 151 rely mostly on the reaction energies where the changes in the chemical identities of the reactants and the surface restructuring of the catalyst during the course of reactions are neglected.…”

Section: Kinetic Parameter Estimationmentioning

confidence: 99%

Iterative multiscale and multi-physics computations for operando catalyst nanostructure elucidation and kinetic modeling

Rajan¹,

Pushkar²,

Dharmalingam³

et al. 2023

iScience

View full text Add to dashboard Cite

“…Recently, machine learning techniques have been used to predict the E a , , including linear regression to support vector regression, ensemble tree models, Gaussian processes, and neural networks, just to name a few. When considering the reactants’ and surfaces’ geometric properties, such as distance, angle, coordination number (CN), bond counts, etc., various models with improved accuracy over the BEP relationship were achieved. , Though these “black-box” models can reach a higher accuracy, they lack transparency in general .…”

Section: Introductionmentioning

confidence: 99%

Structure Sensitivity of Metal Catalysts Revealed by Interpretable Machine Learning and First-Principles Calculations

Shu,

Li,

Liu

et al. 2024

J. Am. Chem. Soc.

View full text Add to dashboard Cite

The nature of the active sites and their structure sensitivity are the keys to rational design of efficient catalysts but have been debated for almost one century in heterogeneous catalysis. Though the Brønsted−Evans−Polanyi (BEP) relationship along with linear scaling relation has long been used to study the reactivity, explicit geometry, and composition properties are absent in this relationship, a fact that prevents its exploration in structure sensitivity of supported catalysts. In this work, based on interpretable multitask symbolic regression and a comprehensive first-principles data set, we discovered a structure descriptor, the topological under-coordinated number mediated by number of valence electrons and the lattice constant, to successfully address the structure sensitivity of metal catalysts. The database used for training, testing, and transferability investigation includes bond-breaking barriers of 20 distinct chemical bonds over 10 transition metals, two metal crystallographic phases, and 17 different facets. The resulting 2D descriptor composing the structure term and the reaction energy term shows great accuracy to predict the reaction barriers and generalizability over the data set with diverse chemical bonds in symmetry, bond order, and steric hindrance. The theory is physical and concise, providing a constructive strategy not only to understand the structure sensitivity but also to decipher the entangled geometric and electronic effects of metal catalysts. The insights revealed are valuable for the rational design of the sitespecific metal catalysts.

show abstract

Prediction of energies for reaction intermediates and transition states on catalyst surfaces using graph-based machine learning models

Cited by 6 publications

References 54 publications

Predicting the Enthalpy of Hydrocarbon Radicals Adsorbed on Pt(111) Using Molecular Fingerprints and Machine Learning

Predicting the Enthalpy of Hydrocarbon Radicals Adsorbed on Pt(111) Using Molecular Fingerprints and Machine Learning

Iterative multiscale and multi-physics computations for operando catalyst nanostructure elucidation and kinetic modeling

Structure Sensitivity of Metal Catalysts Revealed by Interpretable Machine Learning and First-Principles Calculations

Contact Info

Product

Resources

About