Predicting adsorption on metals: simple yet effective descriptors for surface catalysis

Ras, Erik‐Jan; Louwerse, Manuel J.; Mittelmeijer‐Hazeleger, Marjo C.; Rothenberg, Gadi

doi:10.1039/c3cp42965b

Cited by 38 publications

(36 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[20][21][22][23][24] Considering that first-principles calculations are too time-consuming to explore the full spectrum of possibilities, and on the other hand, a great amount of data is being generated and accumulated in the field, ML methods can give a fast and high-precision alternative to the first-principles models. However, ML methods in catalysis [25][26][27][28][29][30][31][32][33][34] are still in their infancy.…”

Section: Introductionmentioning

confidence: 99%

Machine-learning prediction of the d-band center for metals and bimetals

et al. 2016

View full text Add to dashboard Cite

The d-band center for metals has been widely used in order to understand activity trends in metal-surface-catalyzed reactions in terms of the linear Brønsted-Evans-Polanyi relation and Hammer-Nørskov d-band model. In this paper, the d-band centers for eleven metals (Fe, Co, Ni, Cu, Ru, Rh, Pd, Ag, Ir, Pt, Au) and their pairwise bimetals for two different structures (1% metal doped-or overlayer-covered metal surfaces) are statistically predicted using machine learning methods from readily available values as descriptors for the target metals (such as the density and the enthalpy of fusion of each metal). The predictive accuracy of four regression methods with different numbers of descriptors and different test-set/training-set ratios are quantitatively evaluated using statistical cross validations. It is shown that the d-band centers are reasonably well predicted by the gradient boosting regression (GBR) method with only six descriptors, even when we predict 75% of the data from only 25% given for training (average 2 root mean square error (RMSE) < 0.5 eV). This demonstrates a potential use of machine learning methods for predicting the activity trends of metal surfaces with a negligible CPU time compared to first-principles methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine-learning prediction of the d-band center for metals and bimetals

et al. 2016

View full text Add to dashboard Cite

show abstract

“…We show that one and two parameter regression analysis is not sufficient to accurately predict the adsorption strength. We therefore closely follow the strategy of Ras et al, 3 who used a multi-parameter regression and a genetic algorithm to accurately predict the adsorption strength of a set of small molecules to metal surfaces, and finally arrive at an accurate prediction of the adsorption strength.…”

Section: Introductionmentioning

confidence: 99%

“…The comparatively efficient treatment of entire classes of materials allows the determination of fundamental material parameters, so called descriptors, which can be correlated to the performance in a given application. [2][3][4][5][6][7][8] Today databases for these descriptors for different types of materials exist, 9 and it is possible to screen them to identify promising compounds and predict their efficiency.…”

Section: Introductionmentioning

confidence: 99%

“…In the literature, descriptors based on structural parameters, the stability of the active site, electronic structure related parameters, the volume and the charge of the active site have been suggested. 2,3,25,35,36,[38][39][40] It is a priory not clear which descriptors are necessary to accurately describe the molecular adsorption of CO and NO to transition metal exchanged zeolites. We therefore focus on a series of descriptors.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Developing a Descriptor-Based Approach for CO and NO Adsorption Strength to Transition Metal Sites in Zeolites

et al. 2017

View full text Add to dashboard Cite

The discovery of new materials tailored for a given application typically requires the screening of a large number of compounds and this process can be significantly accelerated by computational analysis. In such an approach the performance of a compound is correlated to a materials property, a so called descriptor. Here we develop a descriptor-based approach for the adsorption of CO and NO to Cu, Ni, Co and Fe sites in zeolites. We start out by discussing a possible design strategy for zeolite catalysts, define the studied test set of sites in the zeolites SSZ-13 and Mordenite, and define a 1 set of appropriate descriptors. In a subsequent step we use these descriptors in single-, two-and multi-parameter regression analysis and finally use a machine-learning genetic algorithm to reduce the number of variables. We find that one or two descriptors are not sufficient to accurately capture the interactions between molecules and metal centers in zeolites and indeed a multi-parameter approach is necessary. Even though many of the descriptors are directly correlated, we identify the position of the s-orbital and the number of valence electrons of the active site as well as the HOMO-LUMO gap of the adsorbate as most important descriptors. Furthermore the reconstruction of the active sites upon adsorption plays a crucial role and when it is explicitly included in the analysis, correlations improve significantly. In the future we expect that the fundamental methodology developed here will be adapted and transferred to selected problems in adsorption and catalysis and will assist the rational design of materials for the given application.

show abstract

“…Once the regression model is successfully constructed, it permits the rapid identification of the optimal catalyst for a target reaction by interpolation without calculating results for all the other candidates. Ras and Rothenberg et al presented a simple and efficient model based on genetic algorithm variable selection and Partial Least Squares (PLS) regression for predicting the adsorption of molecules (heats of adsorption) on metal surfaces [9]. Their model used six descriptors for each metal (number of d-electrons, surface energy, first ionization potential, as well as atomic radius, volume, and mass) and three for each adsorptive species (HOMO-LUMO energy gap, molecular volume, and mass).…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Predictions of Factors Affecting the Activity of Heterogeneous Metal Catalysts

et al. 2018

View full text Add to dashboard Cite

The ultimate goal in heterogeneous catalytic science is to accurately predict trends in catalytic activity based on the electronic and geometric structures of active metal surfaces. Such predictions would allow the rational design of materials having specific catalytic functions without extensive trial-and-error experiments. The d-band center values of metals are well known to be an important parameter affecting the catalytic activity of these materials, and activity trends in metal surface catalyzed reactions can be explained based on the linear Brønsted-Evans-Polanyi relationship and the Hammer-Nørskov d-band model. The present work demonstrates the possibility of employing state-of-the-art machine learning methods to predict the d-band centers of metals and bimetals while using negligible CPU time compared to the more common first-principles approach.

show abstract

Predicting adsorption on metals: simple yet effective descriptors for surface catalysis

Cited by 38 publications

References 39 publications

Machine-learning prediction of the d-band center for metals and bimetals

Machine-learning prediction of the d-band center for metals and bimetals

Developing a Descriptor-Based Approach for CO and NO Adsorption Strength to Transition Metal Sites in Zeolites

Machine Learning Predictions of Factors Affecting the Activity of Heterogeneous Metal Catalysts

Contact Info

Product

Resources

About