Machine Learning Enabled Screening of Single Atom Alloys: Predicting Reactivity Trend for Ethanol Dehydrogenation

Abstract

A machine learning (ML) approach implementing the gradient boosting regressor (GBR) algorithm is applied to predict the binding energies of oxygen (E O ) and carbon (E C ) atoms on single atom alloys (SAAs) of Cu, Ag and Au. Readily available periodic properties of the transition metals are utilized as input features in the model. Their relative contribution in adsorbate-metal interaction is assessed to develop a comprehensive descriptor. In test runs, the ML model is observed to predict E O and E C with significantly reduced errors (~0.2 eV). Further, ML approach is augmented with an ab initio microkinetic model (MKM) for non-oxidative dehydrogenation (NODH) of ethanol. The ML-MKM is calculated to yield higher turnover frequency for ethanol conversion on NiAu, NiAg, and PtAg SAAs as compared to their monometallic counterparts Au and Ag catalysts. Overall, the ML model provides a rationale for feature selection to synthesize catalytically active SAAs of group 11 elements using fast-track in silico screening.

Tracing the reactivity of single atom alloys for ethanol dehydrogenation using ab initio simulations

“…Recently, much emphasis has been placed on building a large dataset of descriptors (e.g., binding energies of key elements) for SAAs, 13 which in-turn provides a comprehensive evaluation of turnover rates using linear scaling. 28,29 Our group has demonstrated the application of an ML method in predicting turnover rates for the NODH reaction of ethanol over the bimetallic alloys of Cu. 11 On applying the same ML method, the binding energies of carbon and oxygen atoms for NiCu, PtCu and PdCu SAAs are estimated.…”

“…This thought resonates well with several studies which have pursued ML approaches for catalytic trends. 13,28,29 However, catalytic turnovers estimated from ML predicted descriptors and scaling relations may not provide an ideal platform, since departure from scaling relations is reported in the reactivity of SAAs. 14,15 Therefore, an attempt is made here to estimate reactivity trends at the reaction temperature from a complete ab initio parameterized MKM with the adsorption and transition state energies derived from density functional theory (DFT) calculations.…”

Stick or Spill? Scaling Relationships for the Binding Energies of Adsorbates on Single-Atom Alloy Catalysts

“… 25 The success of these models results from their simplicity: only a few parameters (e.g., the d-band center or the binding energies of C and O) are needed to provide semiquantitative predictions regarding the performance of catalysts. 16 , 26 − 28 These models have proved particularly useful for experimentalists and theoreticians to rationalize experimental observations 24 , 27 and predict behaviors on-the-fly in multiscale modeling simulations. 29 Although some of these simple relationships hold for SAAs, the behavior of these materials can significantly differ from that of pure transition metals.…”

Insights and Activation Energy Surface of the Dehydrogenation of C2HxO Species in Ethanol Oxidation Reaction on Ir(100)

“…[1] In ethanol oxidation reaction (EOR) that takes place in direct ethanol fuel cells [2][3][4][5] or in hydrogen production via ethanol steam reforming, [6][7][8][9][10][11] ethanol dehydrogenation is the first step in the complex reaction network and therefore has been an active area of research. [12,13] Additionally, ethanol dehydrogenation is the first elementary reaction and plays important roles in the synthesis of acetaldehyde, [14][15][16][17][18] ethyl acetate, [19][20][21] butadiene, [22,23] butanol, [24][25][26] polyvinyl alcohol, [27] aromatic alcohols, [28] and bio-fuels. [29,30] Different degree of ethanol dehydrogenation is involved depending on the overall reaction of interest.…”

“…For instance, investigating dehydrogenation is critical for the advancement of energy research toward sustainability and feasible applications [1] . In ethanol oxidation reaction (EOR) that takes place in direct ethanol fuel cells [2–5] or in hydrogen production via ethanol steam reforming, [6–11] ethanol dehydrogenation is the first step in the complex reaction network and therefore has been an active area of research [12,13] . Additionally, ethanol dehydrogenation is the first elementary reaction and plays important roles in the synthesis of acetaldehyde, [14–18] ethyl acetate, [19–21] butadiene, [22,23] butanol, [24–26] polyvinyl alcohol, [27] aromatic alcohols, [28] and bio‐fuels [29,30] .…”