Invariant Molecular Representations for Heterogeneous Catalysis.

Catalyst screening is a critical step in the discovery and development of heterogeneous catalysts, which are vital for a wide range of chemical processes. In recent years, computational catalyst screening, primarily through density functional theory (DFT), has gained significant attention as a method for identifying promising catalysts. However, the computation of adsorption energies for all likely chemical intermediates present in complex surface chemistries is computationally intensive and costly due to the expensive nature of these calculations and the intrinsic idiosyncrasies of the methods or data sets used. This study introduces a novel machine learning (ML) method to learn adsorption energies from multiple DFT functionals by using invariant molecular representations (IMRs). To do this, we first extract molecular fingerprints for the reaction intermediates and later use a Siamese-neural-network-based training strategy to learn invariant molecular representations or the IMR across all available functionals. Our Siamese network-based representations demonstrate superior performance in predicting adsorption energies compared with other molecular representations. Notably, when considering mean absolute values of adsorption energies as 0.43 eV (PBE-D3), 0.46 eV (BEEF-vdW), 0.81 eV (RPBE), and 0.37 eV (scan+rVV10), our IMR method has achieved the lowest mean absolute errors (MAEs) of 0.18 0.10, 0.16, and 0.18 eV, respectively. These results emphasize the superior predictive capacity of our Siamese network-based representations. The empirical findings in this study illuminate the efficacy, robustness, and dependability of our proposed ML paradigm in predicting adsorption energies, specifically for propane dehydrogenation on a platinum catalyst surface.

Benchmarking the Accuracy of Density Functional Theory against the Random Phase Approximation for the Ethane Dehydrogenation Network on Pt(111).

The Random Phase Approximation (RPA) is conceptually the most accurate Density Functional Approximation method, able to simultaneously predict both adsorbate and surface energies accurately; however, this work questions its superiority over DFT for catalytic application on hydrocarbon systems. This work uses microkinetic modeling to benchmark the accuracy of DFT functionals against that of RPA for the ethane dehydrogenation reaction on Pt(111). Eight different functionals, with and without dispersion corrections, across the GGA, meta-GGA and hybrid classes are evaluated: PBE, PBE-D3, RPBE, RPBE-D3, BEEF-vdW, SCAN, SCAN-rVV10, and HSE06. We show that PBE and RPBE, without dispersion correction, closely model RPA energies for adsorption, transition states, reaction, and activation energies. Next, RPA fails to describe the gas phase energy as unsaturation and chain-length increases in the hydrocarbon. Finally, we show that RPBE has the best accuracy-to-cost ratio, and RPA is likely not superior to RPBE or BEEF-vdW, which also gives a measure of uncertainty.