Application of DFTB and machine learning to evaluate the stability of biomass intermediates on the Rh(111) surface

TL;DR

This study combines DFTB calculations and machine learning to efficiently predict and classify the stability of biomass intermediates adsorbed on Rh(111) surfaces, addressing the challenge of numerous possible species and geometries.

Contribution

It introduces a novel workflow integrating DFTB and ML for rapid stability assessment of biomass intermediates on metal surfaces.

Findings

Achieved a MAE of 0.39 eV in adsorption energy predictions.

Accurately ranked different adsorption geometries.

Developed a data-driven classification scheme for reactions.

Abstract

Biomass compounds adsorbed on surfaces are challenging to study due to the large number of possible species and adsorption geometries. In this work, possible intermediates of erythrose, glyceraldehyde, glycerol and propionic acid are studied on the Rh(111) surface. The intermediates and elementary reactions are generated from first 2 recursions of a recursive bond-breaking algorithm. These structures are used as the input of an unsupervised Mol2Vec algorithm to generate vector descriptors. A data-driven scheme to classify the reactions is developed and adsorption energies are predicted. The lowest mean absolute error (MAE) of our prediction on adsorption energies is 0.39 eV, and the relative ordering of different surface adsorption geometries is relatively accurate. We show that combining geometries from density functional tight-binding (DFTB) calculations with energies from machine-learning predictions provides a novel workflow for rapidly assessing the stability of various molecular geometries on the Rh(111) surface.