Accurate Computational Prediction of Core-Electron Binding Energies in Carbon-Based Materials: A Machine-Learning Model Combining Density-Functional Theory and GW

Dorothea Golze; Markus Hirvensalo; Patricia Hernández-León; Anja Aarva; Jarkko Etula; Toma Susi; Patrick Rinke; Tomi Laurila; Miguel A Caro

doi:10.1021/acs.chemmater.1c04279

Accurate Computational Prediction of Core-Electron Binding Energies in Carbon-Based Materials: A Machine-Learning Model Combining Density-Functional Theory and GW

Chem Mater. 2022 Jul 26;34(14):6240-6254. doi: 10.1021/acs.chemmater.1c04279. Epub 2022 Jul 13.

Authors

Dorothea Golze^{1

2}, Markus Hirvensalo², Patricia Hernández-León³, Anja Aarva³, Jarkko Etula⁴, Toma Susi⁵, Patrick Rinke², Tomi Laurila^{3

4}, Miguel A Caro³

Affiliations

¹ Faculty of Chemistry and Food Chemistry, Technische Universität Dresden, 01062 Dresden, Germany.
² Department of Applied Physics, Aalto University, 02150 Espoo, Finland.
³ Department of Electrical Engineering and Automation, Aalto University, 02150 Espoo, Finland.
⁴ Department of Chemistry and Materials Science, Aalto University, 02150 Espoo, Finland.
⁵ University of Vienna, Faculty of Physics, Boltzmanngasse 5, 1090 Vienna, Austria.

Abstract

We present a quantitatively accurate machine-learning (ML) model for the computational prediction of core-electron binding energies, from which X-ray photoelectron spectroscopy (XPS) spectra can be readily obtained. Our model combines density functional theory (DFT) with GW and uses kernel ridge regression for the ML predictions. We apply the new approach to disordered materials and small molecules containing carbon, hydrogen, and oxygen and obtain qualitative and quantitative agreement with experiment, resolving spectral features within 0.1 eV of reference experimental spectra. The method only requires the user to provide a structural model for the material under study to obtain an XPS prediction within seconds. Our new tool is freely available online through the XPS Prediction Server.