Machine learning for exploring small polaron configurational space

V. C. Birschitzky, F. Ellinger, U. Diebold, M. Reticcioli, C. Franchini

Faculty of Physics & Center for Computational Materials Science, University of Vienna, 1090 Vienna, Austria
Vienna Doctoral School in Physics, University of Vienna, 1090 Vienna, Austria
Institut für Angewandte Physik, TU Wien, 1040 Wien, Austria
Dipartimento di Fisica e Astronomia, Università di Bologna, 40127 Bologna, Italy

npj Comput. Mater. 8 (2022) 1–9

Polaron defects are ubiquitous in materials and play an important role in many processes involving carrier mobility, charge transfer and surface reactivity. Determining small polarons' spatial distributions is essential to understand materials properties and functionalities. However, the required exploration of the configurational space is computationally demanding when using first principles methods. Here, we propose a machine-learning (ML) accelerated search that determines the ground state polaronic configuration. The ML model is trained on databases of polaron configurations generated by density functional theory (DFT) via molecular dynamics or random sampling. To establish a mapping between configurations and their stability, we designed descriptors modelling the interactions among polarons and charged point defects. We used the DFT+ML protocol to explore the polaron configurational space for two surface-systems, reduced rutile TiO2(110) and Nb-doped SrTiO3(001). The ML-aided search proposes additional polaronic configurations and can be utilized to determine optimal polaron distributions at any charge concentration.

Corresponding author: Cesare Franchini. Reprints also available from Ulrike Diebold (diebold at iap_tuwien_ac_at).

You can download a PDF file of this open-access article from npj Computational Materials or from the IAP/TU Wien web server.