Machine Learning for Exploring Small Polaron Configurational Space
arXiv:2202.01042 · doi:10.1038/s41524-022-00805-8
Abstract
Polaron defects are ubiquitous in materials and play an important role in many processes involving carrier mobility, charge transfer and surface reactivity. Determining the spatial distribution of small polarons is essential to understand materials properties and functionalities. This requires an exploration of the configurational space, which is computationally demanding when using standard first principles methods, and technically prohibitive for many-polaron systems. Here, we propose a machine-learning (ML) accelerated search that compares the energy stability of different polaron patterns and determines the ground state configuration. The kernel-regression based ML model is trained on databases generated by density functional theory (DFT) calculations on a minimal set of initial polaron patterns, obtained by using either molecular dynamics simulations or a random sampling approach. To establish an efficient mapping between training data and configuration stability we designed simple descriptors that model the interactions among polarons and charged point defects. The proposed DFT+ML protocol is used here to explore millions of polaron configurations for two different systems, oxygen defective rutile TiO(110) and Nb-doped SrTiO(001). Our data shows that the ML-aided search correctly individuates the ground-state polaron patterns, proposes polaronic configurations not visited in the training and can be used to efficiently determine the optimal distribution of polarons at any charge concentration.
References in corpus (25)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- The NumPy array: a structure for efficient numerical computation
- Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
- On-the-fly machine learning force field generation: Application to melting points
- A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
- A direct view at excess electrons in TiO rutile and anatase
- SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
- Tunable polaronic conduction in anatase TiO2
- Charge Localization Dynamics induced by Oxygen Vacancies on the Titania TiO(110) Surface
- A Computational Framework for Automation of Point Defect Calculations
- Electron-phonon interaction and charge carrier mass enhancement in SrTiO3
- Perspective: Exciton polarons in two-dimensional hybrid metal-halide perovskites
- Representing molecule-surface interactions with symmetry-adapted neural networks
- Ab initio theory of polarons: formalism and applications
- Polarons from first principles, without supercells
- Interplay between adsorbates and polarons: CO on rutile TiO(110)
- Coexistence of trapped and free excess electrons in SrTiO3
- Formation and dynamics of small polarons on the rutile TiO(110) surface
- The effect of intrinsic point defects on ferroelectric polarization behavior of SrTiO
- Mobility of Holstein polaron: an unbiased approach
- Predicting Oxidation and Spin States by High-Dimensional Neural Networks: Applications to Lithium Manganese Oxide Spinels
- Polaron mobility in the "beyond quasiparticles" regime
- Small Polarons in Transition Metal Oxides
- Incipient ferroelectricity: A route towards bulk-terminated SrTiO3
- Does a pristine, unreconstructed SrTiO(001) surface exist?