Adaptive Slater Koster Parameters: Crossing Oxidation States with Density Functional Tight Binding

TL;DR

This paper introduces an adaptive approach to Slater-Koster parameters in DFTB, improving electronic structure predictions across oxidation states using machine learning.

Contribution

It presents a novel adaptive scheme for SK parameters based on local environments and machine learning, enhancing DFTB accuracy for transition metal oxides.

Findings

Significant improvement in electronic structure and energetics for Ni and Li systems.

Achieved 95% band-structure accuracy across Ni-O compositions.

Demonstrated smooth variation of SK integrals across oxidation states.

Abstract

We propose to adapt the confined pseudo-atomic orbitals underpinning the precalculated Slater-Koster (SK) interaction tables in Density Functional Tight Binding (DFTB) to local atomic environments. We demonstrate significant improvement in electronic structure and energetics in the application to a partially oxidized Ni surface and Li insertion into graphite, where we assign optimal SK parameters to metal atoms in different oxidation states. Further analysis reveals the smoothness of the SK integrals across the varying oxidation states. Exploiting this, we introduce a site-resolved machine-learning scheme for fully adaptive DFTB. Using atomic descriptors and simple regression architectures already established in the context of machine-learning interatomic potentials, our scheme achieves 95% band-structure accuracy across all Ni-O binary compositions in the Materials Project.