Critical assessment of machine-learned repulsive potentials for the Density Functional based Tight-Binding method: a case study for pure silicon

Abstract

We investigate the feasability of improving the semi-empirical density functional based tight-binding method (DFTB) through a general and transferable many-body repulsive potential for pure silicon using a common machine-learning framework. Atomic environments using atom centered symmetry functions fed into flexible high-dimensional neural-networks allow to overcome the limited pair potentials used until now, with the ability to train simultaneously on a large variety of systems. We achieve an improvement on bulk systems, with good performance on energetic, vibrational and structural properties. Contrarily, there are difficulties for clusters due to surface effects. To deepen the discussion, we also put these results into perspective with two fully machine-learned numerical potentials for silicon from the literature. This allows us to identify both the transferability of such approaches together with the impact of narrowing the role of machine-learning models to reproduce only a part of the total energy.

References in corpus (10)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Machine learning a general purpose interatomic potential for silicon
• Density-functional tight-binding for beginners
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• Ab initio quality neural-network potential for sodium
• Building machine learning force fields for nanoclusters
• Semi-Automated Creation of Density Functional Tight Binding Models Through Leveraging Chebyshev Polynomial-based Force Fields
• Towards a simplified description of thermoelectric materials: Accuracy of approximate density functional theory for phonon dispersions

Cited by in corpus (1)

• Enhancing the Accuracy of Density Functional Tight Binding Models Through ChIMES Many-body Interaction Potentials