English

Accurate Many-Body Repulsive Potentials for Density-Functional Tight-Binding from Deep Tensor Neural Networks

Chemical Physics 2020-06-19 v1 Computational Physics

Abstract

We combine density-functional tight-binding (DFTB) with deep tensor neural networks (DTNN) to maximize the strengths of both approaches in predicting structural, energetic, and vibrational molecular properties. The DTNN is used to learn a non-linear model for the localized many-body interatomic repulsive energy, which so far has been treated in an atom-pairwise manner in DFTB. Substantially improving upon standard DFTB and DTNN, the resulting DFTB-NNrep_{\sf{rep}} model yields accurate predictions of atomization and isomerization energies, equilibrium geometries, vibrational frequencies and dihedral rotation profiles for a large variety of organic molecules compared to the hybrid DFT-PBE0 functional. Our results highlight the high potential of combining semi-empirical electronic-structure methods with physically-motivated machine learning approaches for predicting localized many-body interactions. We conclude by discussing future advancements of the DFTB-NNrep_{\sf{rep}} approach that could enable chemically accurate electronic-structure calculations for systems with tens of thousands of atoms.

Keywords

Cite

@article{arxiv.2006.10429,
  title  = {Accurate Many-Body Repulsive Potentials for Density-Functional Tight-Binding from Deep Tensor Neural Networks},
  author = {Martin Stöhr and Leonardo Medrano Sandonas and Alexandre Tkatchenko},
  journal= {arXiv preprint arXiv:2006.10429},
  year   = {2020}
}
R2 v1 2026-06-23T16:25:45.819Z