Accurate Deep Learning-aided Density-free Strategy for Many-Body Dispersion-corrected Density Functional Theory

TL;DR

This paper introduces a transferable, density-free deep learning model for many-body dispersion corrections in DFT, reducing computational cost while maintaining high accuracy and broadening applicability.

Contribution

The authors develop a novel DNN-based MBD model that bypasses explicit electron density partitioning, enabling efficient and accurate dispersion corrections in DFT calculations.

Findings

DNN-MBD achieves accuracy comparable to traditional methods.

The model reduces computational cost by avoiding explicit density partitioning.

It extends MBD applicability to force fields and neural network-based methods.

Abstract

Using a Deep Neuronal Network model (DNN) trained on the large ANI-1 data set of small organic molecules, we propose a transferable density-free many-body dispersion model (DNN-MBD). The DNN strategy bypasses the explicit Hirshfeld partitioning of the Kohn-Sham electron density required by MBD models to obtain the atom-in-molecules volumes used by the Tkatchenko-Scheffler polarizability rescaling. The resulting DNN-MBD model is trained with minimal basis iterative Stockholder atomic volumes and, coupled to Density Functional Theory (DFT), exhibits comparable (if not greater) accuracy to other approaches based on different partitioning schemes. Implemented in the Tinker-HP package, the DNN-MBD model decreases the overall computational cost compared to MBD models where the explicit density partitioning is performed. Its coupling with the recently introduced Stochastic formulation of the MBD equations (J. Chem. Theory. Comput., 2022, 18, 3, 1633-1645) enables large routine dispersion-corrected DFT calculations at preserved accuracy. Furthermore, the DNN electron density-free features extend MBD's applicability beyond electronic structure theory within methodologies such as force fields and neural networks.