Learning to Use the Force: Fitting Repulsive Potentials in Density-Functional Tight-Binding with Gaussian Process Regression, Theoretical and Computational Chemistry, ChemRxiv

The Density-Functional Tight Binding (DFTB) method is a popular semiempirical approximation to Density Functional Theory (DFT). In many cases, DFTB can provide comparable accuracy to DFT at a fraction of the cost, enabling simulations on length- and time-scales that are unfeasible with first principles DFT. At the same time (and in contrast to empirical interatomic potentials and force-fields), DFTB still offers direct access to electronic properties such as the band-structure. These advantages come at the cost of introducing empirical parameters to the method, leading to a reduced transferability compared to true first-principle approaches. Consequently, it would be very useful if the parameter-sets could be routinely adjusted for a given project. While fairly robust and transferable parameterization workflows exist for the electronic structure part of DFTB, the so-called repulsive potential Vrep poses a major challenge. In this paper we propose a machine-learning (ML) approach to fitting Vrep, using Gaussian Process Regression (GPR). The use of GPR circumvents the need for non-linear or global parameter optimization, while at the same time offering arbitrary flexibility in terms of the functional form. We also show that the proposed method can be applied to multiple elements at once, by fitting repulsive potentials for organic molecules containing carbon, hydrogen and oxygen. Overall, the new approach removes focus from the choice of functional form and parameterization procedure, in favour of a data-driven philosophy.

Density-Functional Tight-Binding (DFTB) as fast approximate DFT

Neural network potentials for chemistry: concepts, applications

PDF) Kernel Charge Equilibration: Efficient and Accurate Prediction

Benchmarks of the density functional tight-binding method for

Quantum machine learning for chemistry and physics - Chemical Society Reviews (RSC Publishing) DOI:10.1039/D2CS00203E

Recent advances and applications of machine learning in solid-state materials science

Interfacing q-AQUA with a Polarizable Force Field: The Best of

PDF) Systematic Comparison of Experimental Crystallographic Geometries and Gas-Phase Computed Conformers for Torsion Preferences

Spectroscopic Calibration of Modern Density Functional Methods Using [CuCl4]2

Density-functional tight-binding for beginners - ScienceDirect

PDF) Kernel Charge Equilibration: Efficient and Accurate Prediction of Molecular Dipole Moments with a Machine-Learning Enhanced Electron Density Model

Obtaining Robust Density Functional Tight Binding Parameters for Solids Across the Periodic Table, Theoretical and Computational Chemistry, ChemRxiv

PDF) DFT Exchange: Sharing Perspectives on the Workhorse of

PDF) DFT Exchange: Sharing Perspectives on the Workhorse of

PDF) Semiempirical Hamiltonians learned from data can have