Fortnet, a software package for training Behler-Parrinello neural networks

Abstract

A new, open source, parallel, stand-alone software package (Fortnet) has been developed, which implements Behler-Parrinello neural networks. It covers the entire workflow from feature generation to the evaluation of generated potentials, coupled with higher-level analysis such as the analytic calculation of atomic forces. The functionality of the software package is demonstrated by driving the training for the fitted correction functions of the density functional tight binding (DFTB) method, which are commonly used to compensate the inaccuracies resulting from the DFTB approximations to the Kohn-Sham Hamiltonian. The usual two-body form of those correction functions limits the transferability of the parameterizations between very different structural environments. The recently introduced DFTB+ANN approach strives to lift these limitations by combining DFTB with a near-sighted artificial neural network (ANN). After investigating various approaches, we have found the combination of DFTB with an ANN acting on-top of some baseline correction functions (delta learning) the most promising one. It allowed to introduce many-body corrections on top of two-body parametrizations, while excellent transferability to chemical environments with deviating energetics could be demonstrated.

References in corpus (11)

• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Density-functional tight-binding for beginners
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• A Portable High-Quality Random Number Generator for Lattice Field Theory Simulations
• i-PI: A Python interface for ab initio path integral molecular dynamics simulations
• Efficient Training of ANN Potentials by Including Atomic Forces via Taylor Expansion and Application to Water and a Transition-Metal Oxide
• PANNA: Properties from Artificial Neural Network Architectures

Cited by in corpus (1)

• Hybrid functionals for periodic systems in the density functional tight-binding method