Accelerating fourth-generation machine learning potentials by quasi-linear scaling particle mesh charge equilibration
Authors:
Preprint
Abstract
Machine learning potentials (MLP) have revolutionized the field of atomistic simulations by describing the atomic interactions with the accuracy of electronic structure methods at a small fraction of the costs. Most current MLPs construct the energy of a system as a sum of atomic energies, which depend on information about the atomic environments provided in form of predefined or learnable feature vectors. If, in addition, non-local phenomena like long-range charge transfer are important, fourth-generation MLPs need to be used, which include a charge equilibration (Qeq) step to take the global structure of the system into account. This Qeq can significantly increase the computational cost and thus can become the computational bottleneck for large systems. In this paper we present a highly efficient formulation of Qeq that does not require the explicit computation of the Coulomb matrix elements resulting in a quasi-linearly scaling method. Moreover, our approach also allows for the efficient calculation of energy derivatives, which explicitly consider the global structure-dependence of the atomic charges as obtained from Qeq. Due to its generality, the method is not restricted to MLPs but can also be applied within a variety of other force fields.Keywords
All Related Versions
This publication has 40 references indexed in Scilit:
- LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scalesComputer Physics Communications, 2022
- Four Generations of High-Dimensional Neural Network PotentialsChemical Reviews, 2021
- Development of Multimodal Machine Learning Potentials: Toward a Physics-Aware Artificial IntelligenceAccounts of Chemical Research, 2021
- Machine Learning Force FieldsChemical Reviews, 2021
- General-Purpose Machine Learning Potentials Capturing Nonlocal Charge TransferAccounts of Chemical Research, 2021
- Machine Learning Interatomic Potentials as Emerging Tools for Materials ScienceAdvanced Materials, 2019
- First Principles Neural Network Potentials for Reactive Simulations of Large Molecular and Condensed SystemsAngewandte Chemie International Edition, 2017
- Constructing high‐dimensional neural network potentials: A tutorial reviewInternational Journal of Quantum Chemistry, 2015
- Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentialsJournal of Computational Physics, 2015
- Parallel multilevel preconditioned conjugate-gradient approach to variable-charge molecular dynamicsComputer Physics Communications, 1997