A Hessian-Based Assessment of Atomic Forces for Training Machine Learning Interatomic Potentials

Abstract

In recent years, many types of machine learning potentials (MLPs) have been introduced, which are able to represent high-dimensional potential-energy surfaces (PES) with close to first-principles accuracy. Most current MLPs rely on atomic energy contributions given as a function of the local chemical environments. Frequently, in addition to total energies also atomic forces are used to construct the potentials, as they provide detailed local information about the PES. Since many systems are too large for electronic structure calculations, obtaining reliable reference forces from smaller subsystems like molecular fragments or clusters can substantially simplify the construction of the training sets. Here, we propose a method to determine structurally converged molecular fragments providing reliable atomic forces based on an analysis of the Hessian. The method, which serves as a locality test and allows to estimate the importance of long-range interactions, is illustrated for a series of molecular model systems and the metal-organic framework MOF-5 as an example for a complex organic-inorganic hybrid material.

arXiv comment15 pages, 13 figures excluding the supporting information, submitted to JCP

References in corpus (20)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Machine learning for molecular simulation
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Machine-learning based interatomic potential for amorphous carbon
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Computational characterization and prediction of metal-organic framework properties
• Incorporating long-range physics in atomic-scale machine learning
• Comparing the Accuracy of High-Dimensional Neural Network Potentials and the Systematic Molecular Fragmentation Method: A Benchmark Study for all-trans Alkanes

Cited by in corpus (2)

• Tutorial: How to Train a Neural Network Potential
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules