Tensorial properties via the neuroevolution potential framework: Fast simulation of infrared and Raman spectra

Abstract

Infrared and Raman spectroscopy are widely used for the characterization of gases, liquids, and solids, as the spectra contain a wealth of information concerning in particular the dynamics of these systems. Atomic scale simulations can be used to predict such spectra but are often severely limited due to high computational cost or the need for strong approximations that limit application range and reliability. Here, we introduce a machine learning (ML) accelerated approach that addresses these shortcomings and provides a significant performance boost in terms of data and computational efficiency compared to earlier ML schemes. To this end, we generalize the neuroevolution potential approach to enable the prediction of rank one and two tensors to obtain the tensorial neuroevolution potential (TNEP) scheme. We apply the resulting framework to construct models for the dipole moment, polarizability, and susceptibility of molecules, liquids, and solids, and show that our approach compares favorably with several ML models from the literature with respect to accuracy and computational efficiency. Finally, we demonstrate the application of the TNEP approach to the prediction of infrared and Raman spectra of liquid water, a molecule (PTAF-), and a prototypical perovskite with strong anharmonicity (BaZrO3). The TNEP approach is implemented in the free and open source software package GPUMD, which makes this methodology readily available to the scientific community.

arXiv comment11 pages, 6 figures

References in corpus (30)

• Van der Waals Density Functional for General Geometries
• CP2K: An Electronic Structure and Molecular Dynamics Software Package -- Quickstep: Efficient and Accurate Electronic Structure Calculations
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• A beginner's guide to the modern theory of polarization
• An exchange functional that tests the robustness of the plasmon description of the van der Waals density functional
• Accounting for electronic polarization in nonpolarizable force fields
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• A combined theoretical and experimental study of the low temperature properties of BaZrO3
• Deep neural network for the dielectric response of insulators
• Raman Spectrum and Polarizability of Liquid Water from Deep Neural Networks
• Improving the accuracy of the neuroevolution machine learning potential for multi-component systems
• The Interplay of Structure and Dynamics in the Raman Spectrum of Liquid Water over the Full Frequency and Temperature Range
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
• Limits of the phonon quasi-particle picture at the cubic-to-tetragonal phase transition in halide perovskites
• Inexpensive modelling of quantum dynamics using path integral generalized Langevin equation thermostats
• Lattice dynamics and Raman spectrum of BaZrO3 single crystals
• On the Calculation of IR Spectra with a Fully Polarizable QM/MM Approach Based on Fluctuating Charges and Fluctuating Dipoles
• First-principles study of the infrared spectrum in liquid water from a systematically improved description of H-bond network
• Infrared spectra at coupled cluster accuracy from neural network representations
• Machine Learning for Polaritonic Chemistry: Accessing chemical kinetics
• High-dimensional neural network potentials for accurate vibrational frequencies: The formic acid dimer benchmark
• The dielectric response of rock-salt crystals at finite temperatures from first principles
• Understanding correlations in BaZrO3:Structure and dynamics on the nano-scale
• Anharmonicity of the antiferrodistortive soft mode in barium zirconate BaZrO${}_3$

Cited by in corpus (9)

• E(n)-Equivariant Cartesian Tensor Passing Potential
• Advances in modeling complex materials: The rise of neuroevolution potentials
• Machine Learning for Polaritonic Chemistry: Accessing chemical kinetics
• Highly efficient path-integral molecular dynamics simulations with GPUMD using neuroevolution potentials: Case studies on thermal properties of materials
• Efficient Composite Infrared Spectroscopy: Combining the Doubly-Harmonic Approximation with Machine Learning Potentials
• Untangling the Raman spectrum of cubic and tetragonal BaZrO${}_3$
• Optical line shapes of color centers in solids from classical autocorrelation functions
• A simple approach to rotationally invariant machine learning of avector quantity
• A Bond-Based Machine Learning Model for Molecular Polarizabilities and A Priori Raman Spectra