Raman Spectrum and Polarizability of Liquid Water from Deep Neural Networks

Abstract

We introduce a scheme based on machine learning and deep neural networks to model the environmental dependence of the electronic polarizability in insulating materials. Application to liquid water shows that training the network with a relatively small number of molecular configurations is sufficient to predict the polarizability of arbitrary liquid configurations in close agreement with ab initio density functional theory calculations. In combination with a neural network representation of the interatomic potential energy surface,the scheme allows us to calculate the Raman spectra along 2-nanosecond classical trajectories at different temperatures for H2O and D2O. The vast gains in efficiency provided by the machine learning approach enable longer trajectories and larger system sizes relative to ab initio methods, reducing the statistical error and improving the resolution of the low-frequency Raman spectra. Decomposing the spectra into intramolecular and intermolecular contributions elucidates the mechanisms behind the temperature dependence of the low-frequency and stretch modes.

References in corpus (22)

• Phonons and related properties of extended systems from density-functional perturbation theory
• Maximally-localized generalized Wannier functions for composite energy bands
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• A First-Principles Approach to Insulators in Finite Electric Fields
• Ab initio theory and modeling of water
• Why does hydronium diffuse faster than hydroxide in liquid water?
• On the accuracy of the MB-pol many-body potential for water: Interaction energies, vibrational frequencies, and classical thermodynamic and dynamical properties from clusters to liquid water and ice
• Deep Potential: a general representation of a many-body potential energy surface
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• Real-space approach to calculation of electric polarization and dielectric constants
• Using Gaussian Process Regression to Simulate the Vibrational Raman Spectra of Molecular Crystals
• On the Consistency of Approximate Quantum Dynamics Simulation Methods for Vibrational Spectra in the Condensed Phase
• Quantum fluctuations and isotope effects in ab initio descriptions of water
• Water: one molecule, two surfaces, one mistake
• Critical role of quantum dynamical effects in the Raman spectroscopy of liquid water

Cited by in corpus (37)

• Machine Learning Force Fields
• DeePMD-kit v2: A software package for Deep Potential models
• The Phase Diagram of a Deep Potential Water Model
• Intelligent Computing: The Latest Advances, Challenges and Future
• 86 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracy
• A deep potential model with long-range electrostatic interactions
• Deep Potentials for Materials Science
• Perspective on integrating machine learning into computational chemistry and materials science
• Deep neural network for the dielectric response of insulators
• Homogeneous ice nucleation in an ab initio machine learning model of water
• Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
• Universal Machine Learning for the Response of Atomistic Systems to External Fields
• Heat transport in liquid water from first-principles and deep-neural-network simulations
• Viscosity in water from first-principles and deep-neural-network simulations
• Predicting tensorial molecular properties with equivariant machine-learning models
• Molecular dynamics simulation with finite electric fields using Perturbed Neural Network Potentials
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Fully First-Principles Surface Spectroscopy with Machine Learning
• E(n)-Equivariant Cartesian Tensor Passing Potential
• Tensorial properties via the neuroevolution potential framework: Fast simulation of infrared and Raman spectra
• Revealing the molecular structures of a-Al2O3(0001)-water interface by machine learning based computational vibrational spectroscopy
• High-dimensional neural network potentials for accurate vibrational frequencies: The formic acid dimer benchmark
• Two-component dynamics and the liquid-like to gas-like crossover in supercritical water
• Efficient Composite Infrared Spectroscopy: Combining the Doubly-Harmonic Approximation with Machine Learning Potentials
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• A chemical bond-based machine learning model for dipole moment: Application to dielectric properties of liquid methanol and ethanol
• Thermal disorder and phonon softening in the ferroelectric phase transition of lead titanate
• Enhancing the formation of ionic defects to study the ice Ih/XI transition with molecular dynamics simulations
• An equivariant neural operator for developing nonlocal tensorial constitutive models
• Exciting DeePMD: Learning excited state energies, forces, and non-adiabatic couplings
• Untangling the Raman spectrum of cubic and tetragonal BaZrO${}_3$
• Aqueous Solution Chemistry In Silico and the Role of Data Driven Approaches
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
• A Bond-Based Machine Learning Model for Molecular Polarizabilities and A Priori Raman Spectra
• Transferability of the chemical bond-based machine learning model for dipole moment: the GHz to THz dielectric properties of liquid propylene glycol and polypropylene glycol
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems