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 (5)

• Ab initio theory and modeling of 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
• 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

Cited by in corpus (32)

• 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
• 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
• Homogeneous ice nucleation in an ab initio machine learning model of water
• 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
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• Efficient Composite Infrared Spectroscopy: Combining the Doubly-Harmonic Approximation with Machine Learning Potentials
• 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