Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra

Abstract

Machine learning has emerged as an invaluable tool in many research areas. In the present work, we harness this power to predict highly accurate molecular infrared spectra with unprecedented computational efficiency. To account for vibrational anharmonic and dynamical effects -- typically neglected by conventional quantum chemistry approaches -- we base our machine learning strategy on ab initio molecular dynamics simulations. While these simulations are usually extremely time consuming even for small molecules, we overcome these limitations by leveraging the power of a variety of machine learning techniques, not only accelerating simulations by several orders of magnitude, but also greatly extending the size of systems that can be treated. To this end, we develop a molecular dipole moment model based on environment dependent neural network charges and combine it with the neural network potentials of Behler and Parrinello. Contrary to the prevalent big data philosophy, we are able to obtain very accurate machine learning models for the prediction of infrared spectra based on only a few hundreds of electronic structure reference points. This is made possible through the introduction of a fully automated sampling scheme and the use of molecular forces during neural network potential training. We demonstrate the power of our machine learning approach by applying it to model the infrared spectra of a methanol molecule, n-alkanes containing up to 200 atoms and the protonated alanine tripeptide, which at the same time represents the first application of machine learning techniques to simulate the dynamics of a peptide. In all these case studies we find excellent agreement between the infrared spectra predicted via machine learning models and the respective theoretical and experimental spectra.

12 pages, 9 figures

References in corpus (8)

• The NumPy array: a structure for efficient numerical computation
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Neural networks for the prediction organic chemistry reactions
• A general method to describe intersystem crossing dynamics in trajectory surface hopping
• The Many-Body Expansion Combined with Neural Networks
• 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 (133)

• Machine learning and the physical sciences
• SchNet - a deep learning architecture for molecules and materials
• Machine Learning Force Fields
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Machine learning for molecular simulation
• Less is more: sampling chemical space with active learning
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• Physics-inspired structural representations for molecules and materials
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Machine learning for electronically excited states of molecules
• The Phase Diagram of a Deep Potential Water Model
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• Autonomous discovery in the chemical sciences part I: Progress
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Machine learning enables long time scale molecular photodynamics simulations
• Inverse design of 3d molecular structures with conditional generative neural networks
• Perspective on integrating machine learning into computational chemistry and materials science
• On the Completeness of Atomic Structure Representations
• Committee neural network potentials control generalization errors and enable active learning
• Inclusion of machine learning kernel ridge regression potential energy surfaces in on-the-fly nonadiabatic molecular dynamics simulation
• Atom-Density Representations for Machine Learning
• Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems
• Deep neural network for the dielectric response of insulators
• QM7-X: A comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
• Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• How to validate machine-learned interatomic potentials
• Machine-Learning X-ray Absorption Spectra to Quantitative Accuracy
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Operators in Machine Learning: Response Properties in Chemical Space
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Automated discovery of a robust interatomic potential for aluminum
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• Using Gaussian Process Regression to Simulate the Vibrational Raman Spectra of Molecular Crystals
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
• Metadynamics for Training Neural Network Model Chemistries: a Competitive Assessment
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials
• Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
• Universal Machine Learning for the Response of Atomistic Systems to External Fields
• Measuring surface charge: why experimental characterization and molecular modeling should be coupled
• Regression-clustering for Improved Accuracy and Training Cost with Molecular-Orbital-Based Machine Learning
• Neural networks and kernel ridge regression for excited states dynamics of CH${}_2$NH${}_2^{+}$: From single-state to multi-state representations and multi-property machine learning models
• Physically inspired deep learning of molecular excitations and photoemission spectra
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Symmetry-Adapted High Dimensional Neural Network Representation of Electronic Friction Tensor of Adsorbates on Metals
• Machine learning and excited-state molecular dynamics
• Roaming leads to amino acid photodamage: A deep learning study of tyrosine
• Permutationally Invariant, Reproducing Kernel-Based Potential Energy Surfaces for Polyatomic Molecules: From Formaldehyde to Acetone
• Simulations meet Machine Learning in Structural Biology
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Dynamical Strengthening of Covalent and Non-Covalent Molecular Interactions by Nuclear Quantum Effects at Finite Temperature
• Spectroscopy from Machine Learning by Accurately Representing the Atomic Polar Tensor
• Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
• Transfer learning for chemically accurate interatomic neural network potentials
• Fast Neural Network Approach for Direct Covariant Forces Prediction in Complex Multi-Element Extended Systems
• Closing the gap between theory and experiment for lithium manganese oxide spinels using a high-dimensional neural network potential
• Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
• Machine-learning prediction of infrared spectra of interstellar polycyclic aromatic hydrocarbons
• Infrared spectra at coupled cluster accuracy from neural network representations
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments
• Transferability of neural network potentials for varying stoichiometry: phonons and thermal conductivity of Mn${}_x$Ge${}_y$ compounds
• Fully First-Principles Surface Spectroscopy with Machine Learning
• Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer
• Hydration free energies from kernel-based machine learning: Compound-database bias
• Machine learning quantum mechanics: solving quantum mechanics problems using radial basis function networks
• Transferability of machine learning potentials: Protonated water neural network potential applied to the protonated water hexamer
• Tensorial properties via the neuroevolution potential framework: Fast simulation of infrared and Raman spectra
• Thermally Averaged Magnetic Anisotropy Tensors via Machine Learning Based on Gaussian Moments
• Combining quantum mechanics and machine-learning calculations for anharmonic corrections to vibrational frequencies
• Accurate Molecular-Orbital-Based Machine Learning Energies via Unsupervised Clustering of Chemical Space
• High-dimensional neural network potentials for accurate vibrational frequencies: The formic acid dimer benchmark
• Atomistic structure search using local surrogate mode
• Size and Temperature Transferability of Direct and Local Deep Neural Networks for Atomic Forces
• Computational Infrared Spectroscopy of 958 Phosphorus-bearing Molecules
• Reducing the cost of neural network potential generation for reactive molecular systems
• Unified Deep Learning Framework for Many-Body Quantum Chemistry via Green's Functions
• Infrared spectra of neutral polycyclic aromatic hydrocarbons by machine learning
• A machine learning potential for simulating infrared spectra of nanosilicate clusters
• Optimized Multifidelity Machine Learning for Quantum Chemistry
• Efficient Composite Infrared Spectroscopy: Combining the Doubly-Harmonic Approximation with Machine Learning Potentials
• Four-Dimensional-Spacetime Atomistic Artificial Intelligence Models
• Training Algorithm Matters for the Performance of Neural Network Potential: A Case Study of Adam and the Kalman Filter Optimizers
• Neural network approach for a rapid prediction of metal-supported borophene properties
• Mean-Field Density Matrix Decompositions
• A chemical bond-based machine learning model for dipole moment: Application to dielectric properties of liquid methanol and ethanol
• Generating candidates in global optimization algorithms using complementary energy landscapes
• Physics-informed active learning for accelerating quantum chemical simulations
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights
• Accelerated Bayesian Inference for Molecular Simulations using Local Gaussian Process Surrogate Models
• Machine Learning interpretation of the correlation between infrared emission features of interstellar polycyclic aromatic hydrocarbons
• Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches
• Machine learning potentials for complex aqueous systems made simple
• Does Hessian Data Improve the Performance of Machine Learning Potentials?
• IR Spectroscopy of Carboxylate-Passivated Semiconducting Nanocrystals: Simulation and Experiment
• Farthest Point Sampling in Property Designated Chemical Feature Space as a General Strategy for Enhancing the Machine Learning Model Performance for Small Scale Chemical Dataset
• A combined on-the-fly/interpolation procedure for evaluating energy values needed in molecular simulations
• Machine learning at the atomic-scale
• Global Optimization via Optimal Decision Trees
• Tell machine learning potentials what they are needed for: Simulation-oriented training exemplified for glycine
• Non-rotational mechanism of polarization in alcohols
• Compressing physical properties of atomic species for improving predictive chemistry
• Neural Network Approach for Predicting Infrared Spectra from 3D Molecular Structure
• Efficient ensemble uncertainty estimation in Gaussian Processes Regression
• Optical line shapes of color centers in solids from classical autocorrelation functions
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• Electronic Descriptors for Supervised Spectroscopic Predictions
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Accelerating structure search using atomistic graph-based classifiers
• Multi-head committees enable direct uncertainty prediction for atomistic foundation models
• Evolutionary Monte Carlo of QM properties in chemical space: Electrolyte design
• 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
• Machine learning for accelerated bandgap prediction in strain-engineered quaternary III-V semiconductors
• Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
• The Homunculus Brain and Categorical Logic
• Probing the Temporal Response of Liquid Water to a THz Pump Pulse Using Machine Learning-Accelerated Non-Equilibrium Molecular Dynamics
• Atomistic Global Optimization X: A Python package for optimization of atomistic structures
• Anharmonic infrared spectra of cationic pyrene and superhydrogenated derivatives
• Towards accurate predictions of bond-selective fluorescence spectra
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• Active learning of potential-energy surfaces of weakly-bound complexes with regression-tree ensembles
• Learning Atomic Multipoles: Prediction of the Electrostatic Potential with Equivariant Graph Neural Networks
• Active Learning of a Neural Network Potential for Large-Scale Atomistic Simulations of Polymer Electrolyte Membranes