Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer

Abstract

The goal of the present work is to obtain accurate potential energy surfaces (PES) for high-dimensional molecular systems with a small number of $ab$ $initio$ calculations in a system-agnostic way. We use probabilistic modeling based on Gaussian processes (GPs). We illustrate that it is possible to build an accurate GP model of a 51-dimensional PES based on $5000$ randomly distributed $ab$ $initio$ calculations with a global accuracy of $<0.2$ kcal/mol. Our approach uses GP models with composite kernels designed to enhance the Bayesian information content and represents the global PES as a sum of a full-dimensional GP and several GP models for molecular fragments of lower dimensionality. We demonstrate the potency of these algorithms by constructing the global PES for the protonated imidazole dimer, a molecular system with $19$ atoms. We illustrate that GP models thus constructed can extrapolate the PES from low energies ($<10,000$ cm${}^{-1}$), yielding a PES at high energies ($>20,000$ cm${}^{-1}$). This opens the prospect for new applications of GPs, such as mapping out phase transitions by extrapolation or accelerating Bayesian optimization, for high-dimensional physics and chemistry problems with a restricted number of inputs, i.e. for high-dimensional problems where obtaining training data is very difficult.

arXiv comment24 pages, 5 figures

References in corpus (30)

• Practical Bayesian Optimization of Machine Learning Algorithms
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• 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
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine-learning based interatomic potential for amorphous carbon
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Neural networks for the prediction organic chemistry reactions
• Structure Discovery in Nonparametric Regression through Compositional Kernel Search
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Bayesian optimization for tuning and selecting hybrid-density functionals
• Bayesian Error Estimation in Density Functional Theory
• A learning scheme to predict atomic forces and accelerate materials simulations
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Efficient non-parametric fitting of potential energy surfaces for polyatomic molecules with Gaussian processes
• The Many-Body Expansion Combined with Neural Networks
• Bayesian machine learning for quantum molecular dynamics
• Calculating vibrational spectra with sum of product basis functions without storing full-dimensional vectors or matrices
• Extrapolating quantum observables with machine learning: Inferring multiple phase transitions from properties of a single phase
• Reliable estimation of prediction uncertainty for physico-chemical property models
• Gaussian Process Model for Collision Dynamics of Complex Molecules
• Bayesian optimization for the inverse scattering problem in quantum reaction dynamics
• Optimization of an exchange-correlation density functional for water
• Bayesian optimization for inverse problems in time-dependent quantum dynamics

Cited by in corpus (12)

• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Barrier height prediction by machine learning correction of semiempirical calculations
• Bayesian optimization for inverse problems in time-dependent quantum dynamics
• Four-body singlet potential energy surface for reactions of calcium monofluoride
• Quantum Gaussian process model of potential energy surface for a polyatomic molecule
• The loss of the property of locality of the kernel in high-dimensional Gaussian process regression on the example of the fitting of molecular potential energy surfaces
• Gradient domain machine learning with composite kernels: improving the accuracy of PES and force fields for large molecules
• Transformative Applications of Machine Learning for Chemical Reactions
• MOLPIPx: an end-to-end differentiable package for permutationally invariant polynomials in Python and Rust
• Quantum transfer through small networks coupled to phonons: effects of topology vs phonons
• Neural network ensemble for computing cross sections for rotational transitions in H${}_2$O + H${}_2$O collisions
• Active learning of potential-energy surfaces of weakly-bound complexes with regression-tree ensembles