Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels

Abstract

We present an efficient approach for generating highly accurate molecular potential energy surfaces (PESs) using self-correcting, kernel ridge regression (KRR) based machine learning (ML). We introduce structure-based sampling to automatically assign nuclear configurations from a pre-defined grid to the training and prediction sets, respectively. Accurate high-level \textit{ab initio} energies are required only for the points in the training set, while the energies for the remaining points are provided by the ML model with negligible computational cost. The proposed sampling procedure is shown to be superior to random sampling and also eliminates the need for training several ML models. Self-correcting machine learning has been implemented such that each additional layer corrects errors from the previous layer. The performance of our approach is demonstrated in a case study on a published high-level \textit{ab initio} PES of methyl chloride with 44,819 points. The ML model is trained on sets of different size and then used to predict the energies for tens of thousands of nuclear configurations within seconds. The resulting datasets are utilized in variational calculations of the vibrational energy levels of CH${}_3$Cl. By using both structure-based sampling and self-correction, the size of the training set can be kept small (e.g. 10\% of the points) without any significant loss of accuracy. In \textit{ab initio} rovibrational spectroscopy, it is thus possible to reduce the number of computationally costly electronic structure calculations through structure-based sampling and self-correcting KKR-based machine learning by up to 90\%.

References in corpus (19)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• 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
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Nucleation mechanism for the direct graphite-to-diamond phase transition
• Electronic Spectra from TDDFT and Machine Learning in Chemical Space
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• Ab initio quality neural-network potential for sodium
• Machine Learning Exciton Dynamics
• Transferable atomic multipole machine learning models for small organic molecules
• Efficient non-parametric fitting of potential energy surfaces for polyatomic molecules with Gaussian processes
• A machine learning-based selective sampling procedure for identifying the low energy region in a potential energy surface: a case study on proton conduction in oxides
• Accurate \textit{ab initio} vibrational energies of methyl chloride
• Machine Learning for Atomic Forces in a Crystalline Solid: Transferability to Various Temperatures
• A global \textit{ab initio} dipole moment surface for methyl chloride

Cited by in corpus (50)

• Machine learning for molecular simulation
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• 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
• Machine learning a general purpose interatomic potential for silicon
• Machine learning for electronically excited states of molecules
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Inclusion of machine learning kernel ridge regression potential energy surfaces in on-the-fly nonadiabatic molecular dynamics simulation
• Gaussian Process Regression for Geometry Optimization
• QM7-X: A comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Bayesian machine learning for quantum molecular dynamics
• Gaussian Process Regression for Transition State Search
• Accelerated Computation of Free Energy Profile at ab Initio Quantum Mechanical/Molecular Mechanics Accuracy via a Semi-Empirical Reference Potential. I. Weighted Thermodynamics Perturbation
• MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Machine learning and excited-state molecular dynamics
• Automatically growing global reactive neural network potential energy surfaces: a trajectory free active learning strategy
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Permutationally invariant polynomial regression for energies and gradients, using reverse differentiation, achieves orders of magnitude speed-up with high precision compared to other machine learning methods
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects
• Gaussian process model of 51-dimensional potential energy surface for protonated imidazole dimer
• The MD17 Datasets from the Perspective of Datasets for Gas-Phase "Small" Molecule Potentials
• MLatom software ecosystem for surface hopping dynamics in Python with quantum mechanical and machine learning methods
• Training atomic neural networks using fragment-based data generated in virtual reality
• $\Delta$-Machine Learning to Elevate DFT-based Potentials and a Force Field to the CCSD(T) Level Illustrated for Ethanol
• Energy-conserving molecular dynamics is not energy conserving
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• No Headache for PIPs: A PIP Potential for Aspirin Outperforms Other Machine-Learned Potentials
• Mean-Field Density Matrix Decompositions
• Quantum Gaussian process model of potential energy surface for a polyatomic molecule
• Machine learning forces trained by Gaussian process in liquid states: Transferability to temperature and pressure
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights
• Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches
• A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
• Gradient domain machine learning with composite kernels: improving the accuracy of PES and force fields for large molecules
• Tell machine learning potentials what they are needed for: Simulation-oriented training exemplified for glycine
• Thawed Gaussian wavepacket dynamics with $\Delta$-machine learned potentials
• A simple approach to rotationally invariant machine learning of avector quantity
• Ab initio machine learning in chemical compound space
• Translational eigenstates of He@C${}_{60}$ from four-dimensional \textit{ab initio} Potential Energy Surfaces interpolated using Gaussian Process Regression
• Systematically improved potential energy surfaces via sinNN models and sparse grid sampling
• Efficient interpolation of molecular properties across chemical compound space with low-dimensional descriptors
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• Improving Molecular Force Fields Across Configurational Space by Combining Supervised and Unsupervised Machine Learning
• Active learning of potential-energy surfaces of weakly-bound complexes with regression-tree ensembles
• Interpolation and extrapolation of global potential energy surfaces for polyatomic systems by Gaussian processes with composite kernels
• Integer linear programming for unsupervised training set selection in molecular machine learning