Bayesian machine learning for quantum molecular dynamics

Krems, Roman V.

doi:10.1039/c9cp01883b

Cited by 103 publications

(139 citation statements)

References 100 publications

(180 reference statements)

Supporting

Mentioning

136

Contrasting

Order By: Relevance

“…Many different techniques have been developed for fitting multi-dimensional PES (for representative examples, see Refs. [1][2][3][4][5][6]). A major thrust of recent research has been to develop approaches for fitting PES of polyatomic systems by machine learning (ML) models .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Interpolation and Extrapolation of Global Potential Energy Surfaces for Polyatomic Systems by Gaussian Processes with Composite Kernels

Dai

Krems

2020

J. Chem. Theory Comput.

Self Cite

View full text Add to dashboard Cite

Gaussian process regression has recently emerged as a powerful, system-agnostic tool for building global potential energy surfaces (PES) of polyatomic molecules. While the accuracy of GP models of PES increases with the number of potential energy points, so does the numerical difficulty of training and evaluating GP models. Here, we demonstrate an approach to improve the accuracy of global PES without increasing the number of energy points. The present work reports four important results. First, we show that the selection of the best kernel function for GP models of PES can be automated using the Bayesian information criterion as a model selection metric.Second, we demonstrate that GP models of PES trained by a small number of energy points can be significantly improved by iteratively increasing the complexity of GP kernels. The composite kernels thus obtained maximize the accuracy of GP models for a given distribution of potential energy points. Third, we show that the accuracy of the GP models of PES with composite kernels can be further improved by varying the training point distributions. Fourth, we show that GP models with composite kernels can be used for physical extrapolation of PES. We illustrate the approach by constructing the six-dimensional PES for H 3 O + . For the interpolation problem, we show that this algorithm produces a global six-dimensional PES for H 3 O + in the energy range between zero and 21, 000 cm −1 with the root mean square error 65.8 cm −1 using only 500 randomly selected ab initio points as input. To illustrate extrapolation, we produce the PES at high energies using the energy points at low energies as input. We show that one can obtain an accurate global fit of the PES extending to 21, 000 cm −1 based on 1500 potential energy points at energies below 10, 000 cm −1 . arXiv:1907.08717v1 [physics.chem-ph]

show abstract

Section: Introductionmentioning

confidence: 99%

“…Using GPs to construct PES for polyatomic systems has several advantages over other methods [6]. First, it has been shown that accurate GP models can be obtained with a much smaller number of potential energy points than required for any other fitting method [21,24].…”

Section: Introductionmentioning

confidence: 99%

Interpolation and Extrapolation of Global Potential Energy Surfaces for Polyatomic Systems by Gaussian Processes with Composite Kernels

Dai

Krems

2020

J. Chem. Theory Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In particular, in chemical physics, as recently shown, datadriven approaches bring a new perspective to solve some of the most delicate problems of the field. [13][14][15][16] In this paper, we present a data-driven approach to dipole moments of diatomic molecules and its relationship with spectroscopic constants. We show that, after compiling the most exhaustive list of dipole moments for diatomics up to date (to the best of our knowledge) into a dataset, it is possible to learn the dipole moment of diatomic molecules based upon atomic and molecular properties with a relative error t5%.…”

Section: Introductionmentioning

confidence: 99%

A data-driven approach to determine dipole moments of diatomic molecules

Liu

Meijer

Pérez‐Ríos

2020

Phys. Chem. Chem. Phys.

View full text Add to dashboard Cite

show abstract

“…A substantial amount of materials data are accumulated in public databases [1][2][3], and machine-learning-based design of materials is increasingly common in recent years [4][5][6]. The problem of materials design is mathematically formulated as a black-box optimization problem, where a large number of candidates are available and the goal is to find the candidate with best target property via a minimum number of observations.…”

Section: Introductionmentioning

confidence: 99%

Data integration for accelerated materials design via preference learning

Sun¹,

Hou²,

Sumita³

et al. 2020

New J. Phys.

View full text Add to dashboard Cite

Machine learning applications in materials science are often hampered by shortage of experimental data. Integration with external datasets from past experiments is a viable way to solve the problem. But complex calibration is often necessary to use the data obtained under different conditions. In this paper, we present a novel calibration-free strategy to enhance the performance of Bayesian optimization with preference learning. The entire learning process is solely based on pairwise comparison of quantities (i.e., higher or lower) in the same dataset, and experimental design can be done without comparing quantities in different datasets. We demonstrate that Bayesian optimization is significantly enhanced via data integration for organic molecules and inorganic solid-state materials. Our method increases the chance that public datasets are reused and may encourage data sharing in various fields of physics.

show abstract

Bayesian machine learning for quantum molecular dynamics

Cited by 103 publications

References 100 publications

Interpolation and Extrapolation of Global Potential Energy Surfaces for Polyatomic Systems by Gaussian Processes with Composite Kernels

Interpolation and Extrapolation of Global Potential Energy Surfaces for Polyatomic Systems by Gaussian Processes with Composite Kernels

A data-driven approach to determine dipole moments of diatomic molecules

Data integration for accelerated materials design via preference learning

Contact Info

Product

Resources

About