Atomic-Scale Representation and Statistical Learning of Tensorial Properties

This chapter discusses the importance of incorporating three-dimensional symmetries in the context of statistical learning models geared towards the interpolation of the tensorial properties of atomic-scale structures. We focus on Gaussian process regression, and in particular on the construction of structural representations, and the associated kernel functions, that are endowed with the geometric covariance properties compatible with those of the learning targets. We summarize the general formulation of such a symmetry-adapted Gaussian process regression model, and how it can be implemented based on a scheme that generalizes the popular smooth overlap of atomic positions representation. We give examples of the performance of this framework when learning the polarizability and the ground-state electron density of a molecule.

[1]  P. Popelier,et al.  Multipolar electrostatics based on the Kriging machine learning method: an application to serine , 2014, Journal of Molecular Modeling.

[2]  Li Li,et al.  Bypassing the Kohn-Sham equations with machine learning , 2016, Nature Communications.

[3]  Christopher M Wolverton,et al.  Atomistic calculations and materials informatics: A review , 2017 .

[4]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[5]  M. Ceriotti,et al.  Solvent fluctuations and nuclear quantum effects modulate the molecular hyperpolarizability of water , 2017, 1705.01649.

[6]  Noam Bernstein,et al.  Machine learning unifies the modeling of materials and molecules , 2017, Science Advances.

[7]  Anders S. Christensen,et al.  Operators in quantum machine learning: Response properties in chemical space. , 2018, The Journal of chemical physics.

[8]  Andrea Grisafi,et al.  Symmetry-Adapted Machine Learning for Tensorial Properties of Atomistic Systems. , 2017, Physical review letters.

[9]  John M. Alred,et al.  Machine learning electron density in sulfur crosslinked carbon nanotubes , 2018, Composites Science and Technology.

[10]  Alberto Fabrizio,et al.  Transferable Machine-Learning Model of the Electron Density , 2018, ACS central science.

[11]  Alexander V. Shapeev,et al.  Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials , 2015, Multiscale Model. Simul..

[12]  Zhen Lin,et al.  Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network , 2018, NeurIPS.

[13]  Marco Buongiorno Nardelli,et al.  The AFLOW standard for high-throughput materials science calculations , 2015, 1506.00303.

[14]  A. Stone.  Transformation between cartesian and spherical tensors , 1975 .

[15]  Josh E. Campbell,et al.  Machine learning for the structure–energy–property landscapes of molecular crystals† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc04665k , 2017, Chemical science.

[16]  M. Rupp,et al.  Machine learning of molecular electronic properties in chemical compound space , 2013, 1305.7074.

[17]  Anand Chandrasekaran,et al.  Solving the electronic structure problem with machine learning , 2019, npj Computational Materials.

[18]  Gábor Csányi,et al.  Comparing molecules and solids across structural and alchemical space. , 2015, Physical chemistry chemical physics : PCCP.

[19]  Tristan Bereau,et al.  Transferable Atomic Multipole Machine Learning Models for Small Organic Molecules. , 2015, Journal of chemical theory and computation.

[20]  Joel M. Bowman,et al.  Permutationally invariant potential energy surfaces in high dimensionality , 2009 .

[21]  I. S. Gradshteyn,et al.  Table of Integrals, Series, and Products , 1976 .

[22]  Single-centre expansion of Gaussian basis functions and the angular decomposition of their overlap integrals , 1989 .

[23]  Neil D. Lawrence,et al.  Kernels for Vector-Valued Functions: a Review , 2011, Found. Trends Mach. Learn..

[24]  Christof Hättig,et al.  Optimization of auxiliary basis sets for RI-MP2 and RI-CC2 calculations: Core–valence and quintuple-ζ basis sets for H to Ar and QZVPP basis sets for Li to Kr , 2005 .

[25]  R. Kondor,et al.  Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. , 2009, Physical review letters.

[26]  Michele Parrinello,et al.  Demonstrating the Transferability and the Descriptive Power of Sketch-Map. , 2013, Journal of chemical theory and computation.

[27]  Aldo Glielmo,et al.  Efficient nonparametric n -body force fields from machine learning , 2018, 1801.04823.

[28]  Peter Sollich,et al.  Accurate interatomic force fields via machine learning with covariant kernels , 2016, 1611.03877.

[29]  Yang Yang,et al.  Accurate molecular polarizabilities with coupled cluster theory and machine learning , 2018, Proceedings of the National Academy of Sciences.

[30]  Ulrich Weinert,et al.  Spherical tensor representation , 1980 .

[31]  Zhenwei Li,et al.  Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces. , 2015, Physical review letters.

[32]  Alexandre Tkatchenko,et al.  Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning. , 2017, The Journal of chemical physics.

[33]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.

[34]  Kristin A. Persson,et al.  Commentary: The Materials Project: A materials genome approach to accelerating materials innovation , 2013 .

[35]  R. Kondor,et al.  On representing chemical environments , 2012, 1209.3140.

[36]  Michele Ceriotti,et al.  Atom-density representations for machine learning. , 2018, The Journal of chemical physics.

[37]  E Weinan,et al.  Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics , 2017, Physical review letters.

[38]  Michele Ceriotti,et al.  A Data-Driven Construction of the Periodic Table of the Elements , 2018, 1807.00236.