Atom-Density Representations for Machine Learning

Abstract

The applications of machine learning techniques to chemistry and materials science become more numerous by the day. The main challenge is to devise representations of atomic systems that are at the same time complete and concise, so as to reduce the number of reference calculations that are needed to predict the properties of different types of materials reliably. This has led to a proliferation of alternative ways to convert an atomic structure into an input for a machine-learning model. We introduce an abstract definition of chemical environments that is based on a smoothed atomic density, using a bra-ket notation to emphasize basis set independence and to highlight the connections with some popular choices of representations for describing atomic systems. The correlations between the spatial distribution of atoms and their chemical identities are computed as inner products between these feature kets, which can be given an explicit representation in terms of the expansion of the atom density on orthogonal basis functions, that is equivalent to the smooth overlap of atomic positions (SOAP) power spectrum, but also in real space, corresponding to $n$-body correlations of the atom density. This formalism lays the foundations for a more systematic tuning of the behavior of the representations, by introducing operators that represent the correlations between structure, composition, and the target properties. It provides a unifying picture of recent developments in the field and indicates a way forward towards more effective and computationally affordable machine-learning schemes for molecules and materials.

References in corpus (19)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Statistical Aspects of Wasserstein Distances
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine-learning based interatomic potential for amorphous carbon
• Nearsightedness of Electronic Matter
• Insightful classification of crystal structures using deep learning
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Alchemical and structural distribution based representation for improved QML
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Chemical Shifts in Molecular Solids by Machine Learning
• A Transferable Machine-Learning Model of the Electron Density
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• Efficient nonparametric $n$-body force fields from machine learning
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements

Cited by in corpus (69)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• Neuroevolution machine learning potentials: Combining high accuracy and low cost in atomistic simulations and application to heat transport
• Physics-inspired structural representations for molecules and materials
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Predicting materials properties without crystal structure: Deep representation learning from stoichiometry
• Machine learning for electronically excited states of molecules
• Machine-learning interatomic potentials for materials science
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Incorporating long-range physics in atomic-scale machine learning
• On the Completeness of Atomic Structure Representations
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Machine-learned multi-system surrogate models for materials prediction
• Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Learning the electronic density of states in condensed matter
• Atomic cluster expansion of scalar, vectorial and tensorial properties and including magnetism and charge transfer
• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Using Gaussian Process Regression to Simulate the Vibrational Raman Spectra of Molecular Crystals
• Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• Band gap prediction for large organic crystal structures with machine learning
• Deep Learning for UV Absorption Spectra with SchNarc: First Steps Towards Transferability in Chemical Compound Space
• Machine learning and excited-state molecular dynamics
• A Bayesian approach to NMR crystal structure determination
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• Efficient implementation of atom-density representations
• Developments and Further Applications of Ephemeral Data Derived Potentials
• On Machine Learning Force Fields for Metallic Nanoparticles
• A New Kind of Atlas of Zeolite Building Blocks
• Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networks
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• Exploring the robust extrapolation of high-dimensional machine learning potentials
• A spectral-neighbour representation for vector fields: machine-learning potentials including spin
• Predicting the Charge Density Response in Metal Electrodes
• Finite-temperature materials modeling from the quantum nuclei to the hot electrons regime
• Completeness of Atomic Structure Representations
• Compact atomic descriptors enable accurate predictions via linear models
• TimeSOAP: Tracking high-dimensional fluctuations in complex molecular systems via time-variations of SOAP spectra
• Relations between angular and Cartesian orientational expansions
• Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments
• Optimal radial basis for density-based atomic representations
• Accuracy of Charge Densities in Electronic Structure Calculations
• Quantum chemical roots of machine-learning molecular similarity descriptors
• Ranking the Synthesizability of Hypothetical Zeolites with the Sorting Hat
• Machine Learning for compositional disorder: A Comparison Between Different Descriptors and Machine Learning Frameworks
• Mean-Field Density Matrix Decompositions
• Spectral Neural Network Potentials for Binary Alloys
• Prediction rigidities for data-driven chemistry
• Comment on "Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four body interactions"
• Cluster-based multidimensional scaling embedding tool for data visualization
• Machine learning based modeling of disordered elemental semiconductors: understanding the atomic structure of a-Si and a-C
• Particle Swarm Based Hyper-Parameter Optimization for Machine Learned Interatomic Potentials
• Embedding quantum statistical excitations in a classical force field
• HEroBM: a deep equivariant graph neural network for universal backmapping from coarse-grained to all-atom representations
• Investigating 3D Atomic Environments for Enhanced QSAR
• Ab initio machine learning in chemical compound space
• Mapping the Structure of Oxygen-Doped Wurtzite Aluminum Nitride Coatings From Ab Initio Random Structure Search and Experiments
• A general formalism for machine-learning models based on multipolar-spherical harmonics
• Unified theory of atom-centered representations and message-passing machine-learning schemes
• Representing spherical tensors with scalar-based machine-learning models
• Machine learning of electronic structure and atomistic properties from the external potential
• Learning electron densities in the condensed phase
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• Simulations of water and hydrophobic hydration using a neural network potential