Physics-inspired structural representations for molecules and materials

Abstract

The first step in the construction of a regression model or a data-driven analysis, aiming to predict or elucidate the relationship between the atomic scale structure of matter and its properties, involves transforming the Cartesian coordinates of the atoms into a suitable representation. The development of atomic-scale representations has played, and continues to play, a central role in the success of machine-learning methods for chemistry and materials science. This review summarizes the current understanding of the nature and characteristics of the most commonly used structural and chemical descriptions of atomistic structures, highlighting the deep underlying connections between different frameworks, and the ideas that lead to computationally efficient and universally applicable models. It emphasizes the link between properties, structures, their physical chemistry and their mathematical description, provides examples of recent applications to a diverse set of chemical and materials science problems, and outlines the open questions and the most promising research directions in the field.

References in corpus (115)

• 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
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Perspective on density functional theory
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Machine Learning Force Fields
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Ab initio Random Structure Searching
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine learning prediction errors better than DFT accuracy
• Machine-learning based interatomic potential for amorphous carbon
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Nearsightedness of Electronic Matter
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• Nuclear quantum effects enter the mainstream
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Machine learning for electronically excited states of molecules
• Insightful classification of crystal structures using deep learning
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• FCHL revisited: faster and more accurate quantum machine learning
• Alchemical and structural distribution based representation for improved QML
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Shortcomings of the Bond Orientational Order Parameters for the Analysis of Disordered Particulate Matter
• Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints
• Crystal structure prediction using the Minima Hopping method
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
• Chemical Shifts in Molecular Solids by Machine Learning
• An Accurate and Transferable Machine Learning Potential for Carbon
• A Transferable Machine-Learning Model of the Electron Density
• A neural network interatomic potential for the phase change material GeTe
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• De novo exploration and self-guided learning of potential-energy surfaces
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• Data-driven learning of total and local energies in elemental boron
• Extending the Accuracy of the SNAP Interatomic Potential Form
• How to quantify energy landscapes of solids
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• A learning scheme to predict atomic forces and accelerate materials simulations
• On the Completeness of Atomic Structure Representations
• Machine learning with force-field inspired descriptors for materials: fast screening and mapping energy landscape
• Atom-Density Representations for Machine Learning
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Entropy based fingerprint for local crystalline order
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Evidence for supercritical behavior of high-pressure liquid hydrogen
• Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
• Representing molecule-surface interactions with symmetry-adapted neural networks
• Efficient nonparametric $n$-body force fields from machine learning
• Deep neural network for the dielectric response of insulators
• Learning the electronic density of states in condensed matter
• Metrics for measuring distances in configuration spaces
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• Predicting polymorphism in molecular crystals using orientational entropy
• Transferable atomic multipole machine learning models for small organic molecules
• A fingerprint based metric for measuring similarities of crystalline structures
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Operators in Machine Learning: Response Properties in Chemical Space
• Atomic cluster expansion of scalar, vectorial and tensorial properties and including magnetism and charge transfer
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Solid-liquid interface free energy through metadynamics simulations
• Machine learning determination of atomic dynamics at grain boundaries
• On the representation of many-body interactions in water
• 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
• Machine learning driven simulated deposition of carbon films: from low-density to diamondlike amorphous carbon
• Efficient Langevin Simulation of Coupled Classical Fields and Fermions
• Graph similarity drives zeolite diffusionless transformations and intergrowth
• Recognizing molecular patterns by machine learning: an agnostic structural definition of the hydrogen bond
• Chemical diversity in molecular orbital energy predictions with kernel ridge regression
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Navigating at Will on the Water Phase Diagram
• Equation of state of fluid methane from first principles with machine learning potentials
• Recognizing Local and Global Structural Motifs at the Atomic Scale
• A Bayesian approach to NMR crystal structure determination
• Mathematical surprises and Dirac's formalism in quantum mechanics
• Machine Learning of Free Energies in Chemical Compound Space Using Ensemble Representations: Reaching Experimental Uncertainty for Solvation
• Extensive deep neural networks for transferring small scale learning to large scale systems
• A local order metric for condensed phase environments
• Inexpensive modelling of quantum dynamics using path integral generalized Langevin equation thermostats
• Modeling lithium-ion solid-state electrolytes with a pinball model
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• Quantifying Chemical Structure and Atomic Energies in Amorphous Silicon Networks
• Efficient implementation of atom-density representations
• Comment on "Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning"
• An assessment of the structural resolution of various fingerprints commonly used in machine learning
• Solvent Fluctuations and Nuclear Quantum Effects Modulate the Molecular Hyperpolarizability of Water
• Generalized convex hull construction for materials discovery
• A New Kind of Atlas of Zeolite Building Blocks
• Block bond-order potential as a convergent moments-based method
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• Predicting the phase diagram of titanium dioxide with random search and pattern recognition
• Learning from the Density to Correct Total Energy and Forces in First Principle Simulations
• Permutation-invariant distance between atomic configurations
• Resolution limit of data-driven coarse-grained models spanning chemical space
• Wasserstein metric for improved QML with adjacency matrix representations
• Learning on-top: regressing the on-top pair density for real-space visualization of electron correlation
• The Conformational Space of a Flexible Amino Acid at Metallic Surfaces

Cited by in corpus (103)

• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Quantum Machine Learning for Chemistry and Physics
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• How to validate machine-learned interatomic potentials
• Ab-initio quantum chemistry with neural-network wavefunctions
• Ultra-fast interpretable machine-learning potentials
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Ephemeral data derived potentials for random structure search
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• Anisotropic and high thermal conductivity in monolayer quasi-hexagonal fullerene: A comparative study against bulk phase fullerene
• Universal Machine Learning for the Response of Atomistic Systems to External Fields
• Interatomic potentials: Achievements and challenges
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• Examination of computed aluminum grain boundary structures and interface energies that span the 5D space of crystallographic character
• Equivariant analytical mapping of first principles Hamiltonians to accurate and transferable materials models
• Enhanced Sampling in the Age of Machine Learning: Algorithms and Applications
• Quantum dynamics using path integral coarse-graining
• Lifelong Machine Learning Potentials
• Multiscale reweighted stochastic embedding (MRSE): Deep learning of collective variables for enhanced sampling
• Toward Accurate Interpretable Predictions of Materials Properties within Transformer Language Models
• Developments and Further Applications of Ephemeral Data Derived Potentials
• Imaginary components of out-of-time correlators and information scrambling for navigating the learning landscape of a quantum machine learning model
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Tensor-reduced atomic density representations
• Machine learning many-body potentials for colloidal systems
• Exploring the robust extrapolation of high-dimensional machine learning potentials
• E(n)-Equivariant Cartesian Tensor Passing Potential
• Advances in modeling complex materials: The rise of neuroevolution potentials
• Multilayer atomic cluster expansion for semi-local interactions
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• A spectral-neighbour representation for vector fields: machine-learning potentials including spin
• Predicting the Charge Density Response in Metal Electrodes
• Detecting dynamic domains and local fluctuations in complex molecular systems via timelapse neighbors shuffling
• Machine-learning effective many-body potentials for anisotropic particles using orientation-dependent symmetry functions
• Completeness of Atomic Structure Representations
• Navigating chemical reaction space with a steering wheel
• UV-Visible Absorption Spectra of Solvated Molecules by Quantum Chemical Machine Learning
• Indirect Learning of Interatomic Potentials for Accelerated Materials Simulations
• Atomistic structure search using local surrogate mode
• Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments
• Describe, Transform, Machine Learning: Feature Engineering for Grain Boundaries and Other Variable-Sized Atom Clusters
• 3DReact: Geometric deep learning for chemical reactions
• Quantifying Disorder One Atom at a Time Using an Interpretable Graph Neural Network Paradigm
• Optimal radial basis for density-based atomic representations
• Kernel based quantum machine learning at record rate : Many-body distribution functionals as compact representations
• Combining the D3 dispersion correction with the neuroevolution machine-learned potential
• SCINE -- Software for Chemical Interaction Networks
• SPA${}^{\mathrm{H}}$M: the Spectrum of Approximated Hamiltonian Matrices representations
• Quantum chemical roots of machine-learning molecular similarity descriptors
• Ranking the Synthesizability of Hypothetical Zeolites with the Sorting Hat
• Decoding Structure-Spectrum Relationships with Physically Organized Latent Spaces
• Automatic feature selection and weighting in molecular systems using Differentiable Information Imbalance
• Efficient Composite Infrared Spectroscopy: Combining the Doubly-Harmonic Approximation with Machine Learning Potentials
• Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
• Probing the effects of broken symmetries in machine learning
• Multitask methods for predicting molecular properties from heterogeneous data
• SPA${}^{\mathrm{H}}$M(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations
• Metatensor and metatomic: foundational libraries for interoperable atomistic machine learning
• BIP: Boost Invariant Polynomials for Efficient Jet Tagging
• Adaptive energy reference for machine-learning models of the electronic density of states
• Comment on "Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four body interactions"
• A smooth basis for atomistic machine learning
• Tell machine learning potentials what they are needed for: Simulation-oriented training exemplified for glycine
• Interpolating many-body wave functions for accelerated molecular dynamics on the near-exact electronic surface
• Efficient moment tensor machine-learning interatomic potential for accurate description of defects in Ni-Al Alloys
• Condensed-phase molecular representation to link structure and thermodynamics in molecular dynamics
• Fast proper orthogonal descriptors for many-body interatomic potentials
• Machine learning frontier orbital energies of nanodiamonds
• Stability and distortion of fcc-LaH${}_{10}$ with path-integral molecular dynamics
• Machine learning based modeling of disordered elemental semiconductors: understanding the atomic structure of a-Si and a-C
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• On the Quality of Uncertainty Estimates from Neural Network Potential Ensembles
• A neural network potential with self-trained atomic fingerprints: a test with the mW water potential
• Molecular dynamics-driven global tetra-atomic potential energy surfaces: Application to the AlF dimer
• Self-interaction and transport of solvated electrons in molten salts
• Inversion of the chemical environment representations
• A data driven approach to classify descriptors based on their efficiency in translating noisy trajectories into physically-relevant information
• A Fuzzy Classification Framework to Identify Equivalent Atoms in Complex Materials and Molecules
• HEroBM: a deep equivariant graph neural network for universal backmapping from coarse-grained to all-atom representations
• All-in-one foundational models learning across quantum chemical levels
• Machine Learning S-Wave Scattering Phase Shifts Bypassing the Radial Schrödinger Equation
• Translational eigenstates of He@C${}_{60}$ from four-dimensional \textit{ab initio} Potential Energy Surfaces interpolated using Gaussian Process Regression
• Spectral Operator Representations
• On Simulating Thin-Film Processes at the Atomic Scale Using Machine Learned Force Fields
• A general formalism for machine-learning models based on multipolar-spherical harmonics
• Self-supervised Representations and Node Embedding Graph Neural Networks for Accurate and Multi-scale Analysis of Materials
• Deep-learning atomistic semi-empirical pseudopotential model for nanomaterials
• Representing spherical tensors with scalar-based machine-learning models
• Unified theory of atom-centered representations and message-passing machine-learning schemes
• Investigating finite-size effects in molecular dynamics simulations of ion diffusion, heat transport, and thermal motion in superionic materials
• Resolving the Body-Order Paradox of Machine Learning Interatomic Potentials
• Convergence of Body-Orders in Linear Atomic Cluster Expansions
• A critical assessment of bonding descriptors for predicting materials properties
• Efficient interpolation of molecular properties across chemical compound space with low-dimensional descriptors
• Entropy-based Active Learning of Graph Neural Network Surrogate Models for Materials Properties
• Machine learning of electronic structure and atomistic properties from the external potential
• Compressing local atomic neighbourhood descriptors
• Integer linear programming for unsupervised training set selection in molecular machine learning
• A charge-density machine-learning workflow for computing the infrared spectrum of molecules
• Cyclic random graph models predicting giant molecules in hydrocarbon pyrolysis
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems