Efficient implementation of atom-density representations

Abstract

Physically-motivated and mathematically robust atom-centred representations of molecular structures are key to the success of modern atomistic machine learning (ML) methods. They lie at the foundation of a wide range of methods to predict the properties of both materials and molecules as well as to explore and visualize the chemical compound and configuration space. Recently, it has become clear that many of the most effective representations share a fundamental formal connection: that they can all be expressed as a discretization of N-body correlation functions of the local atom density, suggesting the opportunity of standardizing and, more importantly, optimizing the calculation of such representations. We present an implementation, named librascal, whose modular design lends itself both to developing refinements to the density-based formalism and to rapid prototyping for new developments of rotationally equivariant atomistic representations. As an example, we discuss SOAP features, perhaps the most widely used member of this family of representations, to show how the expansion of the local density can be optimized for any choice of radial basis set. We discuss the representation in the context of a kernel ridge regression model, commonly used with SOAP features, and analyze how the computational effort scales for each of the individual steps of the calculation. By applying data reduction techniques in feature space, we show how to further reduce the total computational cost by at up to a factor of 4 or 5 without affecting the model's symmetry properties and without significantly impacting its accuracy.

References in corpus (40)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• 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
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Identification of slow molecular order parameters for Markov model construction
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine-learning based interatomic potential for amorphous carbon
• Machine learning a general purpose interatomic potential for silicon
• 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
• An Accurate and Transferable Machine Learning Potential for Carbon
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• On the Completeness of Atomic Structure Representations
• Atom-Density Representations for Machine Learning
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Growth Mechanism and Origin of High $s{p}^3$ Content in Tetrahedral Amorphous Carbon
• Accelerated materials property predictions and design using motif-based fingerprints
• 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
• Simple Data and Workflow Management with the signac Framework
• 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
• Operators in Machine Learning: Response Properties in Chemical Space
• Neural network based path collective variables for enhanced sampling of phase transformations
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Accurate representation of formation energies of crystalline alloys with many components
• Equation of state of fluid methane from first principles with machine learning potentials
• Recognizing Local and Global Structural Motifs at the Atomic Scale
• PANNA: Properties from Artificial Neural Network Architectures
• An assessment of the structural resolution of various fingerprints commonly used in machine learning
• Simulating solvation and acidity in complex mixtures with first-principles accuracy: the case of CH${}_3$SO${}_3$H and H${}_2$O${}_2$ in phenol
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• Regularised Atomic Body-Ordered Permutation-Invariant Polynomials for the Construction of Interatomic Potentials
• Associated Legendre Polynomials and Spherical Harmonics Computation for Chemistry Applications

Cited by in corpus (18)

• Physics-inspired structural representations for molecules and materials
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Quantum dynamics using path integral coarse-graining
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Finite-temperature materials modeling from the quantum nuclei to the hot electrons regime
• Optimal radial basis for density-based atomic representations
• Modeling the Ga/As binary system across temperaturesand compositions from first principles
• Quantum chemical roots of machine-learning molecular similarity descriptors
• GPU-Accelerated Approximate Kernel Method for Quantum Machine Learning
• Thermal conductivity of Li${}_3$PS${}_4$ solid electrolytes with ab initio accuracy
• Predicting hot-electron free energies from ground-state data
• Metatensor and metatomic: foundational libraries for interoperable atomistic machine learning
• A smooth basis for atomistic machine learning
• Comment on "Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four body interactions"
• Self-interaction and transport of solvated electrons in molten salts
• Machine learning model for efficient nonthermal tuning of the charge density wave in monolayer NbSe${}_2$
• Compressing local atomic neighbourhood descriptors