Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems

Abstract

Statistical learning methods show great promise in providing an accurate prediction of materials and molecular properties, while minimizing the need for computationally demanding electronic structure calculations. The accuracy and transferability of these models are increased significantly by encoding into the learning procedure the fundamental symmetries of rotational and permutational invariance of scalar properties. However, the prediction of tensorial properties requires that the model respects the appropriate geometric transformations, rather than invariance, when the reference frame is rotated. We introduce a formalism that can be used to perform machine-learning of tensorial properties of arbitrary rank for general molecular geometries. To demonstrate it, we derive a tensor kernel adapted to rotational symmetry, which is the natural generalization of the smooth overlap of atomic positions (SOAP) kernel commonly used for the prediction of scalar properties at the atomic scale. The performance and generality of the approach is demonstrated by learning the instantaneous electrical response of water oligomers of increasing complexity, from the isolated molecule to the condensed phase.

References in corpus (3)

• Machine Learning Unifies the Modelling of Materials and Molecules
• Machine-learning based interatomic potential for amorphous carbon
• Competing quantum effects in the dynamics of a flexible water model

Cited by in corpus (80)

• Machine Learning Force Fields
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Physics-inspired structural representations for molecules and materials
• Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation
• Coarse Graining Molecular Dynamics with Graph Neural Networks
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Self-Consistent Determination of Long-Range Electrostatics in Neural Network Potentials
• Atomic cluster expansion of scalar, vectorial and tensorial properties and including magnetism and charge transfer
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
• Transferable E(3) equivariant parameterization for Hamiltonian of molecules and solids
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Universal Machine Learning for the Response of Atomistic Systems to External Fields
• Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids
• Symmetry-Adapted High Dimensional Neural Network Representation of Electronic Friction Tensor of Adsorbates on Metals
• Equivariant representations for molecular Hamiltonians and N-center atomic-scale properties
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• Permutationally Invariant, Reproducing Kernel-Based Potential Energy Surfaces for Polyatomic Molecules: From Formaldehyde to Acetone
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Spectroscopy from Machine Learning by Accurately Representing the Atomic Polar Tensor
• Efficient implementation of atom-density representations
• Predicting tensorial molecular properties with equivariant machine-learning models
• A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
• Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks
• Universal Machine Learning Kohn-Sham Hamiltonian for Materials
• Dielectric response with short-ranged electrostatics
• Fully First-Principles Surface Spectroscopy with Machine Learning
• Machine Learning Potential for Electrochemical Interfaces with Hybrid Representation of Dielectric Response
• E(n)-Equivariant Cartesian Tensor Passing Potential
• An equivariant graph neural network for the elasticity tensors of all seven crystal systems
• Hydration free energies from kernel-based machine learning: Compound-database bias
• A spectral-neighbour representation for vector fields: machine-learning potentials including spin
• Dielectric constant of supercritical water in a large pressure-temperature range
• Tensorial properties via the neuroevolution potential framework: Fast simulation of infrared and Raman spectra
• Predicting the Charge Density Response in Metal Electrodes
• Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials
• SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
• Fast and flexible long-range models for atomistic machine learning
• Optimal radial basis for density-based atomic representations
• 3DReact: Geometric deep learning for chemical reactions
• SPA${}^{\mathrm{H}}$M: the Spectrum of Approximated Hamiltonian Matrices representations
• Machine Learning Diffusion Monte Carlo Energies
• Modeling of many-body interactions between elastic spheres through symmetry functions
• KineticNet: Deep learning a transferable kinetic energy functional for orbital-free density functional theory
• Predicting the Electronic Density Response of Condensed-Phase Systems to Electric Field Perturbations
• Machine-learning of atomic-scale properties based on physical principles
• Exploring the design space of machine-learning models for quantum chemistry with a fully differentiable framework
• Mean-Field Density Matrix Decompositions
• Learning on-top: regressing the on-top pair density for real-space visualization of electron correlation
• A deep learning model for chemical shieldings in molecular organic solids including anisotropy
• 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
• Modeling of effective interactions between ligand coated nanoparticles through symmetry functions
• Weighted Active Space Protocol for Multireference Machine-Learned Potentials
• Machine learning at the atomic-scale
• Electronic Descriptors for Supervised Spectroscopic Predictions
• Learning intermolecular forces at liquid-vapor interfaces
• Impact of quantum-chemical metrics on the machine learning prediction of electron density
• 2D spectroscopies from condensed phase dynamics: Accessing third-order response properties from equilibrium multi-time correlation functions
• A simple approach to rotationally invariant machine learning of avector quantity
• Hybrid localized graph kernel for machine learning energy-related properties of molecules and solids
• Learning the Electrostatic Response of the Electron Density through a Symmetry-Adapted Vector Field Model
• A Bond-Based Machine Learning Model for Molecular Polarizabilities and A Priori Raman Spectra
• Ab initio machine learning in chemical compound space
• A general formalism for machine-learning models based on multipolar-spherical harmonics
• General Learning of the Electric Response of Inorganic Materials
• Incorporating electronic information into Machine Learning potential energy surfaces via approaching the ground-state electronic energy as a function of atom-based electronic populations
• Predicting Many Crystal Properties via an Adaptive Transformer-based Framework
• Representing spherical tensors with scalar-based machine-learning models
• Unified theory of atom-centered representations and message-passing machine-learning schemes
• 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
• Surfing multiple conformation-property landscapes via machine learning: Designing magnetic anisotropy
• Learning electron densities in the condensed phase
• Simplifying inverse material design problems for fixed lattices with alchemical chirality
• Machine learning of electronic structure and atomistic properties from the external potential