Through the eyes of a descriptor: Constructing complete, invertible descriptions of atomic environments

Abstract

In this work we apply methods for describing 3D images to the problem of encoding atomic environments in a way that is invariant to rotations, translations, and permutations of the atoms and, crucially, can be decoded back into the original environment modulo global orientation without the need for training a model. From the point of view of decoding, the descriptor is optimally complete and can be extended to arbitrary order, allowing for a systematic convergence of the fidelity of the description. In experiments on molecules ranging from 3 to 29 atoms in size, we demonstrate that positions can be decoded with a 97% success rate and positions plus species with a 70% rate of success, rising to 95% if a second fingerprint is used. In all cases, consistent recovery is observed for molecules with 17 or fewer atoms. Additionally, we evaluate the descriptor's performance in predicting the energies and forces of bulk Ni, Cu, Li, Mo, Si and Ge by means of a neural network model trained on DFT data. When comparing to six machine learning interaction potential methods that use various descriptors and regression schemes our descriptor is found be to competitive, in several cases outperforming well established methods. The combined ability to both decode and make property predictions from a representation that does not need to be learned lays the foundations for a novel way of building generative models that are tasked with solving the inverse problem of predicting atomic arrangements that are statistically likely to have certain desired properties.

arXiv comment25 pages, 8 figures

References in corpus (25)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• 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
• A "missing" family of classical orthogonal polynomials
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Ab initio Random Structure Searching
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Physics-inspired structural representations for molecules and materials
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• Automatic Selection of Atomic Fingerprints and Reference Configurations for 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
• Extending the Accuracy of the SNAP Interatomic Potential Form
• On the Completeness of Atomic Structure Representations
• Atom-Density Representations for Machine Learning
• Machine learning of molecular properties: locality and active learning
• Atomic cluster expansion of scalar, vectorial and tensorial properties and including magnetism and charge transfer
• Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• Atomistic structure learning
• Permutation-invariant distance between atomic configurations
• Compact atomic descriptors enable accurate predictions via linear models
• Optimal radial basis for density-based atomic representations

Cited by in corpus (8)

• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation
• Tensor-reduced atomic density representations
• Inversion of the chemical environment representations
• Unified theory of atom-centered representations and message-passing machine-learning schemes
• Compressing local atomic neighbourhood descriptors