Compressing and forecasting atomic material simulations with descriptors

Abstract

Atomic simulations of material microstructure require significant resources to generate, store and analyze. Here, atomic descriptor functions are proposed as a general latent space to compress atomic microstructure, ideal for use in large-scale simulations. Descriptors can regress a broad range of properties, including character-dependent dislocation densities, stress states or radial distribution functions. A vector autoregressive model can generate trajectories over yield points, resample from new initial conditions and forecast trajectory futures. A forecast confidence, essential for practical application, is derived by propagating forecasts through the Mahalanobis outlier distance, providing a powerful tool to assess coarse-grained models. Application to nanoparticles and yielding of dislocation networks confirms low uncertainty forecasts are accurate and resampling allows for the propagation of smooth microstructure distributions. Yielding is associated with a collapse in the intrinsic dimension of the descriptor manifold, which is discussed in relation to the yield surface.

arXiv comment13 pages, 13 figures

References in corpus (29)

• Double-slit photoelectron interference in strong-field ionization of the neon dimer
• Escaping free-energy minima
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Machine Learning Unifies the Modelling of Materials and Molecules
• Active learning of linearly parametrized interatomic potentials
• Shrinkage Algorithms for MMSE Covariance Estimation
• Probing the ultimate limits of metal plasticity
• Estimating the intrinsic dimension of datasets by a minimal neighborhood information
• Uncovering electron scattering mechanisms in NiFeCoCrMn derived concentrated solid solution and high entropy alloys
• Coarse-Graining Auto-Encoders for Molecular Dynamics
• Displacement cascades and defects annealing in tungsten, Part I: defect database from molecular dynamics simulations
• Dislocation Networks and the Microstructural Origin of Strain Hardening
• A Topological Framework for Local Structure Analysis in Condensed Matter
• Scikit-dimension: a Python package for intrinsic dimension estimation
• Stochastic resonance-free multiple time-step algorithm for molecular dynamics with very large time steps
• Observation of transient and asymptotic driven structural states of tungsten exposed to irradiation
• Complete topology of cells, grains, and bubbles in three-dimensional microstructures
• Atomic Permutationally Invariant Polynomials for Fitting Molecular Force Fields
• Mechanical annealing of model glasses: Effects of strain amplitude and temperature
• Landau theory of crystal plasticity
• DADApy: Distance-based Analysis of DAta-manifolds in Python
• Self-optimized construction of transition rate matrices from accelerated atomistic simulations with Bayesian uncertainty quantification
• Exploring the robust extrapolation of high-dimensional machine learning potentials
• Exploring glassy dynamics with Markov state models from graph dynamical neural networks