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.

13 pages, 13 figures

References in corpus (5)

• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Machine Learning Unifies the Modelling of Materials and Molecules
• Displacement cascades and defects annealing in tungsten, Part I: defect database from molecular dynamics simulations
• Mechanical annealing of model glasses: Effects of strain amplitude and temperature
• Exploring the robust extrapolation of high-dimensional machine learning potentials