Compressing and forecasting atomic material simulations with descriptors

TL;DR

This paper introduces atomic descriptor functions as a compact latent space for efficient simulation, compression, and forecasting of material microstructures, enabling large-scale analysis with uncertainty quantification.

Contribution

It proposes a novel descriptor-based approach for microstructure compression and forecasting, including a confidence measure, validated on nanoparticle and dislocation network simulations.

Findings

Descriptors effectively regress various material properties.

Forecasting with the model shows low uncertainty and high accuracy.

Microstructure yielding correlates with a reduction in descriptor manifold dimension.

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.