Quantifying disorder one atom at a time using an interpretable graph neural network paradigm

Abstract

Quantifying the level of atomic disorder within materials is critical to understanding how evolving local structural environments dictate performance and durability. Here, we leverage graph neural networks to define a physically interpretable metric for local disorder, called SODAS. This metric encodes the diversity of the local atomic configurations as a continuous spectrum between the solid and liquid phases, quantified against a distribution of thermal perturbations. We apply this methodology to four prototypical examples with varying levels of disorder: (1) grain boundaries, (2) solid-liquid interfaces, (3) polycrystalline microstructures, and (4) tensile failure/fracture. We also compare SODAS to several commonly used methods. Using elemental aluminum as a case study, we show how our paradigm can track the spatio-temporal evolution of interfaces, incorporating a mathematically defined description of the spatial boundary between order and disorder. We further show how to extract physics-preserved gradients from our continuous disorder fields, which may be used to understand and predict materials performance and failure. Overall, our framework provides a simple and generalizable pathway to quantify the relationship between complex local atomic structure and coarse-grained materials phenomena.

Fragility crossover mediated by covalent-like electronic interactions in metallic liquids

“…A DNN potential of the La 50 Ni 50−x Al x system was obtained using the DeePMD-kit (DP) package [86,87]. Data sets of 25 different compositions obtained by AIMD were fitted to yield high-precision interatomic interaction potentials.…”

“…As shown in figure 5(a), based on a wide range of compositions for the training data set, we used the DeepPMDkit package [86,87] to train the DNN interatomic potential (more training details are contained in supplemental information). Based on this potential, we obtain La 50 Ni 50−x Al x series glass models at a cooling rate of 10 10 K s −1 (T g = 610 K, 615 K, 640 K, 680 K, and 690 K respectively, as indicated by the arrows).…”