Computational methods that automatically extract knowledge from data are critical for enabling data-driven materials science. A reliable identification of lattice symmetry is a crucial first step for materials characterization and analytics. Current methods require a user-specified threshold, and are unable to detect average symmetries for defective structures. Here, we propose a machine learning-based approach to automatically classify structures by crystal symmetry. First, we represent crystals by calculating a diffraction image, then construct a deep learning neural network model for classification. Our approach is able to correctly classify a dataset comprising more than 100,000 simulated crystal structures, including heavily defective ones. The internal operations of the neural network are unraveled through attentive response maps, demonstrating that it uses the same landmarks a materials scientist would use, although never explicitly instructed to do so. Our study paves the way for crystal structure recognition of—possibly noisy and incomplete—three-dimensional structural data in big-data materials science.

A public data-analytics competition was organized by the Novel Materials Discovery (NOMAD) Centre of Excellence and hosted by the online platform Kaggle by using a dataset of 3,000 (Al x Ga y In 1-x-y) 2 O 3 compounds. Its aim was to identify the best machinelearning (ML) model for the prediction of two key physical properties that are relevant for optoelectronic applications: the electronic bandgap energy and the crystalline formation energy. Here, we present a summary of the top-three ranked ML approaches. The first-place solution was based on a crystal-graph representation that is novel for the ML of properties of materials. The second-place model combined many candidate descriptors from a set of compositional, atomic-environment-based, and average structural properties with the light gradient-boosting machine regression model. The third-place model employed the smooth overlap of atomic position representation with a neural network. The Pearson correlation among the prediction errors of nine ML models (obtained by combining the top-three ranked representations with all three employed regression models) was examined by using the Pearson correlation to gain insight into whether the representation or the regression model determines the overall model performance. Ensembling relatively decorrelated models (based on the Pearson correlation) leads to an even higher prediction accuracy.

Due to their ability to recognize complex patterns, neural networks can drive a paradigm shift in the analysis of materials science data. Here, we introduce ARISE, a crystal-structure identification method based on Bayesian deep learning. As a major step forward, ARISE is robust to structural noise and can treat more than 100 crystal structures, a number that can be extended on demand. While being trained on ideal structures only, ARISE correctly characterizes strongly perturbed single- and polycrystalline systems, from both synthetic and experimental resources. The probabilistic nature of the Bayesian-deep-learning model allows to obtain principled uncertainty estimates, which are found to be correlated with crystalline order of metallic nanoparticles in electron tomography experiments. Applying unsupervised learning to the internal neural-network representations reveals grain boundaries and (unapparent) structural regions sharing easily interpretable geometrical properties. This work enables the hitherto hindered analysis of noisy atomic structural data from computations or experiments.

No abstract

No abstract