Deep Learning for Automated Classification and Characterization of Amorphous Materials

TL;DR

This paper demonstrates that deep learning models, especially message passing neural networks with self-attention, can accurately classify amorphous materials and reveal structural features related to glass formation, surpassing traditional methods.

Contribution

It introduces novel deep learning approaches for classifying amorphous materials and deriving new structural metrics, enhancing understanding of glass formation.

Findings

Neural networks achieve >0.98 AUC in classifying liquids and glasses.

Message passing neural networks outperform CNNs in accuracy and interpretability.

Derived three new structural metrics for glass formation.

Abstract

It is difficult to quantify structure-property relationships and to identify structural features of complex materials. The characterization of amorphous materials is especially challenging because their lack of long-range order makes it difficult to define structural metrics. In this work, we apply deep learning algorithms to accurately classify amorphous materials and characterize their structural features. Specifically, we show that convolutional neural networks and message passing neural networks can classify two-dimensional liquids and liquid-cooled glasses from molecular dynamics simulations with greater than 0.98 AUC, with no a priori assumptions about local particle relationships, even when the liquids and glasses are prepared at the same inherent structure energy. Furthermore, we demonstrate that message passing neural networks surpass convolutional neural networks in this context in both accuracy and interpretability. We extract a clear interpretation of how message passing neural networks evaluate liquid and glass structures by using a self-attention mechanism. Using this interpretation, we derive three novel structural metrics that accurately characterize glass formation. The methods presented here provide us with a procedure to identify important structural features in materials that could be missed by standard techniques and give us a unique insight into how these neural networks process data.