Predicting synthesizability of crystalline materials via deep learning

• Published in: Communications materials 2021-11, Vol.2 (1), p.1-11, Article 115
• Main Authors: Davariashtiyani, Ali, Kadkhodaie, Zahra, Kadkhodaei, Sara
• Format: Article
• Language: English
• Subjects: 639/301/1034/1037; 639/705; Anomalies; Artificial neural networks; Atomic structure; Chemical composition; Chemical synthesis; Chemistry and Materials Science; Coders; Color; Crystal structure; Crystallinity; Crystals; Deep learning; Materials Science
• ISSN: 2662-4443; 2662-4443
• DOI: 10.1038/s43246-021-00219-x

Predicting the synthesizability of hypothetical crystals is challenging because of the wide range of parameters that govern materials synthesis. Yet, exploring the exponentially large space of novel crystals for any future application demands an accurate predictive capability for synthesis likelihood to avoid a haphazard trial-and-error. Typically, benchmarks of synthesizability are defined based on the energy of crystal structures. Here, we take an alternative approach to select features of synthesizability from the latent information embedded in crystalline materials. We represent the atomic structure of crystalline materials by three-dimensional pixel-wise images that are color-coded by their chemical attributes. The image representation of crystals enables the use of a convolutional encoder to learn the features of synthesizability hidden in structural and chemical arrangements of crystalline materials. Based on the presented model, we can accurately classify materials into synthesizable crystals versus crystal anomalies across a broad range of crystal structure types and chemical compositions. We illustrate the usefulness of the model by predicting the synthesizability of hypothetical crystals for battery electrode and thermoelectric applications. Predicting the synthesizability of unknown crystals is important for accelerating materials discovery. Here, the synthesizability of crystals with any given composition and structure can be predicted by a deep learning model that maps crystals onto color-coded 3D images processed by convolutional neural networks.