Substitutional alloying using crystal graph neural networks

Abstract

Materials discovery, especially for applications that require extreme operating conditions, requires extensive testing that naturally limits the ability to inquire the wealth of possible compositions. Machine Learning (ML) has nowadays a well-established role in facilitating this effort in systematic ways. The increasing amount of available accurate Density Functional Theory (DFT) data represents a solid basis upon which new ML models can be trained and tested. While conventional models rely on static descriptors, generally suitable for a limited class of systems, the flexibility of Graph Neural Networks (GNNs) allows for direct learning representations on graphs, such as the ones formed by crystals. We utilize crystal graph neural networks (CGNNs) known to predict crystal properties with DFT level accuracy through graphs by encoding the atomic (node/vertex), bond (edge), and global state attributes. In this work, we aim at testing the ability of the CGNN MegNet framework in predicting a number of properties of systems previously unseen in the model, which are obtained by adding a substitutional defect to bulk crystals that are included in the training set. We perform DFT validation to assess the accuracy in the prediction of formation energies and structural features (such as elastic moduli). Using CGNNs, one may identify promising paths in alloy discovery.