A Deep-learning Model for Fast Prediction of Vacancy Formation in Diverse Materials

The presence of point defects such as vacancies plays an important role in material design. Here, we \red{explore} the extrapolative power of a graph neural network (GNN) to predict vacancy formation energies. We show that a model trained only on perfect materials can also be used to predict vacancy formation energies ($E_{vac}$) of defect structures without the need for additional training data. Such GNN-based predictions are considerably faster than density functional theory (DFT) calculations and show the potential as a quick pre-screening tools for defect systems. To test this strategy, we developed a DFT dataset of 473 $E_{vac}$ consisting of 3D elemental solids, alloys, oxides, semiconductors and 2D monolayer materials. We analyzed and discussed the applicability of such direct and fast predictions. We applied the model to predict 192494 $E_{vac}$ for 55723 materials in the JARVIS-DFT database. Our work demonstrates how a GNN-model performs on unseen data. The model is available at \url{https://github.com/usnistgov/alignn}. <br> ALIGNN GitHub repo: https://github.com/usnistgov/alignn JARVIS-Tools repo: https://github.com/usnistgov/jarvis JARVIS-DFT Website: https://jarvis.nist.gov/jarvisdft/ <br>