Predicting energy and stability of known and hypothetical crystals using graph neural network
Shubham Pandey, Jiaxing Qu, Vladan Stevanović, Peter C. St. John, Prashun Gorai
Abstract
11,000 calculations for hypothetical structures as our training database, we demonstrate that our model satisfactorily ranks the structures in the correct order of total energies for a given composition. Furthermore, we present a thorough error analysis to explain failure modes of the model, including both prediction outliers and occasional inconsistencies in the training data. By examining intermediate layers of the model, we analyze how the model represents learned structures and properties.
Topics & Concepts
OutlierArtificial neural networkComputer scienceStability (learning theory)GraphGraph theoryRenewable energyEnergy (signal processing)Data miningTraining setArtificial intelligenceMachine learningTheoretical computer scienceMathematicsEngineeringStatisticsCombinatoricsElectrical engineeringMachine Learning in Materials ScienceComputational Drug Discovery MethodsX-ray Diffraction in Crystallography