CRYSPNet: Crystal Structure Predictions via Neural Network
This addresses the challenge of crystal structure prediction for materials science researchers, offering a more efficient and accurate tool, though it is incremental as it applies existing neural network methods to a specific domain.
The paper tackles the problem of predicting crystal structures of inorganic materials, which is computationally expensive and inaccurate with standard methods, by developing CRYSPNet, a neural network tool that predicts Bravais lattice, space group, and lattice parameters from chemical composition, outperforming alternative strategies by a large margin on over 100,000 database entries.
Structure is the most basic and important property of crystalline solids; it determines directly or indirectly most materials characteristics. However, predicting crystal structure of solids remains a formidable and not fully solved problem. Standard theoretical tools for this task are computationally expensive and at times inaccurate. Here we present an alternative approach utilizing machine learning for crystal structure prediction. We developed a tool called Crystal Structure Prediction Network (CRYSPNet) that can predict the Bravais lattice, space group, and lattice parameters of an inorganic material based only on its chemical composition. CRYSPNet consists of a series of neural network models, using as inputs predictors aggregating the properties of the elements constituting the compound. It was trained and validated on more than 100,000 entries from the Inorganic Crystal Structure Database. The tool demonstrates robust predictive capability and outperforms alternative strategies by a large margin. Made available to the public (at https://github.com/AuroraLHT/cryspnet), it can be used both as an independent prediction engine or as a method to generate candidate structures for further computational and/or experimental validation.