Neural Network for Crystal Structure Error Classification
A neural network has been trained to classify crystal structure errors in metal–organic frameworks (MOF) and other databases.
According to a recent study, this approach can detect and classify structural errors, including proton omissions, charge imbalances, and crystallographic disorder.
Machine learning models are only as good as the data they are trained on.
This reminds us that the accuracy of computational predictions relies on the fidelity of the databases used. The study aims to improve the accuracy of these predictions by identifying and correcting errors in crystal structure databases.
Author summary: Neural network improves database accuracy.
- Detects proton omissions
- Identifies charge imbalances
- Flags crystallographic disorder