Neural Network for Crystal Structure Error Classification
A study has introduced a neural network designed to classify crystal structure errors in metal–organic frameworks (MOF) and other databases.
The approach, as noted by Tiffany Rogers, is a reminder that machine learning models are only as good as the data they are trained on.
The neural network aims to improve the fidelity of crystal structure databases by detecting and classifying structural errors, including proton omissions, charge imbalances, and crystallographic disorder.
Artificial intelligence and machine learning are becoming increasingly central to materials research, with scientists often turning to such tools to predict properties of new compounds.
This development could help boost the accuracy of computational predictions used in materials discovery that rely on such databases.
Author's summary: AI improves crystal database accuracy.