Continued challenges in high-throughput materials predictions: MatterGen predicts compounds from the training dataset
Abstract
Artificial intelligence models for rapid materials prediction continue to face challenges with incorporating disorder and other crystallographic effects in their predictions, leading them to classify known materials as novel compounds.
Fields of Study & Subjects
Machine Learning in Materials Science
X-ray Diffraction in Crystallography
Electron and X-Ray Spectroscopy Techniques
Publication details
- Journal / source
- Materials Horizons
- Publisher
- Royal Society of Chemistry (RSC)
- Volume
- 13
- Issue
- 11
- Pages
- 5672–5679
- Publication date
- 1 January 2026
- Language
- EN