Interpretable AI in materials discovery: Uncovering how models make predictions

A method to interpret artificial intelligence (AI) models used in materials discovery by analyzing their learned features has ...
Nature

Resolving chemical-motif similarity with enhanced atomic structure representations for accurately predicting descriptors at metallic interfaces

Accurately predicting catalytic descriptors with machine learning (ML) methods is significant to achieving accelerated catalyst design, where a unique representation of the atomic structure of each ...
Nature

Machine learning-powered recognition of crystalline phases and orientations in epitaxial Y-doped HfO

This study presents an efficient method for automatically identifying the crystal structure and orientation of Y-doped HfO 2-based thin films using deep learning. This approach enables large-scale ...