Crystal Structure

Crystal structure research focuses on understanding and predicting the arrangement of atoms in crystalline materials, aiming to correlate structure with material properties. Current research heavily utilizes machine learning, employing graph neural networks, diffusion models, and transformers to analyze and generate crystal structures, often incorporating techniques like equivariance to account for inherent symmetries. These advancements are significantly impacting materials science by accelerating the discovery of novel materials with desired properties and improving the efficiency of materials characterization techniques like X-ray diffraction analysis. The ultimate goal is to enable rational design of materials for specific applications.

Papers

April 1, 2022

TopTemp: Parsing Precipitate Structure from Temper Topology
Lara Kassab, Scott Howland, Henry Kvinge, Keerti Sahithi Kappagantula, Tegan Emerson
Microstructure Model 3D Microstructures Crystal Structure Personality Classification Topological Representation Topology Generation

March 2, 2022

Naturally-meaningful and efficient descriptors: machine learning of material properties based on robust one-shot ab initio descriptors
Sherif Abdulkader Tawfik, Salvy P. Russo
Machine Learning One Shot Crystal Structure Material Property Ab Initio Metal Organic Framework Descriptor Extraction Novel Material

Crystal Structure

Papers

TopTemp: Parsing Precipitate Structure from Temper Topology

Naturally-meaningful and efficient descriptors: machine learning of material properties based on robust one-shot ab initio descriptors