English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Machine learning (ML) methods have gained increasing popularity in exploringand developing new materials. More specifically, graph neural network (GNN) hasbeen applied in predicting material properties. In this work, we develop anovel model, GATGNN, for predicting inorganic material properties based ongraph neural networks composed of multiple graph-attention layers (GAT) and aglobal attention layer. Through the application of the GAT layers, our modelcan efficiently learn the complex bonds shared among the atoms within eachatom's local neighborhood. Subsequently, the global attention layer providesthe weight coefficients of each atom in the inorganic crystal material whichare used to considerably improve our model's performance. Notably, with thedevelopment of our GATGNN model, we show that our method is able to bothoutperform the previous models' predictions and provide insight into thecrystallization of the material.

Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Prediction