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

Applications of machine learning techniques in materials science are oftenbased on two key ingredients, a set of empirical descriptors and a database ofa particular material property of interest. The advent of graph neuralnetworks, such as the Crystal Graph Convolutional Neural Network (CGCNN),demonstrates the possibility of directly mapping the relationship betweenmaterial structures and properties without employing empirical descriptors.Another exciting recent advancement is in large language models such asOpenAI's GPT-4, which demonstrates competency at reading comprehension tasksand holds great promise for accelerating the acquisition of databases onmaterial properties. Here, we utilize the combination of GPT-4 and CGCNN todevelop rare-earth doped phosphors for solid-state lighting. GPT-4 is appliedto data-mine chemical formulas and emission wavelengths of 264 Eu(II)-dopedphosphors from 274 papers. A CGCNN model is trained on the acquired dataset,achieving a test $R^2$ of 0.77. The model is then used to screen over 40,000inorganic materials to make predictions on the emission wavelengths. We alsodemonstrate the possibility of leveraging transfer learning to fine-tune abandgap-predicting CGCNN model towards the prediction of phosphor emissionwavelengths. The workflow requires minimal human supervision, little domainknowledge about phosphors, and is generalizable to other material properties.

GPT-assisted learning of structure-property relationships by graph neural networks: Application to rare-earth doped phosphors