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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Developing accurate, transferable and computationally inexpensive machinelearning models can rapidly accelerate the discovery and development of newmaterials. Some of the major challenges involved in developing such models are,(i) limited availability of materials data as compared to other fields, (ii)lack of universal descriptor of materials to predict its various properties.The limited availability of materials data can be addressed through transferlearning, while the generic representation was recently addressed by Xie andGrossman [1], where they developed a crystal graph convolutional neural network(CGCNN) that provides a unified representation of crystals. In this work, wedevelop a new model (MT-CGCNN) by integrating CGCNN with transfer learningbased on multi-task (MT) learning. We demonstrate the effectiveness of MT-CGCNNby simultaneous prediction of various material properties such as FormationEnergy, Band Gap and Fermi Energy for a wide range of inorganic crystals (46774materials). MT-CGCNN is able to reduce the test error when employed oncorrelated properties by upto 8%. The model prediction has lower test errorcompared to CGCNN, even when the training data is reduced by 10%. We alsodemonstrate our model's better performance through prediction of end userscenario related to metal/non-metal classification. These results encouragefurther development of machine learning approaches which leverage multi-tasklearning to address the aforementioned challenges in the discovery of newmaterials. We make MT-CGCNN's source code available to encourage reproducibleresearch.

MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction