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

Accurately predicting the physical and chemical properties of materialsremains one of the most challenging tasks in material design, and one effectivestrategy is to construct a reliable data set and use it for training a machinelearning model. In this study, we constructed a large-scale material genomedatabase (Matgen) containing 76,463 materials collected fromexperimentally-observed database, and computed their bandgap properties throughthe Density functional theory (DFT) method with Perdew-Burke-Ernzehof (PBE)functional. We verified the computation method by comparing part of our resultswith those from the open Material Project (MP) and Open Quantum MaterialsDatabase (OQMD), all with PBE computations, and found that Matgen achieved thesame computation accuracy based on both measured and computed bandgapproperties. Based on the computed properties of our comprehensive dataset, wehave developed a new graph-based deep learning model, namely CrystalNet,through our recently developed Communicative Message Passing Neural Network(CMPNN) framework. The model was shown to outperform other state-of-the-artprediction models. A further fine-tuning on 1716 experimental bandgap values(CrystalNet-TL) achieved a superior performance with mean absolute error (MAE)of 0.77 eV on independent test, which has outperformed the pure PBE (1.14~1.45eV). Moreover, the model was proven applicable to hypothetical materials withMAE of 0.77 eV as referred by computations from HSE, a highly accurate quantummechanics (QM) method, consist better than PBE (MAE=1.13eV). We also madematerial structures, computed properties by PBE, and the CrystalNet modelspublically available at https://matgen.nscc-gz.cn.

Leveraging Large-scale Computational Database and Deep Learning for Accurate Prediction of Material Properties