Hu, Y, Wu, M, Yuan, M, Wen, Y, Ren, P, Ye, S, Liu, F, Zhou, B, Fang, H, Wang, R, Ji, Z and Huang, R Accurate Prediction of Dielectric Properties and Band Gaps in Materials with Machine Learning Approach. Applied Physics Letters. ISSN 0003-6951 (Accepted)

Preview

Text 1766240_2_unknown_upload_24673538_sjtzn7.pdf - Accepted Version Download (4MB) | Preview

Abstract

The conventional approach to exploring suitable dielectrics for future logic and memory devices relies on first-principle calculations, which are expensive and time-consuming. In this work, we adopt a data-driven machine learning (ML)-based approach to build a model for predicting these properties. By incorporating structural information into the input descriptors, we achieve record-high accuracy in predicting the dielectric constant, with an R2 of 0.886 and an RMSE of 0.083. Additionally, we achieve high predictions for the band gap, with accuracies of 0.832 and 0.533 for R2 and RMSE, respectively. The features corresponding to specific properties are analyzed to obtain physical insights. Finally, we employ first-principle calculations to validate the feasibility of this model. This work proposes a highly efficient approach for using ML to predict material properties.

Item Type:	Article
Additional Information:	The following article has been accepted by Applied Physics Letters. After it is published, it will be found at https://pubs.aip.org/aip/apl
Uncontrolled Keywords:	02 Physical Sciences; 09 Engineering; 10 Technology; Applied Physics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Computer Science and Mathematics
Publisher:	American Institute of Physics
SWORD Depositor:	A Symplectic
Date Deposited:	30 Sep 2024 13:04
Last Modified:	30 Sep 2024 13:04
URI:	https://researchonline.ljmu.ac.uk/id/eprint/24295

View Item