Next Article in Journal
Improving the Adhesiveness of Cemented Glass Components by DBD Plasma Pre-Treatment at Atmospheric Pressure
Previous Article in Journal
The Classification of Inertinite Macerals in Coal Based on the Multifractal Spectrum Method
Open AccessArticle

Computational Screening of New Perovskite Materials Using Transfer Learning and Deep Learning

1
School of Mechanical Engineering, Guizhou University, Guiyang 550025, China
2
Key laboratory of advanced manufacturing technology, Ministry of education, Guiyang 550025, China
3
Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29208, USA
*
Authors to whom correspondence should be addressed.
Appl. Sci. 2019, 9(24), 5510; https://doi.org/10.3390/app9245510
Received: 8 November 2019 / Revised: 2 December 2019 / Accepted: 12 December 2019 / Published: 14 December 2019
(This article belongs to the Section Materials)
As one of the most studied materials, perovskites exhibit a wealth of superior properties that lead to diverse applications. Computational prediction of novel stable perovskite structures has big potential in the discovery of new materials for solar panels, superconductors, thermal electric, and catalytic materials, etc. By addressing one of the key obstacles of machine learning based materials discovery, the lack of sufficient training data, this paper proposes a transfer learning based approach that exploits the high accuracy of the machine learning model trained with physics-informed structural and elemental descriptors. This gradient boosting regressor model (the transfer learning model) allows us to predict the formation energy with sufficient precision of a large number of materials of which only the structural information is available. The enlarged training set is then used to train a convolutional neural network model (the screening model) with the generic Magpie elemental features with high prediction power. Extensive experiments demonstrate the superior performance of our transfer learning model and screening model compared to the baseline models. We then applied the screening model to filter out promising new perovskite materials out of 21,316 hypothetical perovskite structures with a large portion of them confirmed by existing literature. View Full-Text
Keywords: perovskites; transfer learning; deep learning; convolutional neural networks; small dataset; formation energy perovskites; transfer learning; deep learning; convolutional neural networks; small dataset; formation energy
Show Figures

Graphical abstract

MDPI and ACS Style

Li, X.; Dan, Y.; Dong, R.; Cao, Z.; Niu, C.; Song, Y.; Li, S.; Hu, J. Computational Screening of New Perovskite Materials Using Transfer Learning and Deep Learning. Appl. Sci. 2019, 9, 5510.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop