Accelerating the prediction of remanent polarization in multicomponent ferroelectrics by using variational autoencoder-based data augmentation
Using a variational autoencoder to expand the dataset to 20 000, six key descriptors for the remanent polarization of the (K 1− x − y − z Na x Ba y Ca z )(Nb 1− u − v − w Zr u Ti v )O 3 system were identified, enabling accurate predictions for new experimental systems.
Authors
- J. Luo (ORCID: https://orcid.org/0000-0002-4108-8681)
- Zixiong Sun (ORCID: https://orcid.org/0000-0001-9127-8224)
- Ping Wang (ORCID: https://orcid.org/0000-0002-1510-7869)
- Wanbiao Hu (ORCID: https://orcid.org/0000-0003-0180-9648)
- Yujie Bai (ORCID: https://orcid.org/0000-0001-8244-8770)
- Xinying Liu (ORCID: https://orcid.org/0000-0002-1629-0298)
- Ran Gao (ORCID: https://orcid.org/0000-0002-8505-6972)
- Hongyu Yang (ORCID: https://orcid.org/0000-0002-5894-1693)
Institutions
- Xidian University (CN)
- National Engineering Research Center of Electromagnetic Radiation Control Materials (CN)
- Shaanxi University of Science and Technology (CN)
Publication Details
- Journal
- Journal of Materials Chemistry C
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5tc01781e
- Citations
- 6
- Primary Topic
- Magnetic Properties and Applications
- Type
- article
- Field-Weighted Citation Impact
- 2.56