Deep learning for exploring ultra-thin ferroelectrics with highly improved sensitivity of piezoresponse force microscopy
Abstract Hafnium oxide-based ferroelectrics have been extensively studied because of their existing ferroelectricity, even in ultra-thin film form. However, studying the weak response from ultra-thin film requires improved measurement sensitivity. In general, resonance-enhanced piezoresponse force m...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-02-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-023-00982-0 |
| _version_ | 1827983307598462976 |
|---|---|
| author | Panithan Sriboriboon Huimin Qiao Owoong Kwon Rama K. Vasudevan Stephen Jesse Yunseok Kim |
| author_facet | Panithan Sriboriboon Huimin Qiao Owoong Kwon Rama K. Vasudevan Stephen Jesse Yunseok Kim |
| author_sort | Panithan Sriboriboon |
| collection | DOAJ |
| description | Abstract Hafnium oxide-based ferroelectrics have been extensively studied because of their existing ferroelectricity, even in ultra-thin film form. However, studying the weak response from ultra-thin film requires improved measurement sensitivity. In general, resonance-enhanced piezoresponse force microscopy (PFM) has been used to characterize ferroelectricity by fitting a simple harmonic oscillation model with the resonance spectrum. However, an iterative approach, such as traditional least squares (LS) fitting, is sensitive to noise and can result in the misunderstanding of weak responses. In this study, we developed the deep neural network (DNN) hybrid with deep denoising autoencoder (DDA) and principal component analysis (PCA) to extract resonance information. The DDA/PCA-DNN improves the PFM sensitivity down to 0.3 pm, allowing measurement of weak piezoresponse with low excitation voltage in 10-nm-thick Hf0.5Zr0.5O2 thin films. Our hybrid approaches could provide more chances to explore the low piezoresponse of the ultra-thin ferroelectrics and could be applied to other microscopic techniques. |
| first_indexed | 2024-04-09T22:45:32Z |
| format | Article |
| id | doaj.art-12264c3e13d143369d9d4bf4c8b5ec87 |
| institution | Directory Open Access Journal |
| issn | 2057-3960 |
| language | English |
| last_indexed | 2024-04-09T22:45:32Z |
| publishDate | 2023-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj.art-12264c3e13d143369d9d4bf4c8b5ec872023-03-22T11:50:23ZengNature Portfolionpj Computational Materials2057-39602023-02-01911810.1038/s41524-023-00982-0Deep learning for exploring ultra-thin ferroelectrics with highly improved sensitivity of piezoresponse force microscopyPanithan Sriboriboon0Huimin Qiao1Owoong Kwon2Rama K. Vasudevan3Stephen Jesse4Yunseok Kim5School of Advanced Materials and Engineering, Sungkyunkwan University (SKKU)School of Advanced Materials and Engineering, Sungkyunkwan University (SKKU)School of Advanced Materials and Engineering, Sungkyunkwan University (SKKU)Center for Nanophase Materials Sciences, Oak Ridge National LaboratoryCenter for Nanophase Materials Sciences, Oak Ridge National LaboratorySchool of Advanced Materials and Engineering, Sungkyunkwan University (SKKU)Abstract Hafnium oxide-based ferroelectrics have been extensively studied because of their existing ferroelectricity, even in ultra-thin film form. However, studying the weak response from ultra-thin film requires improved measurement sensitivity. In general, resonance-enhanced piezoresponse force microscopy (PFM) has been used to characterize ferroelectricity by fitting a simple harmonic oscillation model with the resonance spectrum. However, an iterative approach, such as traditional least squares (LS) fitting, is sensitive to noise and can result in the misunderstanding of weak responses. In this study, we developed the deep neural network (DNN) hybrid with deep denoising autoencoder (DDA) and principal component analysis (PCA) to extract resonance information. The DDA/PCA-DNN improves the PFM sensitivity down to 0.3 pm, allowing measurement of weak piezoresponse with low excitation voltage in 10-nm-thick Hf0.5Zr0.5O2 thin films. Our hybrid approaches could provide more chances to explore the low piezoresponse of the ultra-thin ferroelectrics and could be applied to other microscopic techniques.https://doi.org/10.1038/s41524-023-00982-0 |
| spellingShingle | Panithan Sriboriboon Huimin Qiao Owoong Kwon Rama K. Vasudevan Stephen Jesse Yunseok Kim Deep learning for exploring ultra-thin ferroelectrics with highly improved sensitivity of piezoresponse force microscopy npj Computational Materials |
| title | Deep learning for exploring ultra-thin ferroelectrics with highly improved sensitivity of piezoresponse force microscopy |
| title_full | Deep learning for exploring ultra-thin ferroelectrics with highly improved sensitivity of piezoresponse force microscopy |
| title_fullStr | Deep learning for exploring ultra-thin ferroelectrics with highly improved sensitivity of piezoresponse force microscopy |
| title_full_unstemmed | Deep learning for exploring ultra-thin ferroelectrics with highly improved sensitivity of piezoresponse force microscopy |
| title_short | Deep learning for exploring ultra-thin ferroelectrics with highly improved sensitivity of piezoresponse force microscopy |
| title_sort | deep learning for exploring ultra thin ferroelectrics with highly improved sensitivity of piezoresponse force microscopy |
| url | https://doi.org/10.1038/s41524-023-00982-0 |
| work_keys_str_mv | AT panithansriboriboon deeplearningforexploringultrathinferroelectricswithhighlyimprovedsensitivityofpiezoresponseforcemicroscopy AT huiminqiao deeplearningforexploringultrathinferroelectricswithhighlyimprovedsensitivityofpiezoresponseforcemicroscopy AT owoongkwon deeplearningforexploringultrathinferroelectricswithhighlyimprovedsensitivityofpiezoresponseforcemicroscopy AT ramakvasudevan deeplearningforexploringultrathinferroelectricswithhighlyimprovedsensitivityofpiezoresponseforcemicroscopy AT stephenjesse deeplearningforexploringultrathinferroelectricswithhighlyimprovedsensitivityofpiezoresponseforcemicroscopy AT yunseokkim deeplearningforexploringultrathinferroelectricswithhighlyimprovedsensitivityofpiezoresponseforcemicroscopy |