Mask or Enhance: Data Curation Aiding the Discovery of Piezoresponse Force Microscopy Contributors

Mask or Enhance: Data Curation Aiding the Discovery of Piezoresponse Force Microscopy Contributors
复制标题

掩盖或增强:数据管理有助于发现压电响应力显微镜贡献者

DOI:
10.1002/apxr.202200090
复制
发表时间:
2023
期刊:
Advanced Physics Research
影响因子:
--
通讯作者:
Bassiri‐Gharb, Nazanin
Bassiri‐Gharb, Nazanin
中科院分区:
--
文献类型:
--
作者:
Ligonde, Gardy Kevin;Williams, Kerisha N.;Gaponenko, Iaroslav;Bassiri‐Gharb, Nazanin

文献摘要

参考文献

相似文献

压电响应力显微镜(PFM)通常用于探测铁电和压电材料的纳米级机电响应。然而,在对恢复信号的解释方面仍然存在许多挑战。具体来说,许多非铁电因素会影响测量的响应,包括静电、电荷注入和捕获以及地形串扰。最近,机器学习(ML)已被用于识别复杂数据系统中的多个贡献者,例如PFM响应。在PFM技术的ML方法中,维度堆叠提供了实质性的进步,可以在不同数据维度跨越不同范围的材料响应中编码物理和/或化学相关性。然而,维度堆叠需要对每个维度进行适当的缩放(在ML分析之前),以尽量减少不希望的信息损失。本文讨论了全局和局部尺度参数聚类对谐振PFM (RPFM)偏振开关实验的影响。具体来说,尺度参数的维度叠加可以掩盖或增强铁电和非铁电行为,并有助于识别各种有助于测量RPFM响应的物理现象。本研究强调了数据管理对机器学习的重要性,以及它在识别基于扫描探针显微镜(SPM)的多维数据技术(如共振和/或光谱SPM)的信号贡献者方面的作用。
Piezoresponse force microscopy (PFM) is routinely used to probe the nanoscale electromechanical response of ferroelectric and piezoelectric materials. However, many challenges remain in the interpretation of the recovered signal. Specifically, many non‐ferroelectric contributions affect the measured response, ranging from electrostatics, to charge injection and trapping, and topographic cross‐talk. Recently, machine learning (ML) has been utilized to identify multiple contributors within complex data systems, such as PFM response. A substantial advancement in ML approaches for PFM techniques is offered by dimensional stacking, enabling encoding of physical and/or chemical correlations within the materials' response across different data dimensions spanning varying ranges. However, dimensional stacking requires appropriate scaling for each dimension (before ML analysis) to minimize undesired information loss. Here, the impact of clustering globally and locally scaled parameters in polarization switching experiments via resonant PFM (RPFM) are discussed. Specifically, dimensional stacking of scaled parameters can mask or enhance ferroelectric and non‐ferroelectric behaviors, and aid identification of various physical phenomena contributing to the measured RPFM response. This study highlights the importance of data curation for ML, and its role in identifying signal contributors to scanning probe microscopy (SPM)‐based techniques with multidimensional data, such as resonant and/or spectroscopic SPM.
DOI: 10.1021/acsnano.8b02208
发表时间: 2018-06-01
期刊: ACS NANO
影响因子: 17.1
作者:
Rashidi, Mohammad;Wolkow, Robert A.
通讯作者: Wolkow, Robert A.
DOI: 10.1002/admi.202001648
发表时间: 2020-12-10
影响因子: 5.4
作者:
Abbasi, Kevin;Smith, Hugh;Sehirlioglu, Alp
通讯作者: Sehirlioglu, Alp
带激发压电响应力显微镜成像和光谱学中间接形貌串扰的解耦
DOI: --
发表时间: 2016
期刊:
影响因子: --
作者:
Sang Mo Yang;L. Mazet;M. Okatan;S. Jesse;G. Niu;T. Schroeder;S. Schamm;C. Dubourdieu;A. Baddorf;Sergei V. Kalinin
通讯作者: Sergei V. Kalinin
DOI: 10.1002/adma.202206237
发表时间: 2022-10-21
期刊: ADVANCED MATERIALS
影响因子: 29.4
作者:
Buragohain, Pratyush;Lu, Haidong;Gruverman, Alexei
通讯作者: Gruverman, Alexei
DOI: 10.1002/adma.202002425
发表时间: 2020-08-14
期刊: ADVANCED MATERIALS
影响因子: 29.4
作者:
Griffin, Lee A.;Gaponenko, Iaroslav;Bassiri-Gharb, Nazanin
通讯作者: Bassiri-Gharb, Nazanin