Revealing ferroelectric switching character using deep recurrent neural networks
Revealing ferroelectric switching character using deep recurrent neural networks
复制标题
DOI：
10.1038/s41467-019-12750-0
复制
发表时间：
2019-10-22
影响因子：
16.6
通讯作者：
Martin, Lane W.
中科院分区：
文献类型：
--
作者：
Agar, Joshua C.;Naul, Brett;Martin, Lane W.
操纵磁畴的能力是铁电体应用功能的基础。虽然已经有对域结构的受控纳米级操纵来驱动涌现特性的演示，但这种方法缺乏自动操纵所需的内部反馈回路。在这里，我们使用深度序列到序列自动编码器，从具有分层域结构的拉伸应变 PbZr0.2Ti0.8O3 的压电响应力谱中自动提取纳米级铁电开关的潜在特征。我们确定了压电响应和悬臂共振磁滞回线的特征行为，从而可以对纳米级开关机制进行分类和量化。具体来说，我们确定了与带电畴壁的成核和生长相关的弹性硬化事件。这项工作证明了无监督神经网络在从纳米级多通道高光谱图像中学习材料物理响应特征方面的功效，并提供了利用操作光谱的新功能，可以自动操纵材料中的纳米级结构。
The ability to manipulate domains underpins function in applications of ferroelectrics. While there have been demonstrations of controlled nanoscale manipulation of domain structures to drive emergent properties, such approaches lack an internal feedback loop required for automatic manipulation. Here, using a deep sequence-to-sequence autoencoder we automate the extraction of latent features of nanoscale ferroelectric switching from piezo-response force spectroscopy of tensile-strained PbZr0.2Ti0.8O3 with a hierarchical domain structure. We identify characteristic behavior in the piezoresponse and cantilever resonance hysteresis loops, which allows for the classification and quantification of nanoscale-switching mechanisms. Specifically, we identify elastic hardening events which are associated with the nucleation and growth of charged domain walls. This work demonstrates the efficacy of unsupervised neural networks in learning features of a material's physical response from nanoscale multichannel hyperspectral imagery and provides new capabilities in leveraging in operando spectroscopies that could enable the automated manipulation of nanoscale structures in materials.