Revealing ferroelectric switching character using deep recurrent neural networks.

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 piezoresponse 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.

Machine Detection of Enhanced Electromechanical Energy Conversion in PbZr0.2 Ti0.8 O3 Thin Films.

Many energy conversion, sensing, and microelectronic applications based on ferroic materials are determined by the domain structure evolution under applied stimuli. New hyperspectral, multidimensional spectroscopic techniques now probe dynamic responses at relevant length and time scales to provide an understanding of how these nanoscale domain structures impact macroscopic properties. Such approaches, however, remain limited in use because of the difficulties that exist in extracting and visualizing scientific insights from these complex datasets. Using multidimensional band-excitation scanning probe spectroscopy and adapting tools from both computer vision and machine learning, an automated workflow is developed to featurize, detect, and classify signatures of ferroelectric/ferroelastic switching processes in complex ferroelectric domain structures. This approach enables the identification and nanoscale visualization of varied modes of response and a pathway to statistically meaningful quantification of the differences between those modes. Among other things, the importance of domain geometry is spatially visualized for enhancing nanoscale electromechanical energy conversion.

Effectiveness of a school-based deworming campaign in rural Kenya.

In 2007, the rate of intestinal helminth infection in primary school-aged children in a rural village in Southwestern Kenya was estimated to be at least 68%, based on direct stool smear. Since the 2007 survey, these same school children have been treated with 400-mg albendazole every 3 months. We repeated a cross-sectional stool survey in the same area in 2010 (i.e. 3 years later) to estimate the current parasite prevalence. While only 44.5% of children were infected in 2010, the decline was not as marked as one might expect from a well-managed quarterly deworming campaign. Due to the relative insensitivity of the technique utilized here-the direct smear examination of a single stool sample-we were only able to identify heavy infections, and the true rate of parasitism is likely much higher, suggesting heavy environmental contamination and rapid re-infection rates. Community education and sanitation improvements are needed for more definitive impact.