Joshua Agar and his colleagues studying nanoscale ferroelectrics are using deep neural networks to extract useful information from the massive amounts of data generated by their experiments. Applying this artificial intelligence method, Agar and his team have discovered—and visualized for the first time—a new mechanism of ferroelectric switching.
Ferroelectrics exhibit spontaneous electric polarization—as a result of small shifts in charged atoms—that can be reversed by the application of an external electric field. Despite promise in applications including next-generation low-power information storage/computation, energy efficiency via harvesting waste energy, and environmentally friendly solid-state cooling, a number of issues still need to be solved for these nanomaterials to reach their full potential.
Agar, an assistant professor of materials science and engineering, uses a multimodal hyperspectral imaging technique (through Oak Ridge National Laboratory) called band-excitation piezoresponse force microscopy, which measures the mechanical properties of the materials as they respond to electrical stimuli. These in situ characterization techniques allow for the direct observation of nanoscale processes in action.
“Our experiments involve touching the material with a cantilever and measuring the material’s properties as we drive it with an electrical field,” he says. “Essentially, we go to every single pixel and measure the response of a very small region of the material as we drive it through transformations.”
The technique yields vast amounts of information about how the material is responding and the kinds of processes that are happening as it transitions between different states, explains Agar.
“You get this map for every pixel with many spectra and different responses,” says Agar. “All this information comes out at once. The problem is how do you figure out what’s going on because the data is not clean—it’s noisy.”
The technique is described in an article in Nature Communications. Other authors include researchers from University of California, Berkeley; Lawrence Berkeley National Laboratory; the University of Texas at Arlington; Penn State University; and the Center for Nanophase Materials Science at ORNL.
Applying the neural network technique, which uses models employed in natural language processing, Agar and his colleagues were able to directly image and visualize an important subtlety in the switching of a classical ferroelectric material, lead zirconium titanate, which, prior to this, had never been done.
When the material switches its polarization state under an external electrical field, explains Agar, it forms a domain wall, or a boundary between two different orientations of polarization. Depending on the geometry, charges can then accumulate at that boundary. The modular conductivity at these domain wall interfaces is key to the material’s strong potential for use in transistors and memory devices.
“What we are detecting here from a physics perspective is the formation of different types of domain walls that are either charged or uncharged, depending on the geometry,” he says.
According to Agar, this discovery could not have been possible using more primitive machine learning approaches, as those techniques tend to use linear models to identify linear correlations. Such models cannot efficiently deal with structured data or make the complex correlations needed to understand the data generated by hyperspectral imaging.
This particular neural network approach could have immediate applications: “It could be used in electron microscopy, in scanning tunneling microscopy, and even in aerial photography,” he says. “It crosses boundaries.”