Abstract:Recent advances in scanning transmission electron and scanning probe microscopies have opened exciting opportunities in probing the materials structural parameters and various functional properties in real space with angstrom-level precision. This progress has been accompanied by an exponential increase in the size and quality of datasets produced by microscopic and spectroscopic experimental techniques. These developments necessitate adequate methods for extracting relevant physical and chemical information from the large datasets, for which a priori information on the structures of various atomic configurations and lattice defects is limited or absent. Here we demonstrate an application of deep neural networks to extract information from atomically resolved images including location of the atomic species and type of defects.We develop a "weakly-supervised" approach that uses information on the coordinates of all atomic species in the image, extracted via a deep neural network, to identify a rich variety of defects that are not part of an initial training set. We further apply our approach to interpret complex atomic and defect transformation, including switching between different coordination of silicon dopants in graphene as a function of time, formation of peculiar silicon dimer with mixed 3-fold and 4-fold coordination, and the motion of molecular "rotor". This deep learning based approach resembles logic of a human operator, but can be scaled leading to significant shift in the way of extracting and analyzing information from raw experimental data. Keywords:STEM, neural networks, weakly-supervised learning, graphene, TMDC. 3In the last decade, the proliferation of electron microscopy and scanning probe microscopy techniques have generated massive amounts of data on local chemical structure and atomic transformation. [1][2][3] Since the advent of aberration corrected Scanning Transmission Electron Microscopy (STEM), atomically resolved images of multiple materials classes ranging from multiferroics, semiconductors, and superconductors have become common. [4][5][6][7][8] The further impetus to this field was given by the development of atomically resolved dynamic studies, when the dynamic changes in matter on the atomic level are visualized. These traditionally include the thermal and chemical processes enabled by advanced thermal and environmental holders. 9,10 More recently, progressively more attention is being attracted to the dynamic processes induced by the electron beam irradiation, 11-14 especially promising in the context of e-beam atomic fabrication. [15][16][17] Similar advances are achieved in the field of atomically resolved scanning tunneling (STM) and atomic force microscopy (AFM). The recent famous examples include direct imaging of chemical bonds in molecules, 18 visualizing atomic collapse in artificial nuclei on graphene, 19 and inferring mechanisms behind fundamental physical phenomena, such as high-T c superconductivity, from single atom defect induced scattering patterns. 20 I...

Topological defects in ferroic materials are attracting much attention both as a playground of unique physical phenomena and for potential applications in reconfigurable electronic devices. Here, we explore electronic transport at artificially created ferroelectric vortices in BiFeO 3 thin films. The creation of one-dimensional conductive channels activated at voltages as low as 1 V is demonstrated. We study the electronic as well as the static and dynamic polarization structure of several topological defects using a combination of first-principles and phase-field modelling. The modelling predicts that the core structure can undergo a reversible transformation into a metastable twist structure, extending charged domain walls segments through the film thickness. The vortex core is therefore a dynamic conductor controlled by the coupled response of polarization and electron-mobile-vacancy subsystems with external bias. This controlled creation of conductive one-dimensional channels suggests a pathway for the design and implementation of integrated oxide electronic devices based on domain patterning.

Ferroelectric materials have remained one of the foci of condensed matter physics and materials science for over 50 years. In the last 20 years, the development of voltage-modulated scanning probe microscopy techniques, exemplified by Piezoresponse force microscopy (PFM) and associated time-and voltage spectroscopies, opened a pathway to explore these materials on a single-digit nanometer level. Consequently, domain structures, walls and polarization dynamics can now be imaged in real space. More generally, PFM has allowed studying electromechanical coupling in a broad variety of materials ranging from ionics to biological systems. It can also be anticipated that the recent Nobel prize 1 in molecular electromechanical machines will result in rapid growth in interest in PFM as a method to probe their behavior on single device and device assembly levels. However, the broad introduction of PFM also resulted in a growing number of reports on nearly-ubiquitous presence of ferroelectric-like phenomena including remnant polar states and electromechanical hysteresis loops in materials which are non-ferroelectric in the bulk, or in cases where size effects are expected to suppress ferroelectricity. While in certain cases plausible physical mechanisms can be suggested, there is remarkable similarity in observed behaviors, irrespective of the materials system. In this review, we summarize the basic principles of PFM, briefly discuss the features of ferroelectric surfaces salient to PFM imaging and spectroscopy, and summarize existing reports on ferroelectric-like responses in non-classical ferroelectric materials. We further discuss possible mechanisms behind observed behaviors, and possible experimental strategies for their identification.3

Understanding elementary mechanisms behind solid-state phase transformations and reactions is the key to optimizing desired functional properties of many technologically relevant materials. Recent advances in scanning transmission electron microscopy (STEM) allow the real-time visualization of solid-state transformations in materials, including those induced by an electron beam and temperature, with atomic resolution. However, despite the ever-expanding capabilities for high-resolution data acquisition, the inferred information about kinetics and thermodynamics of the process and single defect dynamics and interactions is minima, due to the inherent limitations of manual ex-situ analysis of the collected volumes of data. To circumvent this problem, we developed a deep learning framework for dynamic STEM imaging that is trained to find the structures (defects) that break a crystal lattice periodicity and apply it for mapping solid state reactions and transformations in layered WS 2 doped with Mo. This framework allows extracting thousands of lattice defects from raw STEM data (single images and movies) in a matter of seconds, which are then classified into different categories using unsupervised clustering methods. We further expanded our framework to extract parameters of diffusion for the sulfur vacancies and analyzed transition probabilities associated with switching between different configurations of defect complexes consisting of Mo dopant and sulfur vacancy, providing insight into point defect dynamics and reactions. This approach is universal and its application to beam induced reactions allows mapping chemical transformation pathways in solids at the atomic level. _______________________ * sergei2@ornl.gov *