Learning from Imperfections: Predicting Structure and Thermodynamics from Atomic Imaging of Fluctuations.

In materials characterization, traditionally a single experimental sample is used to derive information about a single point in the composition space, while the imperfections, impurities, and stochastic details of material structure are deemed irrelevant or complicating factors in the analysis. Here we demonstrate that atomic-scale studies of a single nominal composition can provide information about microstructures and thermodynamic response over a finite area of chemical space. Using the principles of statistical inference, we develop a framework for incorporating structural fluctuations into statistical mechanical models and use it to solve the inverse problem of deriving effective interatomic interactions responsible for elemental segregation in a La5/8Ca3/8MnO3 thin film. The results are further analyzed by a variational autoencoder to detect anomalous behavior in the composition phase diagram. This study provides a framework for creating generative models from a combination of multiple experimental data and provides direct insight into the driving forces for cation segregation in manganites.

Direct atomic fabrication and dopant positioning in Si using electron beams with active real-time image-based feedback.

Semiconductor fabrication is a mainstay of modern civilization, enabling the myriad applications and technologies that underpin everyday life. However, while sub-10 nanometer devices are already entering the mainstream, the end of the Moore's law roadmap still lacks tools capable of bulk semiconductor fabrication on sub-nanometer and atomic levels, with probe-based manipulation being explored as the only known pathway. Here we demonstrate that the atomic-sized focused beam of a scanning transmission electron microscope can be used to manipulate semiconductors such as Si on the atomic level, inducing growth of crystalline Si from the amorphous phase, reentrant amorphization, milling, and dopant front motion. These phenomena are visualized in real-time with atomic resolution. We further implement active feedback control based on real-time image analytics to automatically control the e-beam motion, enabling shape control and providing a pathway for atom-by-atom correction of fabricated structures in the near future. These observations open a new epoch for atom-by-atom manufacturing in bulk, the long-held dream of nanotechnology.

Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations.

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 data sets produced by microscopic and spectroscopic experimental techniques. These developments necessitate adequate methods for extracting relevant physical and chemical information from the large data sets, 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.

Knowledge Extraction from Atomically Resolved Images.

Tremendous strides in experimental capabilities of scanning transmission electron microscopy and scanning tunneling microscopy (STM) over the past 30 years made atomically resolved imaging routine. However, consistent integration and use of atomically resolved data with generative models is unavailable, so information on local thermodynamics and other microscopic driving forces encoded in the observed atomic configurations remains hidden. Here, we present a framework based on statistical distance minimization to consistently utilize the information available from atomic configurations obtained from an atomically resolved image and extract meaningful physical interaction parameters. We illustrate the applicability of the framework on an STM image of a FeSexTe1-x superconductor, with the segregation of the chalcogen atoms investigated using a nonideal interacting solid solution model. This universal method makes full use of the microscopic degrees of freedom sampled in an atomically resolved image and can be extended via Bayesian inference toward unbiased model selection with uncertainty quantification.

UV-activated ZnO films on a flexible substrate for room temperature O2 and H2O sensing.

We demonstrate that UV-light activation of polycrystalline ZnO films on flexible polyimide (Kapton) substrates can be used to detect and differentiate between environmental changes in oxygen and water vapor. The in-plane resistive and impedance properties of ZnO films, fabricated from bacteria-derived ZnS nanoparticles, exhibit unique resistive and capacitive responses to changes in O2 and H2O. We propose that the distinctive responses to O2 and H2O adsorption on ZnO could be utilized to statistically discriminate between the two analytes. Molecular dynamic simulations (MD) of O2 and H2O adsorption energy on ZnO surfaces were performed using the large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) with a reactive force-field (ReaxFF). These simulations suggest that the adsorption mechanisms differ for O2 and H2O adsorption on ZnO, and are governed by the surface termination and the extent of surface hydroxylation. Electrical response measurements, using DC resistance, AC impedance spectroscopy, and Kelvin Probe Force Microscopy (KPFM), demonstrate differences in response to O2 and H2O, confirming that different adsorption mechanisms are involved. Statistical and machine learning approaches were applied to demonstrate that by integrating the electrical and kinetic responses the flexible ZnO sensor can be used for detection and discrimination between O2 and H2O at low temperature.

Deep data mining in a real space: separation of intertwined electronic responses in a lightly doped BaFe2As2.

Electronic interactions present in material compositions close to the superconducting dome play a key role in the manifestation of high-T c superconductivity. In many correlated electron systems, however, the parent or underdoped states exhibit strongly inhomogeneous electronic landscape at the nanoscale that may be associated with competing, coexisting, or intertwined chemical disorder, strain, magnetic, and structural order parameters. Here we demonstrate an approach based on a combination of scanning tunneling microscopy/spectroscopy and advanced statistical learning for an automatic separation and extraction of statistically significant electronic behaviors in the spin density wave regime of a lightly (∼1%) gold-doped BaFe2As2. We show that the decomposed STS spectral features have a direct relevance to fundamental physical properties of the system, such as SDW-induced gap, pseudogap-like state, and impurity resonance states.