Automated analysis of evolving interfaces during in situ electron microscopy

Machine learning in electron microscopy for advanced nanocharacterization: current developments, available tools and future outlook

In the last few years, electron microscopy has experienced a new methodological paradigm aimed to fix the bottlenecks and overcome the challenges of its analytical workflow. Machine learning and artificial intelligence are answering this call providing powerful resources towards automation, exploration, and development. In this review, we evaluate the state-of-the-art of machine learning applied to electron microscopy (and obliquely, to materials and nano-sciences). We start from the traditional imaging techniques to reach the newest higher-dimensionality ones, also covering the recent advances in spectroscopy and tomography. Additionally, the present review provides a practical guide for microscopists, and in general for material scientists, but not necessarily advanced machine learning practitioners, to straightforwardly apply the offered set of tools to their own research. To conclude, we explore the state-of-the-art of other disciplines with a broader experience in applying artificial intelligence methods to their research (e.g., high-energy physics, astronomy, Earth sciences, and even robotics, videogames, or marketing and finances), in order to narrow down the incoming future of electron microscopy, its challenges and outlook.

Machine Learning to Reveal Nanoparticle Dynamics from Liquid-Phase TEM Videos

Liquid-phase transmission electron microscopy (TEM) has been recently applied to materials chemistry to gain fundamental understanding of various reaction and phase transition dynamics at nanometer resolution. However, quantitative extraction of physical and chemical parameters from the liquid-phase TEM videos remains bottlenecked by the lack of automated analysis methods compatible with the videos' high noisiness and spatial heterogeneity. Here, we integrate, for the first time, liquid-phase TEM imaging with our customized analysis framework based on a machine learning model called U-Net neural network. This combination is made possible by our workflow to generate simulated TEM images as the training data with well-defined ground truth. We apply this framework to three typical systems of colloidal nanoparticles, concerning their diffusion and interaction, reaction kinetics, and assembly dynamics, all resolved in real-time and real-space by liquid-phase TEM. A diversity of properties for differently shaped anisotropic nanoparticles are mapped, including the anisotropic interaction landscape of nanoprisms, curvature-dependent and staged etching profiles of nanorods, and an unexpected kinetic law of first-order chaining assembly of concave nanocubes. These systems representing properties at the nanoscale are otherwise experimentally inaccessible. Compared to the prevalent image segmentation methods, U-Net shows a superior capability to predict the position and shape boundary of nanoparticles from highly noisy and fluctuating background-a challenge common and sometimes inevitable in liquid-phase TEM videos. We expect our framework to push the potency of liquid-phase TEM to its full quantitative level and to shed insights, in high-throughput and statistically significant fashion, on the nanoscale dynamics of synthetic and biological nanomaterials.

In-situ electron microscopy mapping of an order-disorder transition in a superionic conductor

Solid-solid phase transitions are processes ripe for the discovery of correlated atomic motion in crystals. Here, we monitor an order-disorder transition in real-time in nanoparticles of the super-ionic solid, Cu_2-xSe. The use of in-situ high-resolution transmission electron microscopy allows the spatiotemporal evolution of the phase transition within a single nanoparticle to be monitored at the atomic level. The high spatial resolution reveals that cation disorder is nucleated at low co-ordination, high energy sites of the nanoparticle where cationic vacancy layers intersect with surface facets. Time-dependent evolution of the reciprocal lattice of individual nanoparticles shows that the initiation of cation disorder is accompanied by a ~3% compression of the anionic lattice, establishing a correlation between these two structural features of the lattice. The spatiotemporal insights gained here advance understanding of order-disorder transitions, ionic structure and transport, and the role of nanoparticle surfaces in phase transitions.

Control of Growth Front Evolution by Bi Additives during ZnAu Electrodeposition

The performance of many electrochemical energy storage systems can be compromised by the formation of metal dendrites during charging. Additives in the electrolyte represent a useful strategy to mitigate dendrite formation, but understanding the mechanisms involved requires knowledge of the nanoscale effects of additives during electrochemical deposition. Here we quantify the effects of an inorganic additive on the morphology of an evolving electrochemical growth front, using liquid cell electron microscopy to provide the necessary spatial and temporal resolution. We examine deposition of ZnAu on Au in the presence of Bi additive, and show that low concentrations of Bi delay but do not prevent the formation of growth front instabilities. We describe a model in which Bi segregates at the growth front and promotes the surface diffusion and relaxation of Zn, allowing better coverage of the initial Au electrode surface. A more precise knowledge of the mechanism of inorganic additive effects may help in designing electrolyte chemistry for battery and other applications where morphology control is essential.

Nanoscale evolution of interface morphology during electrodeposition

Control of interfacial morphology in electrochemical processes is essential for applications ranging from nanomanufacturing to batteries. Here, we quantify the evolution of an electrochemical growth front, using liquid cell electron microscopy to access unexplored length and time scales. During galvanostatic deposition of copper from an acidic electrolyte, we find that the growth front initially evolves consistent with kinetic roughening theory. Subsequently, it roughens more rapidly, consistent with diffusion-limited growth physics. However, the onset of roughening is strongly delayed compared to expectations, suggesting the importance of lateral diffusion of ions. Based on these growth regimes, we discuss morphological control and demonstrate the effects of two strategies, pulse plating and the use of electrolyte additives.

Understanding structure evolution during electrochemical growth is crucial in materials processing and design of devices such as batteries. Here, the authors image copper during electrodeposition to provide strategies for controlling interface morphology.