More Like this

1. Proximity labeling expansion microscopy (PL-ExM) evaluates interactome labeling techniques

   https://doi.org/10.1039/D4TB00516C  

   Park, Sohyeon; Wang, Xiaorong; Mo, Yajin; Zhang, Sicheng; Li, Xiangpeng; Fong, Katie C; Yu, Clinton; Tran, Arthur A; Scipioni, Lorenzo; Dai, Zhipeng; et al (August 2024, Journal of Materials Chemistry B)

   Proximity labeling expansion microscopy (PL-ExM) visualizes superresolution structures of interactome on widely accessible light microscopes, enabling the assessment of the precision and efficiency of proximity labeling techniques. 

   more » « less
2. Quantitative infrared photothermal microscopy

   https://doi.org/10.1117/12.2545159  

   Pavlovetc, Ilia M.; Podshivaylov, Eduard A.; Frantsuzov, Pavel A.; Hartland, Gregory V.; Kuno, Masaru K. (February 2020, Proc. SPIE 11246, Single Molecule Spectroscopy and Super-resolution Imaging XIII)

   Gregor, Ingo; Erdmann, Rainer; Koberling, Felix (Ed.)

   Infrared photothermal heterodyne imaging (IR-PHI) represents a convenient table top approach for conducting superresolution imaging and spectroscopy throughout the all-important mid infrared (MIR) spectral region. Although IR-PHI provides label-free, superresolution MIR absorption information, it is not quantitative. In this study, we establish quantitative relationships between observed IR-PHI signals and relevant photothermal parameters of investigated specimens. Specifically, we conduct a size series analysis of different radii polystyrene (PS) beads so as to quantitatively link IR-PHI signal contrast to specimen heat capacity, MIR peak absorption cross-section, and scattering cross-section at IR-PHI’s probe wavelength. 

   more » « less
3. Extending a Physics-informed Machine-learning Network for Superresolution Studies of Rayleigh–Bénard Convection

   https://doi.org/10.3847/1538-4357/ad1c55  

   Salim, Diane M.; Burkhart, Blakesley; Sondak, David (March 2024, The Astrophysical Journal)

   Abstract Advancing our understanding of astrophysical turbulence is bottlenecked by the limited resolution of numerical simulations that may not fully sample scales in the inertial range. Machine-learning (ML) techniques have demonstrated promise in upscaling resolution in both image analysis and numerical simulations (i.e., superresolution). Here we employ and further develop a physics-constrained convolutional neural network ML model called “MeshFreeFlowNet” (MFFN) for superresolution studies of turbulent systems. The model is trained on both the simulation images and the evaluated partial differential equations (PDEs), making it sensitive to the underlying physics of a particular fluid system. We develop a framework for 2D turbulent Rayleigh–Bénard convection generated with theDedaluscode by modifying the MFFN architecture to include the full set of simulation PDEs and the boundary conditions. Our training set includes fully developed turbulence sampling Rayleigh numbers (Ra) ofRa= 10⁶–10¹⁰. We evaluate the success of the learned simulations by comparing the power spectra of the directDedalussimulation to the predicted model output and compare both ground-truth and predicted power spectral inertial range scalings to theoretical predictions. We find that the updated network performs well at allRastudied here in recovering large-scale information, including the inertial range slopes. The superresolution prediction is overly dissipative at smaller scales than that of the inertial range in all cases, but the smaller scales are better recovered in more turbulent than laminar regimes. This is likely because more turbulent systems have a rich variety of structures at many length scales compared to laminar flows. 

   more » « less
4. AI-assisted superresolution cosmological simulations

   https://doi.org/10.1073/pnas.2022038118  

   Li, Yin; Ni, Yueying; Croft, Rupert_A_C; Di_Matteo, Tiziana; Bird, Simeon; Feng, Yu (May 2021, Proceedings of the National Academy of Sciences)

   Significance Cosmological simulations are indispensable for understanding our Universe, from the creation of the cosmic web to the formation of galaxies and their central black holes. This vast dynamic range incurs large computational costs, demanding sacrifice of either resolution or size and often both. We build a deep neural network to enhance low-resolution dark-matter simulations, generating superresolution realizations that agree remarkably well with authentic high-resolution counterparts on their statistical properties and are orders-of-magnitude faster. It readily applies to larger volumes and generalizes to rare objects not present in the training data. Our study shows that deep learning and cosmological simulations can be a powerful combination to model the structure formation of our Universe over its full dynamic range. 

   more » « less
5. Superresolution of GOES-16 ABI Bands to a Common High Resolution with a Convolutional Neural Network

   https://doi.org/10.1175/AIES-D-23-0065.1  

   White, Charles_H; Ebert-Uphoff, Imme; Haynes, John_M; Noh, Yoo-Jeong (April 2024, Artificial Intelligence for the Earth Systems)

   Abstract Superresolution is the general task of artificially increasing the spatial resolution of an image. The recent surge in machine learning (ML) research has yielded many promising ML-based approaches for performing single-image superresolution including applications to satellite remote sensing. We develop a convolutional neural network (CNN) to superresolve the 1- and 2-km bands on the GOES-R series Advanced Baseline Imager (ABI) to a common high resolution of 0.5 km. Access to 0.5-km imagery from ABI band 2 enables the CNN to realistically sharpen lower-resolution bands without significant blurring. We first train the CNN on a proxy task, which allows us to only use ABI imagery, namely, degrading the resolution of ABI bands and training the CNN to restore the original imagery. Comparisons at reduced resolution and at full resolution withLandsat-8/Landsat-9observations illustrate that the CNN produces images with realistic high-frequency detail that is not present in a bicubic interpolation baseline. Estimating all ABI bands at 0.5-km resolution allows for more easily combining information across bands without reconciling differences in spatial resolution. However, more analysis is needed to determine impacts on derived products or multispectral imagery that use superresolved bands. This approach is extensible to other remote sensing instruments that have bands with different spatial resolutions and requires only a small amount of data and knowledge of each channel’s modulation transfer function. Significance StatementSatellite remote sensing instruments often have bands with different spatial resolutions. This work shows that we can artificially increase the resolution of some lower-resolution bands by taking advantage of the texture of higher-resolution bands on theGOES-16ABI instrument using a convolutional neural network. This may help reconcile differences in spatial resolution when combining information across bands, but future analysis is needed to precisely determine impacts on derived products that might use superresolved bands. 

   more » « less