Deep neural networks in real-time coherent diffraction imaging
Abstract not provided.
SEARCH · Search NASA
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Abstract not provided.
Today, most X-ray pixel detectors used at light sources transmit raw pixel data off the detector ASIC. With the availability of more advanced ASIC technology nodes for scientific application, more digital functionalities from the computing domains (e.g., compression) can be integrated directly into a detector ASIC to increase data velocity. In this paper, we describe a lightweight, user-configurable detector ASIC digital architecture with on-chip compression which can be implemented in 130 nm technologies in a reasonable area on the ASIC periphery. In addition, we present a design to efficiently handle the variable data from the stream of parallel compressors. The architecture includes user-selectable lossy and lossless compression blocks. The impact of lossy compression algorithms is evaluated on simulated and experimental X-ray ptychography datasets. This architecture is a practical approach to increase pixel detector frame rates towards the continuous 1 MHz regime for not only coherent imaging techniques such as ptychography, but also for other diffraction techniques at X-ray light sources.
We have installed and tested an Olympus LEXT confocal microscope at the 34-ID-C beamline of the Advanced Photon Source (APS). The beamline is for Coherent X-ray Diffraction (CXD) experiments in which a nanometre-sized crystal is aligned inside a focussed X-ray beam. The microscope was required for three-dimensional (3D) sample alignment to get around sphere-of-confusion issues when locating Bragg peaks in reciprocal space. In this way, and by use of strategic sample preparations, we have succeeded in measuring six Bragg peaks from a single 200 nm gold crystal and obtained six projections of its internal displacement field. This enables the clear identification of stacking-fault bands within the crystal. The confocal alignment method will allow a full determination of the strain tensor provided three or more Bragg reflections from the same crystal are found.
This paper reports improved reconstruction of complex wave fields from extended objects. The combination of ptychography with Fresnel diffractive imaging results in better reconstructions with fewer iterations required to convergence than either method considered separately. The method is applied to retrieve the projected thickness of a gold microstructure and comparative results using ptychography and Fresnel diffractive imaging are presented.
We demonstrate a resolution of 45 nm with a sample size down to 3 μm × 3 μm is achieved in a short exposure time of 2 s, from the diffraction pattern generated by a table-top high harmonic source at around 30 nm. By using a narrow-bandwidth focusing mirror, the diffraction pattern's quality is improved and the required exposure time is significantly reduced. In order to obtain a high quality of the reconstructed image, the ratio of the beam size to the sample size and the curvature of the focused beam need to be considered in the reconstruction process. This new experimental scheme is very promising for imaging sub-10 nm scale objects with a table-top source based on a small inexpensive femtosecond laser system.
X-ray free electron lasers (XFELs) create new possibilities for structural studies of biological objects that extend beyond what is possible with synchrotron radiation. Serial femtosecond crystallography has allowed high-resolution structures to be determined from micro-meter sized crystals, whereas single particle coherent X-ray imaging requires development to extend the resolution beyond a few tens of nanometers. Here we describe an intermediate approach: the XFEL imaging of biological assemblies with helical symmetry. We collected X-ray scattering images from samples of microtubules injected across an XFEL beam using a liquid microjet, sorted these images into class averages, merged these data into a diffraction pattern extending to 2 nm resolution, and reconstructed these data into a projection image of the microtubule. Details such as the 4 nm tubulin monomer became visible in this reconstruction. These results illustrate the potential of single-molecule X-ray imaging of biological assembles with helical symmetry at room temperature.
Abstract Domain wall structures form spontaneously due to epitaxial misfit during thin film growth. Imaging the dynamics of domains and domain walls at ultrafast timescales can provide fundamental clues to features that impact electrical transport in electronic devices. Recently, deep learning based methods showed promising phase retrieval (PR) performance, allowing intensity-only measurements to be transformed into snapshot real space images. While the Fourier imaging model involves complex-valued quantities, most existing deep learning based methods solve the PR problem with real-valued based models, where the connection between amplitude and phase is ignored. To this end, we involve complex numbers operation in the neural network to preserve the amplitude and phase connection. Therefore, we employ the complex-valued neural network for solving the PR problem and evaluate it on Bragg coherent diffraction data streams collected from an epitaxial La 2-x Sr x CuO 4 (LSCO) thin film using an X-ray Free Electron Laser (XFEL). Our proposed complex-valued neural network based approach outperforms the traditional real-valued neural network methods in both supervised and unsupervised learning manner. Phase domains are also observed from the LSCO thin film at an ultrafast timescale using the complex-valued neural network.
Abstract not provided
Ptychographic imaging is a powerful means of imaging beyond the resolution limits of typical x-ray optics. Capturing recovered images from raw ptychographic data, however, requires the solution of an inverse problem, namely, phase retrieval. Phase retrieval algorithms are computationally expensive, which precludes real-time imaging. In this work, we propose PtychoNN, an approach to solve the ptychography data inversion problem based on a deep convolutional neural network. We demonstrate how the proposed method can be used to predict real-space structure and phase at each scan point solely from the corresponding far-field diffraction data. Our results demonstrate the practical application of machine learning to recover high fidelity amplitude and phase contrast images of a real sample hundreds of times faster than current ptychography reconstruction packages. Furthermore, by overcoming the constraints of iterative model-based methods, we can significantly relax sampling constraints on data acquisition while still producing an excellent image of the sample. Besides drastically accelerating acquisition and analysis, this capability has profound implications for the imaging of dose sensitive, dynamic, and extremely voluminous samples.
Abstract not provided
Not Available
Not Available
Please check the README file for more information about the dataset.