Reconstruction of nanoscale particles from single-shot wide-angle FEL diffractions patterns with physics-informed neural networks
arXiv:2101.09136 · doi:10.1103/PhysRevE.103.053312
Abstract
Single-shot wide-angle diffraction imaging is a widely used method to investigate the structure of non-crystallizing objects such as nanoclusters, large proteins or even viruses. Its main advantage is that information about the three-dimensional structure of the object is already contained in a single image. This makes it useful for the reconstruction of fragile and non-reproducible particles without the need for tomographic measurements. However, currently there is no efficient numerical inversion algorithm available that is capable of determining the object's structure in real time. Neural networks, on the other hand, excel in image processing tasks suited for such purpose. Here we show how a physics-informed deep neural network can be used to reconstruct complete three-dimensional object models of uniform, convex particles on a voxel grid from single two-dimensional wide-angle scattering patterns. We demonstrate its universal reconstruction capabilities for silver nanoclusters, where the network uncovers novel geometric structures that reproduce the experimental scattering data with very high precision.
References in corpus (20)
- Machine learning and the physical sciences
- Searching for Exotic Particles in High-Energy Physics with Deep Learning
- Femtosecond Diffractive Imaging with a Soft-X-ray Free-Electron Laser
- X-ray image reconstruction from a diffraction pattern alone
- Deep-learning Top Taggers or The End of QCD?
- The Machine Learning Landscape of Top Taggers
- Learning Properties of Ordered and Disordered Materials from Multi-fidelity Data
- Three-dimensional structure determination from a single view
- Dynamics in a cluster under the influence of intense femtosecond hard x-ray pulses
- Real-time coherent diffraction inversion using deep generative networks
- Coherent diffractive imaging of single helium nanodroplets with a high harmonic generation source
- Three-Dimensional Shapes of Spinning Helium Nanodroplets
- Real-time 3D Nanoscale Coherent Imaging via Physics-aware Deep Learning
- Low-signal limit of X-ray single particle imaging
- Fundamental Limits of "Ankylography" due to Dimensional Deficiency
- Deep neural networks for classifying complex features in diffraction images
- Exascale Deep Learning for Scientific Inverse Problems
- Reconstruction of 3-D Atomic Distortions from Electron Microscopy with Deep Learning
- Fast reconstruction of single-shot wide-angle diffraction images through deep learning
- The modulus of the Fourier transform on a sphere determines 3-dimensional convex polytopes