Reconstruction of nanoscale particles from single-shot wide-angle FEL diffractions patterns with physics-informed neural networks

TL;DR

This paper presents a physics-informed neural network approach for real-time 3D reconstruction of nanoscale particles from single-shot wide-angle diffraction patterns, enabling detailed structural analysis of fragile objects.

Contribution

It introduces a novel neural network method that efficiently reconstructs 3D structures from 2D diffraction images, outperforming existing algorithms in speed and accuracy.

Findings

Successfully reconstructs 3D models of nanoclusters from diffraction data

Uncovers new geometric structures consistent with experimental data

Achieves high-precision reconstructions suitable for real-time analysis

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.