Argonne researchers have created an automatic technique that can fill in gaps in X-ray data. Putting together a jigsaw puzzle is a great activity for a rainy Sunday afternoon. But the somewhat more difficult process of quickly assembling 3D scientific jigsaw puzzles--atomic structures of different materials--has recently gotten a lot easier, thanks to new research that pairs high-powered X-ray beams with advanced computing methodologies. Researchers at the U.S. Department of Energy's (DOE) Argonne National Laboratory have developed a new technique that accelerates the solving of material structures from patterns uncovered in X-ray experiments. The technique allows researchers to study certain properties, such as corrosion or battery charging and discharging, in real time.

The problem of phase retrieval, or the algorithmic recovery of lost phase information from measured intensity alone, underlies various imaging methods from astronomy to nanoscale imaging. Traditional methods of phase retrieval are iterative in nature, and are therefore computationally expensive and time consuming. More recently, deep learning (DL) models have been developed to either provide learned priors to iterative phase retrieval or in some cases completely replace phase retrieval with networks that learn to recover the lost phase information from measured intensity alone. However, such models require vast amounts of labeled data, which can only be obtained through simulation or performing computationally prohibitive phase retrieval on hundreds of or even thousands of experimental datasets. Using a 3D nanoscale X-ray imaging modality (Bragg Coherent Diffraction Imaging or BCDI) as a representative technique, we demonstrate AutoPhaseNN, a DL-based approach which learns to solve the phase problem without labeled data. By incorporating the physics of the imaging technique into the DL model during training, AutoPhaseNN learns to invert 3D BCDI data from reciprocal space to real space in a single shot without ever being shown real space images. Once trained, AutoPhaseNN is about one hundred times faster than traditional iterative phase retrieval methods while providing comparable image quality.