AutoPhaseNN: unsupervised physics-aware deep learning of 3D nanoscale Bragg coherent diffraction imaging

Journal Article · 02 June 2022 · npj Computational Materials

DOI: https://doi.org/10.1038/s41524-022-00803-w · OSTI ID:1871070

Yao, Yudong ; Chan, Henry ; Sankaranarayanan, Subramanian; Balaprakash, Prasanna; Harder, Ross J.; Cherukara, Mathew J.

Abstract The problem of phase retrieval underlies various imaging methods from astronomy to nanoscale imaging. Traditional phase retrieval methods are iterative and are therefore computationally expensive. Deep learning (DL) models have been developed to either provide learned priors or completely replace phase retrieval. However, such models require vast amounts of labeled data, which can only be obtained through simulation or performing computationally prohibitive phase retrieval on experimental datasets. Using 3D X-ray Bragg coherent diffraction imaging (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 imaging physics into the DL model during training, AutoPhaseNN learns to invert 3D BCDI data in a single shot without ever being shown real space images. Once trained, AutoPhaseNN can be effectively used in the 3D BCDI data inversion about 100× faster than iterative phase retrieval methods while providing comparable image quality.

• Research Organization: Argonne National Laboratory (ANL), Argonne, IL (United States)
• Sponsoring Organization: USDOE; USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities Division
• Grant/Contract Number: AC02-06CH11357
• OSTI ID: 1871070
• Journal Information: npj Computational Materials, Journal Name: npj Computational Materials Journal Issue: 1 Vol. 8; ISSN 2057-3960
• Publisher: Nature Publishing GroupCopyright Statement
• Country of Publication: United Kingdom
• Language: English