Reconstruction quality in Far-field High-Energy Diffraction Microscopy (FF-HEDM) is limited by the spatial resolution of area detectors and the frequent occurrence of overlapping diffraction spots. To address these challenges, we developed a super-resolution (SR) framework using convolutional neural networks (CNNs) to recreate 2D diffraction peaks at up to x8 resolution from raw detector data. A specialized simulation tool was created to generate synthetic training datasets with varying degrees of peak overlap. Integrated into the Microstructural Imaging using Diffraction Analysis Software (MIDAS), the SR model improves the spatial accuracy and precision of 3D grain reconstruction by an order of magnitude. This approach provides a robust solution for investigation of complex micromechanical states and material classes where the analysis is limited by the presence of overlapping peaks. Furthermore, the methodology developed here can potentially be extended to other techniques that require sub-pixel accuracy for high-fidelity data analysis. • Sequential CNN Super-Resolution Pipeline: Developed a deep-learning framework that sequentially recreates high-resolution 2D diffraction peaks (x2, x4, and x8) from raw, pixelated detector data while strictly preserving total intensity. • Novel Training via SIMR-xrd: Introduced a specialized diffraction simulation tool, SIMR-xrd, to generate synthetic datasets with known ground truth and varying peak overlaps, overcoming the lack of experimental ground truth for model training. • Decade Improvement in Spatial Accuracy: Integration of the super-resolution model into the MIDAS reconstruction platform enhances the spatial accuracy and precision of 3D grain reconstructions by 10 times compared to standard detector resolutions. • Deconvolution of Complex Grain States: The model successfully deconvolves overlapping diffraction peaks from grains with similar orientations and close spatial proximity, enabling the investigation of micromechanical states in materials previously considered inaccessible to FF-HEDM.
Beniwal et al. (Sun,) studied this question.