[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124660-en":3,"doc-seo-124660-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124660,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Machine learning for classifying and interpreting coherent X-ray speckle patterns","Speckle patterns generated by coherent X-ray light are tightly linked to the internal structure of materials, yet turning those patterns into quantitative structural information remains difficult. This work examines how coherent X-ray speckle patterns relate to sample structures using a simplified 2D disk model, and evaluates whether machine learning can learn this relationship. A deep neural network is trained to classify speckle patterns by disk number density, achieving accurate classification for both non-dispersed and dispersed size distributions.","Machine learning for classifying and interpreting coherent X-ray speckle patterns  \nMingren Shen 1, Dina Sheyfer2, Troy David Loeffler3, Subramanian K.R. S. Sankaranarayanan3,5, G. Brian Stephenson4, Maria K. Y. Chan3, Dane Morgan 1  \n1 Department of Materials Science and Engineering, University of Wisconsin-Madison, Madison, Wisconsin, 53706, USA  \n2 X-ray Science Division, Argonne National Laboratory, Lemont, IL 60439, USA  \n3 Center for Nanoscale Materials, Argonne National Laboratory, Lemont, Illinois 60439, USA  \n4 Materials Science Division, Argonne National Laboratory, Lemont, IL 60439, USA  \n5. Department of Mechanical and Industrial Engineering, University of Illinois, Chicago IL – 60607, USA  \nAbstract  \nSpeckle patterns produced by coherent X-ray have a close relationship with the internal structure of materials but quantitative inversion of the relationship to determine structure from speckle patterns is challenging. Here, we investigate the link between coherent X-ray speckle patterns and sample structures using a model 2D disk system and explore the ability of machine learning to learn aspects of the relationship. Specifically, we train a deep neural network to classify the coherent X-ray speckle patterns according to the disk number density in the corresponding structure. It is demonstrated that the classification system is accurate for both non-disperse and disperse size distributions.  \n1. Introduction  \nCurrent and developing X-ray sources such as the advanced synchrotron sources, X-ray free electron lasers, and high harmonic generation sources[1,2] enable utilization of coherent X-ray light to investigate behavior in the time domain and structure at interatomic length scales. For example, X-ray photon correlation spectroscopy has been used by many researchers in materials science, including investigations of micro, nano, and atomic scale structures[3,4] and mechanisms[5], studying dynamics and correlation behaviors[6–8], revealing rich phenomena in complex material systems, e.g. multicomponent fluids[9] and metallic glasses[10], and in other areas. Coherent X-ray imaging methods have been used in many material applications to visualize the chemical composition at nanoscale resolution[11,12] and to study 3D lattice dynamics in nanocrystals[13], and in biology to image the 3D mass density distribution of a whole cell[14], and to reconstruct the 3D structure of the giant mimivirus particle[15] .  \nCoherent X-rays incident on a disordered sample generate X-ray speckle patterns, which are often difficult to interpret, especially to reconstruct molecular structure from the speckle patterns. Such reconstructions to date have often relied on complex, subjective algorithms or required multiple experiments, e.g., using phase retrieval algorithms to iterate between real and reciprocal space[16,17] or alternating projections[18], angles or sample positions[19] . The reconstruction problem occurs because only amplitude information is recorded in the detector and additional computation is required to recover phase information. Deep learning, if used properly, has been shown to be able to learn complex mapping between input space and output space automatically from data[20] and has been widely used for physics[21–24], chemistry[25], material science[26–29], health industry[30–32], etc. It is therefore of interest to explore whether recent developments in image analysis using deep learning might aid in the extraction of structural information from X-ray speckle patterns.  \nMachine learning or deep learning methods can help X-ray speckle pattern problems in three aspects, namely data collection, data transformation, and data analysis. For data collection, the main goal is to acquire high resolution and lower noise images. Konstantinova et al. use a convolutional neuralnetwork-based encode-decoder framework to reduce noises in X-ray images[33] and Cherukara et al. use  \nneural networks to boost low resolution scanning coheren","cbCairlgk5p27e27","https://ap.wps.com/l/cbCairlgk5p27e27","pdf",823759,1,25,"English","en",105,"# Abstract\n# 1. Introduction\n## Coherent X-ray sources and applications\n## Challenges in reconstructing structure from speckle patterns\n## Role of deep learning in data collection, transformation, and analysis\n## Labeled-data challenge and strategies","[{\"question\":\"Why are coherent X-ray speckle patterns difficult to interpret quantitatively?\",\"answer\":\"Detector measurements record mainly amplitude, so phase information must be recovered through additional computation. This makes direct reconstruction of molecular or structural information challenging and often requires complex iterative algorithms or multiple experiments.\"},{\"question\":\"What does this study use machine learning to accomplish?\",\"answer\":\"It trains a deep neural network to classify coherent X-ray speckle patterns based on the disk number density in the corresponding sample structure derived from a simplified 2D disk system.\"},{\"question\":\"How does the method perform for different disk size distributions?\",\"answer\":\"The classification system is demonstrated to be accurate for both non-disperse and disperse size distributions.\"}]","Machine learning for classifying and interpreting coherent X-ray speckle patterns | PDF",1785893611,63,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-for-classifying-and-interpreting-coherent-x-ray-speckle-patterns","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-for-classifying-and-interpreting-coherent-x-ray-speckle-patterns/124660/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are coherent X-ray speckle patterns difficult to interpret quantitatively?","Question",{"text":75,"@type":76},"Detector measurements record mainly amplitude, so phase information must be recovered through additional computation. This makes direct reconstruction of molecular or structural information challenging and often requires complex iterative algorithms or multiple experiments.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does this study use machine learning to accomplish?",{"text":80,"@type":76},"It trains a deep neural network to classify coherent X-ray speckle patterns based on the disk number density in the corresponding sample structure derived from a simplified 2D disk system.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the method perform for different disk size distributions?",{"text":84,"@type":76},"The classification system is demonstrated to be accurate for both non-disperse and disperse size distributions.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]