[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-128804-105":59,"doc-detail-128804-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","machine-learning-applied-to-fiber-fed-focal-plane-wavefront-sensing-a-study-of-aberrated-wave-transmission-through-multimode-optical-fibers","Machine learning applied to fiber-fed focal plane wavefront sensing - a study of aberrated wave transmission through multimode optical fibers","","Research investigates how machine learning and neural networks can identify input features of aberrated wavefronts transmitted through multimode optical fibers for wavefront sensing in ground-based telescopes. The study builds on evidence that multimode fibers support imaging and sensing by learning mappings between output distortions and input aberrations. Multimode fiber propagation simulations start from a Gaussian beam with known aberrations, followed by optical transmission and output analysis. A convolutional neural network is trained and validated to classify superimposed aberration types from output images, reaching test accuracies of 85% and 87% with strong training and generalization performance.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/machine-learning-applied-to-fiber-fed-focal-plane-wavefront-sensing-a-study-of-aberrated-wave-transmission-through-multimode-optical-fibers/128804/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/machine-learning-applied-to-fiber-fed-focal-plane-wavefront-sensing-a-study-of-aberrated-wave-transmission-through-multimode-optical-fibers/128804.png","ImageObject",300,407,{"name":92,"@type":93},"Violet","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-18","2026-08-06",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the core goal of the study on multimode optical fibers and wavefront sensing?","Question",{"text":112,"@type":113},"To assess whether machine learning and neural networks can recognize input features of aberrated wavefronts after they are transmitted through multimode optical fibers, enabling effective wavefront sensing for ground-based telescopes.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How is the training data generated for the convolutional neural network?",{"text":117,"@type":113},"A Gaussian beam is distorted with known aberrations, transmitted through a multimode fiber via propagation simulations, and the resulting output images are used to train and validate the network.",{"name":119,"@type":110,"acceptedAnswer":120},"Why are traditional input/output reconstruction methods difficult in this context?",{"text":121,"@type":113},"Because they are computationally intensive and not suitable for real-time applications, especially when multimode fibers induce mode mixing and speckle patterns.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},128804,1786003564,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":143},1099523885336,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","| Publication Year | 2024 |\n| --- | --- |\n| Acceptance in OA | 2025-04-02T10:06:42Z |\n| Title | Machine learning applied to fiber-fed focal plane wavefront sensing: a study ofaberrated wave transmission through multimode optical fibers |\n| Authors | DI FRANCESCO, Benedetta, DI FRISCHIA, Stefano, DI RICO, Gianluca, DOLCI, Mauro, DI ANTONIO, Ivan, Harris, Robert J., TOZZI, Andrea, IUZZOLINO, Marcella |\n| Publisher's version (DOI) | 10.1117/12.3017944 |\n| Handle | [http://hdl.handle.net/20.500.12386/37001](http://hdl.handle.net/20.500.12386/37001) |\n| Serie | PROCEEDINGS OF SPIE |\n| Volume | 13100 |\n\nMachine Learning applied to fiber-fed focal plane wavefront sensors: a study of aberrated wave transmission through  \nmultimode optical fibers  \nBenedetta Di Francesco a,b , Stefano Di Frischiaa , Gianluca Di Ricoa , Mauro Dolcia , Ivan Di Antonioa , Robert J. Harrisc , Andrea Tozzid , and Marcella Iuzzolinod  \naINAF, Osservatorio Astronomico d’Abruzzo, Via Mentore Maggini, snc, Teramo, Italy b Dipartimento di Fisica, Universit`a di Roma Tor Vergata, Via della Ricerca Scientifica, 1,  \nRoma, Italy  \nc Centre for Advanced Instrumentation, Department of Physics, Durham University, United  \nKingdom  \ndINAF, Osservatorio Astrofisico di Arcetri, Largo Enrico Fermi, 5, Firenze, Italy  \nABSTRACT  \nThis research explores the potential of machine learning and neural networks in recognizing the input features of aberrated wavefronts transmitted through multimode optical fibers, in view of applications for wavefront sensing in ground-based telescopes. Recent studies highlight the efficacy of multimode fibers for imaging and sensing, suggesting neural networks’ effectiveness in mapping relationships between output distortions and input wavefront aberrations. The initial step of our study concerned multimode fiber propagation simulations. An input Gaussian beam was distorted with known aberrations and then sent through the fiber to analyze the effects on the output. This groundwork was used to train and validate a Convolutional Neural Network architecture. Its main role was to understand, from output images, which type of aberration was superimposed in input. We obtained promising results with test accuracy of 85% and 87%, while achieving good performance in network training and generalization.  \nKeywords: optical fibers, wavefront sensing, adaptive optics, machine learning, neural networks, astrophotonics  \n1. OPTICAL FIBERS IN SENSING APPLICATIONS  \nOptical fibers are photonic waveguides able to transmit light over a given distance. In telecommunications, they play a fundamental role for data transmission and internet connectivity. Due to their compactness, easy availability, and flexibility, these devices can adapt to various fields. In the industrial sector, they are widely used as sensors for micro-vibration, temperature, and pressure variations. In the medical field, they are employed as probes in endoscopy, ophthalmology, and bio-imaging.  \nUntil the last decade, their usage in astronomy was confined to certain instruments, primarily spectrographs for Integral Field Spectroscopy (IFS) and Multi-Object Spectroscopy (MOS) . With the emergence of optical fiber imaging and sensing, new possibilities have arisen, notably in the field of Adaptive Optics (AO) where wavefront sensing poses a significant challenge. Despite the existence of several wavefront sensors (Shack-Hartmann, pyramid, curvature sensors...), new fiber-fed Focal Plane Wavefront Sensors (FP-WFS) are emerging. Recent studies 1 , 2 have examined the effectiveness of devices known as Photonic Lanterns (PLs) in measuring aberrationsat the telescope focal plane.  \nOur research explores the potential use of Multimode Fiber (MMF) for wavefront sensing.  \nThis concept is non-trivial, especially considering that MMFs are highly scattering media. They are capable of supporting multiple transmission modes with different propagation constants. The light launched into the fiber  \nFurther aut","cbCailIN4jL4aLJ9","https://ap.wps.com/l/cbCailIN4jL4aLJ9","pdf",702552,"English","# ABSTRACT\n# 1. OPTICAL FIBERS IN SENSING APPLICATIONS\n## Motivation for fiber-fed focal plane wavefront sensing\n## Multimode fiber challenges and speckle-based reconstruction","[{\"question\":\"What is the core goal of the study on multimode optical fibers and wavefront sensing?\",\"answer\":\"To assess whether machine learning and neural networks can recognize input features of aberrated wavefronts after they are transmitted through multimode optical fibers, enabling effective wavefront sensing for ground-based telescopes.\"},{\"question\":\"How is the training data generated for the convolutional neural network?\",\"answer\":\"A Gaussian beam is distorted with known aberrations, transmitted through a multimode fiber via propagation simulations, and the resulting output images are used to train and validate the network.\"},{\"question\":\"Why are traditional input/output reconstruction methods difficult in this context?\",\"answer\":\"Because they are computationally intensive and not suitable for real-time applications, especially when multimode fibers induce mode mixing and speckle patterns.\"}]","Machine learning applied to fiber-fed focal plane wavefront sensing - a study of aberrated wave transmission through multimode optical fibers | PDF",25]