[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117118-en":3,"doc-seo-117118-105":30,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},117118,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Machine learning for ultrafast nonlinear fibre photonics","Machine learning methods are used to accelerate and deepen understanding of ultrafast nonlinear fibre optics. The work shows that neural networks can predict temporal and spectral properties of optical signals after propagation in both focusing and defocusing nonlinearity regimes. The approach also addresses related inverse problems and yields physical insight beyond purely predictive modeling. Evolutionary algorithms are further illustrated to explore and optimise complex nonlinear dynamics in ultrafast fibre lasers.","Machine learning for ultrafast nonlinear fibre photonics  \nChristophe FINOT 1, ∗, Sonia BOSCOLO 2, Junsong PENG 3,4,5,  \nAndrei ERMOLAEV 6, Anastasiia SHEVELEVA 2 and John. M. DUDLEY 6  \n1 Laboratoire Interdisciplinaire Carnot Bourgogne, UMR 6303 CNRS – Université de Bourgogne, Dijon, France  \n2 Aston Institute of Photonic Technologies, Aston University, Birmingham B4 7ET, United Kingdom  \n3 State Key Laboratory of Precision Spectroscopy, East China Normal University, Shanghai 200062, China  \n4 Collaborative Innovation Center of Extreme Optics, Shanxi University, Taiyuan, Shanxi 030006, China  \n5 Chongqing Key Laboratory of Precision Optics, Chongqing Institute of East China Normal University,  \nChongqing 401120, China  \n6 Université de Franche-Comté, Institut FEMTO-ST, CNRS UMR 6174, 25000 Besançon, France  \ne-mail: [christophe.finot @u-bourgogne.fr](christophe.finot @u-bourgogne.fr)  \nABSTRACT  \nWe provide an overview of our latest advances in the application of machine learning methods to ultrafast nonlinear fibre optics. We establish that neural networks are capable of accurately forecasting the temporal and spectral properties of optical signals that are obtained after propagation in the focusing or defocusing regimes of nonlinearity. Machine learning is also efficient in addressing the related inverse problem as well as providing insights into the underlying physical process. In addition, we illustrate the use of evolutionary algorithms to access and optimise complex nonlinear dynamics of ultrafast fibre lasers.  \nKeywords: machine-learning, ultrafast nonlinear optics, nonlinear fiber photonics.  \n1. INTRODUCTION  \nRecent years have seen the rapid growth of the field of smart photonics where the deployment of machinelearning strategies is the key to enhance the performance and expand the functionality of optical systems [1]. Ultrafast photonics areas where the promise of machine learning is being realised include the design and operation of pulsed lasers, and the characterisation and control of ultrafast propagation dynamics [2]. Here, wereview our recent results in the field by providing several examples of advances enabled by machine-learning tools such as neural networks (NNs) and evolutionary algorithms (EAs) .  \nFirst, we describe the use of a supervised feedforward NN paradigm to solve the direct and inverse problems relating to nonlinear pulse shaping in optical fibres, bypassing the need for direct numerical solution of the governing propagation model, i.e, the nonlinear Schrödinger equation (NLSE) or its extensions. Further, we present the use of a NN to obtain new insights into the longitudinal temporal and spectral evolutions of periodic signals made of equally frequency-spaced components. Finally, we discuss the possibility of using EAs to perform search and optimisation of non-stationary regimes of fibre lasers.  \n2. MACHINE LEARNING FOR NONLINEAR PULSE SHAPING  \nPropagation of light in single-mode optical fibers is governed by the NLSE including dispersion and Kerr nonlinearity, to which it is also possible to add the effects of losses or gain. This equation, usually solved numerically by the split-step Fourier algorithm [3], leads to a very large panel of dynamics such as soliton pulse compression, self-similar temporal and spectral broadening, wave-breaking, and spectral narrowing, amongst others. The resulting output properties are highly dependent on the initial pulse properties (peak power, temporal duration, chirp and waveform) as well as the fiber parameters (value and regime of dispersion, fiber length, nonlinear/gain/loss coefficients) so that obtaining a full picture of the output landscape can be very demanding in terms of computational resources.  \nIn that context, we have shown that feedforward NNs, after convenient training, can offer a very efficient substitute to the split-step Fourier algorithm [4] . As can be seen on Fig. 1 for two initial chirped pulses, the network accurately predicts th","cbCaikLX8QyWJmsX","https://ap.wps.com/l/cbCaikLX8QyWJmsX","pdf",766705,1,4,"English","en",105,"# Introduction\n# Machine learning for nonlinear pulse shaping","[{\"question\":\"How do neural networks help with ultrafast nonlinear fibre optics in this work?\",\"answer\":\"Neural networks are trained to forecast temporal and spectral properties of optical signals after nonlinear propagation, and they can also support related inverse problems.\"},{\"question\":\"What direct and inverse tasks does the document discuss for nonlinear pulse shaping?\",\"answer\":\"It describes supervised feedforward neural networks to solve direct and inverse problems tied to nonlinear pulse shaping, avoiding direct numerical solution of the propagation model.\"},{\"question\":\"How are evolutionary algorithms used in ultrafast fibre lasers?\",\"answer\":\"Evolutionary algorithms are used to search and optimise non-stationary regimes, helping access and tune complex nonlinear dynamics in ultrafast fibre lasers.\"}]","Machine learning for ultrafast nonlinear fibre photonics | PDF",1785673980,10,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":28},"machine-learning-for-ultrafast-nonlinear-fibre-photonics","",{"@graph":36,"@context":84},[37,53,67],{"@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":21},"https://docshare.wps.com/document/machine-learning-for-ultrafast-nonlinear-fibre-photonics/117118/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"How do neural networks help with ultrafast nonlinear fibre optics in this work?","Question",{"text":74,"@type":75},"Neural networks are trained to forecast temporal and spectral properties of optical signals after nonlinear propagation, and they can also support related inverse problems.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What direct and inverse tasks does the document discuss for nonlinear pulse shaping?",{"text":79,"@type":75},"It describes supervised feedforward neural networks to solve direct and inverse problems tied to nonlinear pulse shaping, avoiding direct numerical solution of the propagation model.",{"name":81,"@type":72,"acceptedAnswer":82},"How are evolutionary algorithms used in ultrafast fibre lasers?",{"text":83,"@type":75},"Evolutionary algorithms are used to search and optimise non-stationary regimes, helping access and tune complex nonlinear dynamics in ultrafast fibre lasers.","https://schema.org",{"og:url":52,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":29,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]