[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119884-en":3,"doc-seo-119884-105":29,"detail-sidebar-cat-0-en-105":89},{"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":11},119884,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Machine Learning Aided Prediction of Fabrication Uncertainties in Integrated Multi-Ring Filters","Proposes a machine learning framework to predict fabrication uncertainty and determine the effective-index shift in integrated multi-ring filtering elements. The method targets each ring’s effective-index shift, using frequency-response data (phase and amplitude) generated by an analytical model for a two-stage ladder multi-ring resonator (MRR) filter. Training leverages large sets of randomly perturbed configurations that reflect realistic index variations from tolerance-aware simulations, enabling faster real-time tuning by reducing reliance on time-consuming iterative procedures.","POLITECNICO DI TORINO  \nRepository ISTITUZIONALE  \nMachine Learning Aided Prediction of Fabrication Uncertainties in Integrated Multi-Ring Filters  \nOriginal  \nMachine Learning Aided Prediction of Fabrication Uncertainties in Integrated Multi-Ring Filters / Tunesi, Lorenzo; Khan, Ihtesham; Masood, MUHAMMAD UMAR; Marchisio, Andrea; Ghillino, Enrico; Curri, Vittorio; Carena, Andrea; Bardella, Paolo. -ELETTRONICO. - (2023), pp. 1-2. (Intervento presentato al convegno CLEO: Science and Innovations tenutosia San Jose, CA, United States nel 7-12 May 2023) [10 . 1364/CLEO_SI.2023.STh4H.2] .  \nAvailability:  \nThis version is available at: 11583/2980626 since: 2023-08-23T09:27:05Z  \nPublisher:  \nOptica Publ.  \nPublished  \nDOI:10 . 1364/CLEO_SI.2023.STh4H.2  \nTerms of use:  \nThis article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository  \nPublisher copyright  \nOptica Publishing Group (formely OSA) postprint/Author's Accepted Manuscript  \n“© 2023 Optica Publishing Group. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modifications of the content of this paper are prohibited.”  \n(Article begins on next page)  \n07 November 2024  \nMachine Learning Aided Prediction of Fabrication Uncertainties in Integrated Multi-Ring Filters  \nLorenzo Tunesi(1), Ihtesham Khan(1), Muhammad Umar Masood(1), Andrea Marchisio(1) , Enrico Ghillino(2), Vittorio Curri (1) , Andrea Carena(1) , Paolo Bardella(1)  \n(1) Politecnico di Torino, Corso Duca degli Abruzzi, 24, 10129, Torino, Italy  \n(2) Synopsys, Inc., 400 Executive Blvd Ste 101, Ossining, NY 10562, United States ihtesham.khan@polito.it  \nAbstract: We propose a machine learning-based framework to predict the fabrication uncertainty and evaluate the effective-index shift in multi-ring integrated filtering elements.  \nExcellent results are achieved in predicting each ring’s effective-index shift. © 2022 The Author(s)  \n1. Introduction  \nPhotonic integrated circuits (PICs) are becoming increasingly present in the literature as competitive solutions for switching and filtering in transparent optical applications. PICs can offer several benefits in terms of mass production capability and cost-effectiveness while simultaneously allowing a significant degree of freedom in design and control strategies. In this context, while many passive devices can be reliably manufactured under reasonable fabrication tolerances, certain components are still severely affected by tolerances, requiring complex and resource-consuming tuning schemes to ensure the appropriate behavior [1] . One such component is the MicroRing Resonator (MRR), which is one of the standard building blocks for photonic switches and filters. Typically the single-ring configurations can be easily tuned, while its cascaded and more advanced configurations do not allow a straightforward and simple solution.  \nIn this context, we proposed a Machine leaning (ML) based approach to predict the fabrication uncertainty and evaluate the effective-index shift in multi-ring integrated filtering elements in order to achieve an optimized tuning configuration. The training dataset for this approach is comprised of the frequency response (phase and amplitude), which is generated using an analytical model for a two-stage ladder MRR filter. The proposed ML model is exploited to achieve an optimized tuning configuration by predicting the effective-index shift of each ring in real-time operation which is traditionally time-consuming and requires a significant effort for an optimized tuning.  \n2. MRR Filter and Dataset Generation  \nThe device under analysis consists of a two-stage ladder MRR filter [2], depicted in Fig. 1a. This higher-order filtering element is suited for optical Wavelength-Division Multiplexing (WDM) applications, as it allows flat-top transmissi","cbCais1YlbxjT1K5","https://ap.wps.com/l/cbCais1YlbxjT1K5","pdf",451185,1,3,"English","en",105,"# Introduction\n## Photonic integrated circuits and tuning challenges\n## Multi-ring resonators and fabrication tolerances\n# MRR Filter and Dataset Generation\n## Two-stage ladder MRR filter and use cases\n## Transmission data and ML agent training dataset","[{\"question\":\"What problem does the proposed machine learning framework address?\",\"answer\":\"It predicts fabrication uncertainty and evaluates the effective-index shift in integrated multi-ring filtering elements, where small non-idealities can severely impair transmission without proper tuning.\"},{\"question\":\"What data does the ML model use for training and prediction?\",\"answer\":\"The model is trained using frequency response information—specifically phase and amplitude—extracted from analytically generated responses of a two-stage ladder MRR filter under random perturbations.\"},{\"question\":\"How does the approach improve tuning efficiency in multi-ring devices?\",\"answer\":\"By predicting each ring’s effective-index shift in real time directly from transmission data, it avoids non-scalable iterative tuning methods that are traditionally time-consuming and effort-heavy.\"}]","Machine Learning Aided Prediction of Fabrication Uncertainties in Integrated Multi-Ring Filters | PDF",1785726832,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":28},"machine-learning-aided-prediction-of-fabrication-uncertainties-in-integrated-multi-ring-filters","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":21},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/machine-learning-aided-prediction-of-fabrication-uncertainties-in-integrated-multi-ring-filters/119884/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What problem does the proposed machine learning framework address?","Question",{"text":73,"@type":74},"It predicts fabrication uncertainty and evaluates the effective-index shift in integrated multi-ring filtering elements, where small non-idealities can severely impair transmission without proper tuning.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"What data does the ML model use for training and prediction?",{"text":78,"@type":74},"The model is trained using frequency response information—specifically phase and amplitude—extracted from analytically generated responses of a two-stage ladder MRR filter under random perturbations.",{"name":80,"@type":71,"acceptedAnswer":81},"How does the approach improve tuning efficiency in multi-ring devices?",{"text":82,"@type":74},"By predicting each ring’s effective-index shift in real time directly from transmission data, it avoids non-scalable iterative tuning methods that are traditionally time-consuming and effort-heavy.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]