[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121945-en":3,"doc-seo-121945-105":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},121945,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",6,"Technology","Inverse Engineering of Absorption and Scattering in Nanoparticles - A Machine Learning Approach","A region-specified machine learning workflow is used to perform inverse design of highly absorptive multilayer plasmonic nanoparticles. Convolutional neural networks learn the wave-matter interaction and output geometry scaling factors to realize target spectral behavior. The method enables independent control of the absorption-to-scattering ratio, spanning cloaked absorbers and bright absorbers across multiple visible wavelengths, while maintaining high absorption performance.","Chapman University  \nChapman University Digital Commons  \n\n| Engineering Faculty Articles and Research | Fowler School of Engineering |\n| --- | --- |\n| 11-12-2023\u003Cbr>Inverse Engineering of Absorption and Scattering in Nanoparticles: A Machine Learning Approach\u003Cbr>Alex Vallone\u003Cbr>Nooshin M. Estakhri\u003Cbr>Nasim Mohammadi Estrakhri\u003Cbr>Follow this and additional works at: [https://digitalcommons.chapman.edu/engineering_articles](https://digitalcommons.chapman.edu/engineering_articles)\u003Cbr> Part of the Nanoscience and Nanotechnology Commons, and the Other Electrical and Computer Engineering Commons |  |\n\nInverse Engineering of Absorption and Scattering in Nanoparticles: A Machine Learning Approach  \nComments  \nThis is a pre-copy-editing, author-produced PDF of an article accepted for publication in the proceedings of the 2023 IEEE Photonics Conference (IPC) . This article may not exactly replicate the final published version. The definitive publisher-authenticated version is available online at [https://doi.org/10.1109/](https://doi.org/10.1109/)[ ](https://doi.org/10.1109/)IPC57732 .2023.10360618.  \nCopyright  \n© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.  \nInverse Engineering of Absorption and Scattering in Nanoparticles: A Machine Learning Approach  \nAlex Vallone 1, Nooshin M. Estakhri2, and Nasim Mohammadi Estakhri 1*  \n1. Fowler School of Engineering, Chapman University, Orange, CA 92866 USA  \n2. Department of Physics, Virginia Tech, Blacksburg, Virginia 24061, USA  \n*[estakhri@chapman.edu](estakhri@chapman.edu)  \nAbstract—We use a region-specified machine learning approach to inverse design highly absorptive multilayer plasmonic nanoparticles. We demonstrate the design of particles with a wide range of absorption to scattering ratios (i.e., cloaked absorbers and bright absorbers) and for different visible wavelengths.  \nKeywords—convolutional neural networks, scattering and absorption, nanoparticles, inverse design, machine learning.  \nI. INTRODUCTION  \nMachine learning has shown a great potential to accelerate photonic modeling and inverse design [1] . The neural network is trained to learn the underlying dynamics of the wave-matter interaction and subsequently the trained network is used to design photonic systems with the desired performance. This process is different from iterative optimization approaches and does not require continuous access to a photonic simulator.  \nHere, we report using convolutional neural networks (CNN) to inverse design multilayer plasmonic nanoparticles maintaining high absorption levels. Simultaneously, our model controls the relative absorption to scattering ratio ranging from small (cloaked absorbers) to large (high-scattering absorbers) ratios.  \nII. ELECTROMAGNETIC AND MACHINE LEARNING MODELS  \nThe studied physical platform is a three-layer plasmonic nanoparticle. Three scaling factors are defined to describe the geometry of the particle. The spectral responses of the particle (absorption and scattering metrics) are considered as the input data for a residual one-dimensional CNN and the three scaling factors ( α1,2,3 ) are the outputs of the network, as illustrated in Fig. 1. A schematic of the particle is shown in the inset of Fig. 2a. Layer radiuses are related to scaling factors as α1 = r3 700 nm, α2 = r2 r3 , α3 = r1 r2 allowing us to work with normalized design parameters. The model is trained in Adam with mean squared error as loss function [1] . More details about the network can be found in [3] . The training dataset consists of 2310 nanoparticles with maximum diameter of 280 nm. Consequently, the spectral response of the particles is more dynamic toward","cbCaigfjyCJSJitM","https://ap.wps.com/l/cbCaigfjyCJSJitM","pdf",155226,1,4,"English","en",105,"# Introduction\n# Electromagnetic and Machine Learning Models\n## Physical platform and CNN setup\n## Metrics and optimization targets\n# Results and Discussions","[{\"question\":\"How does the proposed machine learning approach perform inverse design?\",\"answer\":\"It trains a convolutional neural network to learn the relationship between absorption/scattering spectral responses and geometry scaling factors, then uses the trained network to generate designs matching desired spectral goals.\"},{\"question\":\"What performance targets are used to control the nanoparticle behavior?\",\"answer\":\"The work uses normalized metrics for absorption and for the absorption-to-scattering ratio (σNorm and σRatio), fixing σNorm to enforce high absorption while controlling σRatio across a wide range.\"},{\"question\":\"What physical model and scattering/absorption computation are used?\",\"answer\":\"The study models a three-layer plasmonic nanoparticle and computes scattering and absorption responses using plane-wave illumination and the first ten Mie coefficients.\"}]","Inverse Engineering of Absorption and Scattering in Nanoparticles - A Machine Learning Approach | PDF",1785807872,10,{"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},"inverse-engineering-of-absorption-and-scattering-in-nanoparticles-a-machine-learning-approach","",{"@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/technology/",3,{"item":52,"name":13,"@type":43,"position":21},"https://docshare.wps.com/document/inverse-engineering-of-absorption-and-scattering-in-nanoparticles-a-machine-learning-approach/121945/",{"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","2026-08-04",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 does the proposed machine learning approach perform inverse design?","Question",{"text":74,"@type":75},"It trains a convolutional neural network to learn the relationship between absorption/scattering spectral responses and geometry scaling factors, then uses the trained network to generate designs matching desired spectral goals.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What performance targets are used to control the nanoparticle behavior?",{"text":79,"@type":75},"The work uses normalized metrics for absorption and for the absorption-to-scattering ratio (σNorm and σRatio), fixing σNorm to enforce high absorption while controlling σRatio across a wide range.",{"name":81,"@type":72,"acceptedAnswer":82},"What physical model and scattering/absorption computation are used?",{"text":83,"@type":75},"The study models a three-layer plasmonic nanoparticle and computes scattering and absorption responses using plane-wave illumination and the first ten Mie coefficients.","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},[92,96,100,104,109,112,117,122,127,130,133],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":110,"slug":111},50,"technology",{"id":113,"doc_module":4,"doc_module_name":46,"category_name":114,"show_sort_weight":115,"slug":116},7,"Healthcare",40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",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"]