Nanophotonic particle simulation and inverse design using artificial neural networks

We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate su...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Science advances 2018-06, Vol.4 (6), p.eaar4206-eaar4206
Hauptverfasser: Peurifoy, John, Shen, Yichen, Jing, Li, Yang, Yi, Cano-Renteria, Fidel, DeLacy, Brendan G, Joannopoulos, John D, Tegmark, Max, Soljačić, Marin
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page eaar4206
container_issue 6
container_start_page eaar4206
container_title Science advances
container_volume 4
creator Peurifoy, John
Shen, Yichen
Jing, Li
Yang, Yi
Cano-Renteria, Fidel
DeLacy, Brendan G
Joannopoulos, John D
Tegmark, Max
Soljačić, Marin
description We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical.
doi_str_mv 10.1126/sciadv.aar4206
format Article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_5983917</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2050481651</sourcerecordid><originalsourceid>FETCH-LOGICAL-c456t-5b77c7966a4e841bea861590c32f95b9dc2cd271799bc80d03b415abd6085f2b3</originalsourceid><addsrcrecordid>eNpVUT1PwzAUtBCIVqUrI8rIkmI7tmMvSKjiS6pgKbPlOE5rSOxgJ0X8e1JaqjLdk969e6c7AC4RnCGE2U3UVpWbmVKBYMhOwBhnOU0xJfz0aB6BaYzvEEJEGKNInIMRFpxxRuAYLF-U8-3ad95ZnbQqdFbXJom26WvVWe8S5crEuo0J0SSliXblkj5at0q23MoOFurEmT78Qvflw0e8AGeVqqOZ7nEC3h7ul_OndPH6-Dy_W6SaUNaltMhznQvGFDGcoMIozhAVUGe4ErQQpca6xDnKhSg0hyXMCoKoKkoGOa1wkU3A7U637YvGlNq4brAh22AbFb6lV1b-3zi7liu_kVTwTKB8ELjeCwT_2ZvYycZGbepaOeP7KDGkkHA0pDZQZzuqDj7GYKrDGwTltg25a0Pu2xgOro7NHeh_2Wc_ciWKdQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2050481651</pqid></control><display><type>article</type><title>Nanophotonic particle simulation and inverse design using artificial neural networks</title><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><creator>Peurifoy, John ; Shen, Yichen ; Jing, Li ; Yang, Yi ; Cano-Renteria, Fidel ; DeLacy, Brendan G ; Joannopoulos, John D ; Tegmark, Max ; Soljačić, Marin</creator><creatorcontrib>Peurifoy, John ; Shen, Yichen ; Jing, Li ; Yang, Yi ; Cano-Renteria, Fidel ; DeLacy, Brendan G ; Joannopoulos, John D ; Tegmark, Max ; Soljačić, Marin</creatorcontrib><description>We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical.</description><identifier>ISSN: 2375-2548</identifier><identifier>EISSN: 2375-2548</identifier><identifier>DOI: 10.1126/sciadv.aar4206</identifier><identifier>PMID: 29868640</identifier><language>eng</language><publisher>United States: American Association for the Advancement of Science</publisher><subject>Computer Science ; Optics ; SciAdv r-articles</subject><ispartof>Science advances, 2018-06, Vol.4 (6), p.eaar4206-eaar4206</ispartof><rights>Copyright © 2018 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC). 2018 The Authors</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c456t-5b77c7966a4e841bea861590c32f95b9dc2cd271799bc80d03b415abd6085f2b3</citedby><cites>FETCH-LOGICAL-c456t-5b77c7966a4e841bea861590c32f95b9dc2cd271799bc80d03b415abd6085f2b3</cites><orcidid>0000-0002-7184-5831 ; 0000-0003-2879-4968</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC5983917/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC5983917/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,864,885,27924,27925,53791,53793</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/29868640$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Peurifoy, John</creatorcontrib><creatorcontrib>Shen, Yichen</creatorcontrib><creatorcontrib>Jing, Li</creatorcontrib><creatorcontrib>Yang, Yi</creatorcontrib><creatorcontrib>Cano-Renteria, Fidel</creatorcontrib><creatorcontrib>DeLacy, Brendan G</creatorcontrib><creatorcontrib>Joannopoulos, John D</creatorcontrib><creatorcontrib>Tegmark, Max</creatorcontrib><creatorcontrib>Soljačić, Marin</creatorcontrib><title>Nanophotonic particle simulation and inverse design using artificial neural networks</title><title>Science advances</title><addtitle>Sci Adv</addtitle><description>We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical.</description><subject>Computer Science</subject><subject>Optics</subject><subject>SciAdv r-articles</subject><issn>2375-2548</issn><issn>2375-2548</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><recordid>eNpVUT1PwzAUtBCIVqUrI8rIkmI7tmMvSKjiS6pgKbPlOE5rSOxgJ0X8e1JaqjLdk969e6c7AC4RnCGE2U3UVpWbmVKBYMhOwBhnOU0xJfz0aB6BaYzvEEJEGKNInIMRFpxxRuAYLF-U8-3ad95ZnbQqdFbXJom26WvVWe8S5crEuo0J0SSliXblkj5at0q23MoOFurEmT78Qvflw0e8AGeVqqOZ7nEC3h7ul_OndPH6-Dy_W6SaUNaltMhznQvGFDGcoMIozhAVUGe4ErQQpca6xDnKhSg0hyXMCoKoKkoGOa1wkU3A7U637YvGlNq4brAh22AbFb6lV1b-3zi7liu_kVTwTKB8ELjeCwT_2ZvYycZGbepaOeP7KDGkkHA0pDZQZzuqDj7GYKrDGwTltg25a0Pu2xgOro7NHeh_2Wc_ciWKdQ</recordid><startdate>201806</startdate><enddate>201806</enddate><creator>Peurifoy, John</creator><creator>Shen, Yichen</creator><creator>Jing, Li</creator><creator>Yang, Yi</creator><creator>Cano-Renteria, Fidel</creator><creator>DeLacy, Brendan G</creator><creator>Joannopoulos, John D</creator><creator>Tegmark, Max</creator><creator>Soljačić, Marin</creator><general>American Association for the Advancement of Science</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-7184-5831</orcidid><orcidid>https://orcid.org/0000-0003-2879-4968</orcidid></search><sort><creationdate>201806</creationdate><title>Nanophotonic particle simulation and inverse design using artificial neural networks</title><author>Peurifoy, John ; Shen, Yichen ; Jing, Li ; Yang, Yi ; Cano-Renteria, Fidel ; DeLacy, Brendan G ; Joannopoulos, John D ; Tegmark, Max ; Soljačić, Marin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c456t-5b77c7966a4e841bea861590c32f95b9dc2cd271799bc80d03b415abd6085f2b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer Science</topic><topic>Optics</topic><topic>SciAdv r-articles</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Peurifoy, John</creatorcontrib><creatorcontrib>Shen, Yichen</creatorcontrib><creatorcontrib>Jing, Li</creatorcontrib><creatorcontrib>Yang, Yi</creatorcontrib><creatorcontrib>Cano-Renteria, Fidel</creatorcontrib><creatorcontrib>DeLacy, Brendan G</creatorcontrib><creatorcontrib>Joannopoulos, John D</creatorcontrib><creatorcontrib>Tegmark, Max</creatorcontrib><creatorcontrib>Soljačić, Marin</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Science advances</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Peurifoy, John</au><au>Shen, Yichen</au><au>Jing, Li</au><au>Yang, Yi</au><au>Cano-Renteria, Fidel</au><au>DeLacy, Brendan G</au><au>Joannopoulos, John D</au><au>Tegmark, Max</au><au>Soljačić, Marin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Nanophotonic particle simulation and inverse design using artificial neural networks</atitle><jtitle>Science advances</jtitle><addtitle>Sci Adv</addtitle><date>2018-06</date><risdate>2018</risdate><volume>4</volume><issue>6</issue><spage>eaar4206</spage><epage>eaar4206</epage><pages>eaar4206-eaar4206</pages><issn>2375-2548</issn><eissn>2375-2548</eissn><abstract>We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical.</abstract><cop>United States</cop><pub>American Association for the Advancement of Science</pub><pmid>29868640</pmid><doi>10.1126/sciadv.aar4206</doi><orcidid>https://orcid.org/0000-0002-7184-5831</orcidid><orcidid>https://orcid.org/0000-0003-2879-4968</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2375-2548
ispartof Science advances, 2018-06, Vol.4 (6), p.eaar4206-eaar4206
issn 2375-2548
2375-2548
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_5983917
source DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals; PubMed Central
subjects Computer Science
Optics
SciAdv r-articles
title Nanophotonic particle simulation and inverse design using artificial neural networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T03%3A50%3A36IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Nanophotonic%20particle%20simulation%20and%20inverse%20design%20using%20artificial%20neural%20networks&rft.jtitle=Science%20advances&rft.au=Peurifoy,%20John&rft.date=2018-06&rft.volume=4&rft.issue=6&rft.spage=eaar4206&rft.epage=eaar4206&rft.pages=eaar4206-eaar4206&rft.issn=2375-2548&rft.eissn=2375-2548&rft_id=info:doi/10.1126/sciadv.aar4206&rft_dat=%3Cproquest_pubme%3E2050481651%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2050481651&rft_id=info:pmid/29868640&rfr_iscdi=true