Loading…

Prioritizing ocean colour channels by neural network input reflectance perturbation

The radiative transfer model Hydrolight was used to produce 18 000 artificial reflectance spectra representing case 1 and case 2 water conditions. Remote sensing reflectances were generated at the MERIS wavebands 412, 442, 490, 510, 560, 620, 665 and 682 nm from randomly generated triplet combinatio...

Full description

Saved in:
Bibliographic Details
Published in:International journal of remote sensing 2005-03, Vol.26 (5), p.1043-1048
Main Authors: Dransfeld, S., Tatnall, A. R., Robinson, I. S., Mobley, C. D.
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c450t-860c291310f9b5bfe9993e39a65c843994e315bc5a3ed4d684f674e94789b73
cites cdi_FETCH-LOGICAL-c450t-860c291310f9b5bfe9993e39a65c843994e315bc5a3ed4d684f674e94789b73
container_end_page 1048
container_issue 5
container_start_page 1043
container_title International journal of remote sensing
container_volume 26
creator Dransfeld, S.
Tatnall, A. R.
Robinson, I. S.
Mobley, C. D.
description The radiative transfer model Hydrolight was used to produce 18 000 artificial reflectance spectra representing case 1 and case 2 water conditions. Remote sensing reflectances were generated at the MERIS wavebands 412, 442, 490, 510, 560, 620, 665 and 682 nm from randomly generated triplet combinations of chlorophyll a, non-chlorophyllous particles and coloured dissolved organic matter concentrations. These spectra were used to train multilayer perceptron neural network algorithms to perform the inversion from input reflectances to these three optically active substances. A method is proposed that establishes the neural network output error sensitivity towards changes in the individual input reflectance channels. From the output error produced for each reflectance change, a hypothesis about the importance of each band can be made. Results suggest a strong weight associated to the 620 nm band for the estimation of all three substances.
doi_str_mv 10.1080/01431160512331314100
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_29512816</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>17337101</sourcerecordid><originalsourceid>FETCH-LOGICAL-c450t-860c291310f9b5bfe9993e39a65c843994e315bc5a3ed4d684f674e94789b73</originalsourceid><addsrcrecordid>eNqFkE1LAzEQhoMoWKv_wEMuelvNNNnsxouI-AUFhXpfsmlWo2lSkyxaf70prXgp9jSX551550HoGMgZkJqcE2AUgJMSRpQCBQaE7KABUM6LUhDYRYMlUmQG9tFBjG-EEF6V1QBNnoLxwSTzbdwL9kpLh5W3vg9YvUrntI24XWCn-yBtHunTh3ds3LxPOOjOapWkUxrPdUh9aGUy3h2ivU7aqI_Wc4gmtzfP1_fF-PHu4fpqXChWklTUnKiRyHVJJ9qy7bQQgmoqJC9VzagQTFMoW1VKqqdsymvW8YppwapatBUdotPV1nnwH72OqZmZqLS10mnfx2Ykso4a-FYQKkorIJBBtgJV8DHm75p5MDMZFg2QZim62SQ6x07W-2VU0nYhCzHxL8sZr4VY9rhYccZ1PsxkNmmnTZIL68NvaNOBJn2lHL7cGqb_1vwB3xKj9w</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>17337101</pqid></control><display><type>article</type><title>Prioritizing ocean colour channels by neural network input reflectance perturbation</title><source>Taylor and Francis Science and Technology Collection</source><creator>Dransfeld, S. ; Tatnall, A. R. ; Robinson, I. S. ; Mobley, C. D.</creator><creatorcontrib>Dransfeld, S. ; Tatnall, A. R. ; Robinson, I. S. ; Mobley, C. D.</creatorcontrib><description>The radiative transfer model Hydrolight was used to produce 18 000 artificial reflectance spectra representing case 1 and case 2 water conditions. Remote sensing reflectances were generated at the MERIS wavebands 412, 442, 490, 510, 560, 620, 665 and 682 nm from randomly generated triplet combinations of chlorophyll a, non-chlorophyllous particles and coloured dissolved organic matter concentrations. These spectra were used to train multilayer perceptron neural network algorithms to perform the inversion from input reflectances to these three optically active substances. A method is proposed that establishes the neural network output error sensitivity towards changes in the individual input reflectance channels. From the output error produced for each reflectance change, a hypothesis about the importance of each band can be made. Results suggest a strong weight associated to the 620 nm band for the estimation of all three substances.</description><identifier>ISSN: 0143-1161</identifier><identifier>EISSN: 1366-5901</identifier><identifier>DOI: 10.1080/01431160512331314100</identifier><identifier>CODEN: IJSEDK</identifier><language>eng</language><publisher>Abingdon: Taylor &amp; Francis Group</publisher><subject>Applied geophysics ; Earth sciences ; Earth, ocean, space ; Exact sciences and technology ; Internal geophysics ; Marine geology</subject><ispartof>International journal of remote sensing, 2005-03, Vol.26 (5), p.1043-1048</ispartof><rights>Copyright Taylor &amp; Francis Group, LLC 2005</rights><rights>2005 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c450t-860c291310f9b5bfe9993e39a65c843994e315bc5a3ed4d684f674e94789b73</citedby><cites>FETCH-LOGICAL-c450t-860c291310f9b5bfe9993e39a65c843994e315bc5a3ed4d684f674e94789b73</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,778,782,27907,27908</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=16468996$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Dransfeld, S.</creatorcontrib><creatorcontrib>Tatnall, A. R.</creatorcontrib><creatorcontrib>Robinson, I. S.</creatorcontrib><creatorcontrib>Mobley, C. D.</creatorcontrib><title>Prioritizing ocean colour channels by neural network input reflectance perturbation</title><title>International journal of remote sensing</title><description>The radiative transfer model Hydrolight was used to produce 18 000 artificial reflectance spectra representing case 1 and case 2 water conditions. Remote sensing reflectances were generated at the MERIS wavebands 412, 442, 490, 510, 560, 620, 665 and 682 nm from randomly generated triplet combinations of chlorophyll a, non-chlorophyllous particles and coloured dissolved organic matter concentrations. These spectra were used to train multilayer perceptron neural network algorithms to perform the inversion from input reflectances to these three optically active substances. A method is proposed that establishes the neural network output error sensitivity towards changes in the individual input reflectance channels. From the output error produced for each reflectance change, a hypothesis about the importance of each band can be made. Results suggest a strong weight associated to the 620 nm band for the estimation of all three substances.</description><subject>Applied geophysics</subject><subject>Earth sciences</subject><subject>Earth, ocean, space</subject><subject>Exact sciences and technology</subject><subject>Internal geophysics</subject><subject>Marine geology</subject><issn>0143-1161</issn><issn>1366-5901</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2005</creationdate><recordtype>article</recordtype><recordid>eNqFkE1LAzEQhoMoWKv_wEMuelvNNNnsxouI-AUFhXpfsmlWo2lSkyxaf70prXgp9jSX551550HoGMgZkJqcE2AUgJMSRpQCBQaE7KABUM6LUhDYRYMlUmQG9tFBjG-EEF6V1QBNnoLxwSTzbdwL9kpLh5W3vg9YvUrntI24XWCn-yBtHunTh3ds3LxPOOjOapWkUxrPdUh9aGUy3h2ivU7aqI_Wc4gmtzfP1_fF-PHu4fpqXChWklTUnKiRyHVJJ9qy7bQQgmoqJC9VzagQTFMoW1VKqqdsymvW8YppwapatBUdotPV1nnwH72OqZmZqLS10mnfx2Ykso4a-FYQKkorIJBBtgJV8DHm75p5MDMZFg2QZim62SQ6x07W-2VU0nYhCzHxL8sZr4VY9rhYccZ1PsxkNmmnTZIL68NvaNOBJn2lHL7cGqb_1vwB3xKj9w</recordid><startdate>20050301</startdate><enddate>20050301</enddate><creator>Dransfeld, S.</creator><creator>Tatnall, A. R.</creator><creator>Robinson, I. S.</creator><creator>Mobley, C. D.</creator><general>Taylor &amp; Francis Group</general><general>Taylor and Francis</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7TN</scope><scope>F1W</scope><scope>H96</scope><scope>L.G</scope><scope>8FD</scope><scope>FR3</scope><scope>H8D</scope><scope>KR7</scope><scope>L7M</scope></search><sort><creationdate>20050301</creationdate><title>Prioritizing ocean colour channels by neural network input reflectance perturbation</title><author>Dransfeld, S. ; Tatnall, A. R. ; Robinson, I. S. ; Mobley, C. D.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c450t-860c291310f9b5bfe9993e39a65c843994e315bc5a3ed4d684f674e94789b73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Applied geophysics</topic><topic>Earth sciences</topic><topic>Earth, ocean, space</topic><topic>Exact sciences and technology</topic><topic>Internal geophysics</topic><topic>Marine geology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Dransfeld, S.</creatorcontrib><creatorcontrib>Tatnall, A. R.</creatorcontrib><creatorcontrib>Robinson, I. S.</creatorcontrib><creatorcontrib>Mobley, C. D.</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Oceanic Abstracts</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy &amp; Non-Living Resources</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>International journal of remote sensing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Dransfeld, S.</au><au>Tatnall, A. R.</au><au>Robinson, I. S.</au><au>Mobley, C. D.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Prioritizing ocean colour channels by neural network input reflectance perturbation</atitle><jtitle>International journal of remote sensing</jtitle><date>2005-03-01</date><risdate>2005</risdate><volume>26</volume><issue>5</issue><spage>1043</spage><epage>1048</epage><pages>1043-1048</pages><issn>0143-1161</issn><eissn>1366-5901</eissn><coden>IJSEDK</coden><abstract>The radiative transfer model Hydrolight was used to produce 18 000 artificial reflectance spectra representing case 1 and case 2 water conditions. Remote sensing reflectances were generated at the MERIS wavebands 412, 442, 490, 510, 560, 620, 665 and 682 nm from randomly generated triplet combinations of chlorophyll a, non-chlorophyllous particles and coloured dissolved organic matter concentrations. These spectra were used to train multilayer perceptron neural network algorithms to perform the inversion from input reflectances to these three optically active substances. A method is proposed that establishes the neural network output error sensitivity towards changes in the individual input reflectance channels. From the output error produced for each reflectance change, a hypothesis about the importance of each band can be made. Results suggest a strong weight associated to the 620 nm band for the estimation of all three substances.</abstract><cop>Abingdon</cop><pub>Taylor &amp; Francis Group</pub><doi>10.1080/01431160512331314100</doi><tpages>6</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0143-1161
ispartof International journal of remote sensing, 2005-03, Vol.26 (5), p.1043-1048
issn 0143-1161
1366-5901
language eng
recordid cdi_proquest_miscellaneous_29512816
source Taylor and Francis Science and Technology Collection
subjects Applied geophysics
Earth sciences
Earth, ocean, space
Exact sciences and technology
Internal geophysics
Marine geology
title Prioritizing ocean colour channels by neural network input reflectance perturbation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T14%3A07%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Prioritizing%20ocean%20colour%20channels%20by%20neural%20network%20input%20reflectance%20perturbation&rft.jtitle=International%20journal%20of%20remote%20sensing&rft.au=Dransfeld,%20S.&rft.date=2005-03-01&rft.volume=26&rft.issue=5&rft.spage=1043&rft.epage=1048&rft.pages=1043-1048&rft.issn=0143-1161&rft.eissn=1366-5901&rft.coden=IJSEDK&rft_id=info:doi/10.1080/01431160512331314100&rft_dat=%3Cproquest_cross%3E17337101%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c450t-860c291310f9b5bfe9993e39a65c843994e315bc5a3ed4d684f674e94789b73%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=17337101&rft_id=info:pmid/&rfr_iscdi=true