Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks
Identifieur interne : 000998 ( Istex/Corpus ); précédent : 000997; suivant : 000999Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks
Auteurs : G. R Ball ; D. Palmer-Brown ; J. Fuhrer ; L. Sk Rby ; B. S Gimeno ; G. MillsSource :
- Ecological Modelling [ 0304-3800 ] ; 2000.
English descriptors
- KwdEn :
Abstract
Ozone is a commonly occurring pollutant that has a large impact on the yield of agricultural crops. The dose–response of crops in the field is complex, with influences from numerous biotic and abiotic factors, including microclimatic variables. This paper presents results of a number of analysis methods of artificial neural network (ANN) models, developed on biomonitoring data from 12 countries, to identify the importance of interacting influences on the biomass response of sensitive (NC-S) and resistant (NC-R) clones of white clover (Trifolium repens L. cv. Regal). These methods of analysis were also used to identify the importance of influences on a subset of the data. Empirical equations were extracted from the ANN model with the best performance and these were analysed to determine their performance and to indicate the nature of microclimatic influences. Analysis indicated that combinations of VPD and the number of raindays were strong influences on the ozone dose–response and that temperature and the number of raindays had a secondary influence on the NC-S/NC-R biomass ratio irrespective of the ozone dose. Analysis of derived empirical equations indicated they compared well with the ANN model and that only a small loss in accuracy occurred.
Url:
DOI: 10.1016/S0304-3800(00)00234-9
Links to Exploration step
ISTEX:F582E4C071EA7ACB5B971367009B0D03CC26EACDLe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks</title><author><name sortKey="Ball, G R" sort="Ball, G R" uniqKey="Ball G" first="G. R" last="Ball">G. R Ball</name><affiliation><mods:affiliation>E-mail: graham.balls@ntu.ac.uk</mods:affiliation></affiliation><affiliation><mods:affiliation>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</mods:affiliation></affiliation></author><author><name sortKey="Palmer Brown, D" sort="Palmer Brown, D" uniqKey="Palmer Brown D" first="D" last="Palmer-Brown">D. Palmer-Brown</name><affiliation><mods:affiliation>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</mods:affiliation></affiliation></author><author><name sortKey="Fuhrer, J" sort="Fuhrer, J" uniqKey="Fuhrer J" first="J" last="Fuhrer">J. Fuhrer</name><affiliation><mods:affiliation>Institute for Environmental Protection and Agriculture, (IUL) Liebfeld, CH-3003 Bern, Switzerland</mods:affiliation></affiliation></author><author><name sortKey="Sk Rby, L" sort="Sk Rby, L" uniqKey="Sk Rby L" first="L" last="Sk Rby">L. Sk Rby</name><affiliation><mods:affiliation>IVL, Box 47086, S-40258, Göteborg, Sweden</mods:affiliation></affiliation></author><author><name sortKey="Gimeno, B S" sort="Gimeno, B S" uniqKey="Gimeno B" first="B. S" last="Gimeno">B. S Gimeno</name><affiliation><mods:affiliation>CIEMAT-DIAE 3B, Avda. Complutense 22, Madrid 28040, Spain</mods:affiliation></affiliation></author><author><name sortKey="Mills, G" sort="Mills, G" uniqKey="Mills G" first="G" last="Mills">G. Mills</name><affiliation><mods:affiliation>Bangor Research Unit, Institute of Terrestrial Ecology, Deiniol Road, Bangor, Gwynedd LL57 2UP, UK</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:F582E4C071EA7ACB5B971367009B0D03CC26EACD</idno><date when="2000" year="2000">2000</date><idno type="doi">10.1016/S0304-3800(00)00234-9</idno><idno type="url">https://api.istex.fr/document/F582E4C071EA7ACB5B971367009B0D03CC26EACD/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000998</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000998</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks</title><author><name sortKey="Ball, G R" sort="Ball, G R" uniqKey="Ball G" first="G. R" last="Ball">G. R Ball</name><affiliation><mods:affiliation>E-mail: graham.balls@ntu.ac.uk</mods:affiliation></affiliation><affiliation><mods:affiliation>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</mods:affiliation></affiliation></author><author><name sortKey="Palmer Brown, D" sort="Palmer Brown, D" uniqKey="Palmer Brown D" first="D" last="Palmer-Brown">D. Palmer-Brown</name><affiliation><mods:affiliation>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</mods:affiliation></affiliation></author><author><name sortKey="Fuhrer, J" sort="Fuhrer, J" uniqKey="Fuhrer J" first="J" last="Fuhrer">J. Fuhrer</name><affiliation><mods:affiliation>Institute for Environmental Protection and Agriculture, (IUL) Liebfeld, CH-3003 Bern, Switzerland</mods:affiliation></affiliation></author><author><name sortKey="Sk Rby, L" sort="Sk Rby, L" uniqKey="Sk Rby L" first="L" last="Sk Rby">L. Sk Rby</name><affiliation><mods:affiliation>IVL, Box 47086, S-40258, Göteborg, Sweden</mods:affiliation></affiliation></author><author><name sortKey="Gimeno, B S" sort="Gimeno, B S" uniqKey="Gimeno B" first="B. S" last="Gimeno">B. S Gimeno</name><affiliation><mods:affiliation>CIEMAT-DIAE 3B, Avda. Complutense 22, Madrid 28040, Spain</mods:affiliation></affiliation></author><author><name sortKey="Mills, G" sort="Mills, G" uniqKey="Mills G" first="G" last="Mills">G. Mills</name><affiliation><mods:affiliation>Bangor Research Unit, Institute of Terrestrial Ecology, Deiniol Road, Bangor, Gwynedd LL57 2UP, UK</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j">Ecological Modelling</title><title level="j" type="abbrev">ECOMOD</title><idno type="ISSN">0304-3800</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="2000">2000</date><biblScope unit="volume">129</biblScope><biblScope unit="issue">2–3</biblScope><biblScope unit="page" from="153">153</biblScope><biblScope unit="page" to="168">168</biblScope></imprint><idno type="ISSN">0304-3800</idno></series><idno type="istex">F582E4C071EA7ACB5B971367009B0D03CC26EACD</idno><idno type="DOI">10.1016/S0304-3800(00)00234-9</idno><idno type="PII">S0304-3800(00)00234-9</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0304-3800</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>AOT40</term><term>Artificial neural networks</term><term>Biomass dose–response</term><term>Biomonitoring</term><term>Climatic factors</term><term>Clover clones</term><term>Equation extraction</term><term>Ozone</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Ozone is a commonly occurring pollutant that has a large impact on the yield of agricultural crops. The dose–response of crops in the field is complex, with influences from numerous biotic and abiotic factors, including microclimatic variables. This paper presents results of a number of analysis methods of artificial neural network (ANN) models, developed on biomonitoring data from 12 countries, to identify the importance of interacting influences on the biomass response of sensitive (NC-S) and resistant (NC-R) clones of white clover (Trifolium repens L. cv. Regal). These methods of analysis were also used to identify the importance of influences on a subset of the data. Empirical equations were extracted from the ANN model with the best performance and these were analysed to determine their performance and to indicate the nature of microclimatic influences. Analysis indicated that combinations of VPD and the number of raindays were strong influences on the ozone dose–response and that temperature and the number of raindays had a secondary influence on the NC-S/NC-R biomass ratio irrespective of the ozone dose. Analysis of derived empirical equations indicated they compared well with the ANN model and that only a small loss in accuracy occurred.</div></front></TEI><istex><corpusName>elsevier</corpusName><author><json:item><name>G.R Ball</name><affiliations><json:string>E-mail: graham.balls@ntu.ac.uk</json:string><json:string>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</json:string></affiliations></json:item><json:item><name>D Palmer-Brown</name><affiliations><json:string>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</json:string></affiliations></json:item><json:item><name>J Fuhrer</name><affiliations><json:string>Institute for Environmental Protection and Agriculture, (IUL) Liebfeld, CH-3003 Bern, Switzerland</json:string></affiliations></json:item><json:item><name>L Skärby</name><affiliations><json:string>IVL, Box 47086, S-40258, Göteborg, Sweden</json:string></affiliations></json:item><json:item><name>B.S Gimeno</name><affiliations><json:string>CIEMAT-DIAE 3B, Avda. Complutense 22, Madrid 28040, Spain</json:string></affiliations></json:item><json:item><name>G Mills</name><affiliations><json:string>Bangor Research Unit, Institute of Terrestrial Ecology, Deiniol Road, Bangor, Gwynedd LL57 2UP, UK</json:string></affiliations></json:item></author><subject><json:item><lang><json:string>eng</json:string></lang><value>Artificial neural networks</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Equation extraction</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Ozone</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>AOT40</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Biomass dose–response</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Clover clones</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Biomonitoring</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>Climatic factors</value></json:item></subject><language><json:string>eng</json:string></language><originalGenre><json:string>Full-length article</json:string></originalGenre><abstract>Ozone is a commonly occurring pollutant that has a large impact on the yield of agricultural crops. The dose–response of crops in the field is complex, with influences from numerous biotic and abiotic factors, including microclimatic variables. This paper presents results of a number of analysis methods of artificial neural network (ANN) models, developed on biomonitoring data from 12 countries, to identify the importance of interacting influences on the biomass response of sensitive (NC-S) and resistant (NC-R) clones of white clover (Trifolium repens L. cv. Regal). These methods of analysis were also used to identify the importance of influences on a subset of the data. Empirical equations were extracted from the ANN model with the best performance and these were analysed to determine their performance and to indicate the nature of microclimatic influences. Analysis indicated that combinations of VPD and the number of raindays were strong influences on the ozone dose–response and that temperature and the number of raindays had a secondary influence on the NC-S/NC-R biomass ratio irrespective of the ozone dose. Analysis of derived empirical equations indicated they compared well with the ANN model and that only a small loss in accuracy occurred.</abstract><qualityIndicators><score>7.34</score><pdfVersion>1.2</pdfVersion><pdfPageSize>536 x 684 pts</pdfPageSize><refBibsNative>true</refBibsNative><keywordCount>8</keywordCount><abstractCharCount>1265</abstractCharCount><pdfWordCount>7064</pdfWordCount><pdfCharCount>44203</pdfCharCount><pdfPageCount>16</pdfPageCount><abstractWordCount>195</abstractWordCount></qualityIndicators><title>Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks</title><pii><json:string>S0304-3800(00)00234-9</json:string></pii><genre><json:string>research-article</json:string></genre><host><volume>129</volume><pii><json:string>S0304-3800(00)X0098-1</json:string></pii><pages><last>168</last><first>153</first></pages><issn><json:string>0304-3800</json:string></issn><issue>2–3</issue><genre><json:string>journal</json:string></genre><language><json:string>unknown</json:string></language><title>Ecological Modelling</title><publicationDate>2000</publicationDate></host><categories><wos><json:string>science</json:string><json:string>ecology</json:string></wos><scienceMetrix><json:string>natural sciences</json:string><json:string>biology</json:string><json:string>ecology</json:string></scienceMetrix></categories><publicationDate>2000</publicationDate><copyrightDate>2000</copyrightDate><doi><json:string>10.1016/S0304-3800(00)00234-9</json:string></doi><id>F582E4C071EA7ACB5B971367009B0D03CC26EACD</id><score>0.039931763</score><fulltext><json:item><extension>pdf</extension><original>true</original><mimetype>application/pdf</mimetype><uri>https://api.istex.fr/document/F582E4C071EA7ACB5B971367009B0D03CC26EACD/fulltext/pdf</uri></json:item><json:item><extension>zip</extension><original>false</original><mimetype>application/zip</mimetype><uri>https://api.istex.fr/document/F582E4C071EA7ACB5B971367009B0D03CC26EACD/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/F582E4C071EA7ACB5B971367009B0D03CC26EACD/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main" xml:lang="en">Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks</title></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>ELSEVIER</publisher><availability><p>©2000 Elsevier Science B.V.</p></availability><date>2000</date></publicationStmt><notesStmt><note type="content">Fig. 1: Actual versus predicted NC-S/NC-R biomass ratio values for model 1 (the optimised ANN model using all data) showing the relationship between actual and predicted values.</note><note type="content">Fig. 2: Graphs of model 1 predictions of the NC-S/NC-R biomass ratio response to AOT40 at a range of: (A) Tmean values, (B) VPD values and (C) Raindays values. Three-dimensional graphs have had their viewpoint altered for clarity of presentation. The shaded region indicates area where values of AOT40 and Tmean/VPD occurred. For the two-dimensional graph the number of raindays is indicated as follows 18 (+), 24 (◊), 30 (■), 36 (○), 42 (•), 48 (X).</note><note type="content">Fig. 3: Actual versus predicted NC-S/NC-R biomass ratio values for the equation extracted from model 1 showing the relationship between actual and predicted value.Fig. 1.</note><note type="content">Table 1: Location of ICP-crops sites and summary values of the environmental variables used in the modela</note><note type="content">Table 2: Correlation matrix for the database used to develop the model</note><note type="content">Table 3: Performance of models for training and test data, trained with a number of permutations of inputs and indicating the number of hidden nodes required for optimum performance and the importance of the inputs used relative to the model using all inputs (selected combinations presented)</note><note type="content">Table 4: Results of retraining the ANN model without the residuals from the earlier ANN model using different permutations of inputs</note></notesStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a" type="main" xml:lang="en">Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks</title><author xml:id="author-1"><persName><forename type="first">G.R</forename><surname>Ball</surname></persName><email>graham.balls@ntu.ac.uk</email><note type="correspondence"><p>Corresponding author. Tel.: +44-115-9418418; fax: +44-115-9486518</p></note><affiliation>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</affiliation></author><author xml:id="author-2"><persName><forename type="first">D</forename><surname>Palmer-Brown</surname></persName><affiliation>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</affiliation></author><author xml:id="author-3"><persName><forename type="first">J</forename><surname>Fuhrer</surname></persName><affiliation>Institute for Environmental Protection and Agriculture, (IUL) Liebfeld, CH-3003 Bern, Switzerland</affiliation></author><author xml:id="author-4"><persName><forename type="first">L</forename><surname>Skärby</surname></persName><affiliation>IVL, Box 47086, S-40258, Göteborg, Sweden</affiliation></author><author xml:id="author-5"><persName><forename type="first">B.S</forename><surname>Gimeno</surname></persName><affiliation>CIEMAT-DIAE 3B, Avda. Complutense 22, Madrid 28040, Spain</affiliation></author><author xml:id="author-6"><persName><forename type="first">G</forename><surname>Mills</surname></persName><affiliation>Bangor Research Unit, Institute of Terrestrial Ecology, Deiniol Road, Bangor, Gwynedd LL57 2UP, UK</affiliation></author></analytic><monogr><title level="j">Ecological Modelling</title><title level="j" type="abbrev">ECOMOD</title><idno type="pISSN">0304-3800</idno><idno type="PII">S0304-3800(00)X0098-1</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="2000"></date><biblScope unit="volume">129</biblScope><biblScope unit="issue">2–3</biblScope><biblScope unit="page" from="153">153</biblScope><biblScope unit="page" to="168">168</biblScope></imprint></monogr><idno type="istex">F582E4C071EA7ACB5B971367009B0D03CC26EACD</idno><idno type="DOI">10.1016/S0304-3800(00)00234-9</idno><idno type="PII">S0304-3800(00)00234-9</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>2000</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>Ozone is a commonly occurring pollutant that has a large impact on the yield of agricultural crops. The dose–response of crops in the field is complex, with influences from numerous biotic and abiotic factors, including microclimatic variables. This paper presents results of a number of analysis methods of artificial neural network (ANN) models, developed on biomonitoring data from 12 countries, to identify the importance of interacting influences on the biomass response of sensitive (NC-S) and resistant (NC-R) clones of white clover (Trifolium repens L. cv. Regal). These methods of analysis were also used to identify the importance of influences on a subset of the data. Empirical equations were extracted from the ANN model with the best performance and these were analysed to determine their performance and to indicate the nature of microclimatic influences. Analysis indicated that combinations of VPD and the number of raindays were strong influences on the ozone dose–response and that temperature and the number of raindays had a secondary influence on the NC-S/NC-R biomass ratio irrespective of the ozone dose. Analysis of derived empirical equations indicated they compared well with the ANN model and that only a small loss in accuracy occurred.</p></abstract><textClass xml:lang="en"><keywords scheme="keyword"><list><head>Keywords</head><item><term>Artificial neural networks</term></item><item><term>Equation extraction</term></item><item><term>Ozone</term></item><item><term>AOT40</term></item><item><term>Biomass dose–response</term></item><item><term>Clover clones</term></item><item><term>Biomonitoring</term></item><item><term>Climatic factors</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="1999-08-11">Modified</change><change when="2000">Published</change></revisionDesc></teiHeader></istex:fulltextTEI><json:item><extension>txt</extension><original>false</original><mimetype>text/plain</mimetype><uri>https://api.istex.fr/document/F582E4C071EA7ACB5B971367009B0D03CC26EACD/fulltext/txt</uri></json:item></fulltext><metadata><istex:metadataXml wicri:clean="Elsevier, elements deleted: ce:floats; body; tail"><istex:xmlDeclaration>version="1.0" encoding="utf-8"</istex:xmlDeclaration><istex:docType PUBLIC="-//ES//DTD journal article DTD version 4.5.2//EN//XML" URI="art452.dtd" name="istex:docType"><istex:entity SYSTEM="gr1" NDATA="IMAGE" name="gr1"></istex:entity><istex:entity SYSTEM="gr2a" NDATA="IMAGE" name="gr2a"></istex:entity><istex:entity SYSTEM="gr2b" NDATA="IMAGE" name="gr2b"></istex:entity><istex:entity SYSTEM="gr2c" NDATA="IMAGE" name="gr2c"></istex:entity><istex:entity SYSTEM="gr3" NDATA="IMAGE" name="gr3"></istex:entity></istex:docType><istex:document><converted-article version="4.5.2" docsubtype="fla" xml:lang="en"><item-info><jid>ECOMOD</jid><aid>2579</aid><ce:pii>S0304-3800(00)00234-9</ce:pii><ce:doi>10.1016/S0304-3800(00)00234-9</ce:doi><ce:copyright type="full-transfer" year="2000">Elsevier Science B.V.</ce:copyright></item-info><head><ce:title>Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks</ce:title><ce:author-group><ce:author><ce:given-name>G.R</ce:given-name><ce:surname>Ball</ce:surname><ce:cross-ref refid="AFF1"><ce:sup>a</ce:sup></ce:cross-ref><ce:cross-ref refid="CORR1">*</ce:cross-ref><ce:e-address>graham.balls@ntu.ac.uk</ce:e-address></ce:author><ce:author><ce:given-name>D</ce:given-name><ce:surname>Palmer-Brown</ce:surname><ce:cross-ref refid="AFF1"><ce:sup>a</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>J</ce:given-name><ce:surname>Fuhrer</ce:surname><ce:cross-ref refid="AFF2"><ce:sup>b</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>L</ce:given-name><ce:surname>Skärby</ce:surname><ce:cross-ref refid="AFF3"><ce:sup>c</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>B.S</ce:given-name><ce:surname>Gimeno</ce:surname><ce:cross-ref refid="AFF4"><ce:sup>d</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>G</ce:given-name><ce:surname>Mills</ce:surname><ce:cross-ref refid="AFF5"><ce:sup>e</ce:sup></ce:cross-ref></ce:author><ce:affiliation id="AFF1"><ce:label>a</ce:label><ce:textfn>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</ce:textfn></ce:affiliation><ce:affiliation id="AFF2"><ce:label>b</ce:label><ce:textfn>Institute for Environmental Protection and Agriculture, (IUL) Liebfeld, CH-3003 Bern, Switzerland</ce:textfn></ce:affiliation><ce:affiliation id="AFF3"><ce:label>c</ce:label><ce:textfn>IVL, Box 47086, S-40258, Göteborg, Sweden</ce:textfn></ce:affiliation><ce:affiliation id="AFF4"><ce:label>d</ce:label><ce:textfn>CIEMAT-DIAE 3B, Avda. Complutense 22, Madrid 28040, Spain</ce:textfn></ce:affiliation><ce:affiliation id="AFF5"><ce:label>e</ce:label><ce:textfn>Bangor Research Unit, Institute of Terrestrial Ecology, Deiniol Road, Bangor, Gwynedd LL57 2UP, UK</ce:textfn></ce:affiliation><ce:correspondence id="CORR1"><ce:label>*</ce:label><ce:text>Corresponding author. Tel.: +44-115-9418418; fax: +44-115-9486518</ce:text></ce:correspondence></ce:author-group><ce:date-received day="3" month="12" year="1998"></ce:date-received><ce:date-revised day="11" month="8" year="1999"></ce:date-revised><ce:date-accepted day="1" month="2" year="2000"></ce:date-accepted><ce:abstract><ce:section-title>Abstract</ce:section-title><ce:abstract-sec><ce:simple-para>Ozone is a commonly occurring pollutant that has a large impact on the yield of agricultural crops. The dose–response of crops in the field is complex, with influences from numerous biotic and abiotic factors, including microclimatic variables. This paper presents results of a number of analysis methods of artificial neural network (ANN) models, developed on biomonitoring data from 12 countries, to identify the importance of interacting influences on the biomass response of sensitive (NC-S) and resistant (NC-R) clones of white clover (<ce:italic>Trifolium repens</ce:italic> L. cv. Regal). These methods of analysis were also used to identify the importance of influences on a subset of the data. Empirical equations were extracted from the ANN model with the best performance and these were analysed to determine their performance and to indicate the nature of microclimatic influences. Analysis indicated that combinations of VPD and the number of raindays were strong influences on the ozone dose–response and that temperature and the number of raindays had a secondary influence on the NC-S/NC-R biomass ratio irrespective of the ozone dose. Analysis of derived empirical equations indicated they compared well with the ANN model and that only a small loss in accuracy occurred.</ce:simple-para></ce:abstract-sec></ce:abstract><ce:keywords class="keyword"><ce:section-title>Keywords</ce:section-title><ce:keyword><ce:text>Artificial neural networks</ce:text></ce:keyword><ce:keyword><ce:text>Equation extraction</ce:text></ce:keyword><ce:keyword><ce:text>Ozone</ce:text></ce:keyword><ce:keyword><ce:text>AOT40</ce:text></ce:keyword><ce:keyword><ce:text>Biomass dose–response</ce:text></ce:keyword><ce:keyword><ce:text>Clover clones</ce:text></ce:keyword><ce:keyword><ce:text>Biomonitoring</ce:text></ce:keyword><ce:keyword><ce:text>Climatic factors</ce:text></ce:keyword></ce:keywords></head></converted-article></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks</title></titleInfo><titleInfo type="alternative" lang="en" contentType="CDATA"><title>Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks</title></titleInfo><name type="personal"><namePart type="given">G.R</namePart><namePart type="family">Ball</namePart><affiliation>E-mail: graham.balls@ntu.ac.uk</affiliation><affiliation>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</affiliation><description>Corresponding author. Tel.: +44-115-9418418; fax: +44-115-9486518</description><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">D</namePart><namePart type="family">Palmer-Brown</namePart><affiliation>Department of Computing, Faculty of Engineering and Computing, Nottingham Trent University, Burton Street, Nottingham NG1 4BU, UK</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">J</namePart><namePart type="family">Fuhrer</namePart><affiliation>Institute for Environmental Protection and Agriculture, (IUL) Liebfeld, CH-3003 Bern, Switzerland</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">L</namePart><namePart type="family">Skärby</namePart><affiliation>IVL, Box 47086, S-40258, Göteborg, Sweden</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">B.S</namePart><namePart type="family">Gimeno</namePart><affiliation>CIEMAT-DIAE 3B, Avda. Complutense 22, Madrid 28040, Spain</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">G</namePart><namePart type="family">Mills</namePart><affiliation>Bangor Research Unit, Institute of Terrestrial Ecology, Deiniol Road, Bangor, Gwynedd LL57 2UP, UK</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="research-article" displayLabel="Full-length article"></genre><originInfo><publisher>ELSEVIER</publisher><dateIssued encoding="w3cdtf">2000</dateIssued><dateModified encoding="w3cdtf">1999-08-11</dateModified><copyrightDate encoding="w3cdtf">2000</copyrightDate></originInfo><language><languageTerm type="code" authority="iso639-2b">eng</languageTerm><languageTerm type="code" authority="rfc3066">en</languageTerm></language><physicalDescription><internetMediaType>text/html</internetMediaType></physicalDescription><abstract lang="en">Ozone is a commonly occurring pollutant that has a large impact on the yield of agricultural crops. The dose–response of crops in the field is complex, with influences from numerous biotic and abiotic factors, including microclimatic variables. This paper presents results of a number of analysis methods of artificial neural network (ANN) models, developed on biomonitoring data from 12 countries, to identify the importance of interacting influences on the biomass response of sensitive (NC-S) and resistant (NC-R) clones of white clover (Trifolium repens L. cv. Regal). These methods of analysis were also used to identify the importance of influences on a subset of the data. Empirical equations were extracted from the ANN model with the best performance and these were analysed to determine their performance and to indicate the nature of microclimatic influences. Analysis indicated that combinations of VPD and the number of raindays were strong influences on the ozone dose–response and that temperature and the number of raindays had a secondary influence on the NC-S/NC-R biomass ratio irrespective of the ozone dose. Analysis of derived empirical equations indicated they compared well with the ANN model and that only a small loss in accuracy occurred.</abstract><note type="content">Fig. 1: Actual versus predicted NC-S/NC-R biomass ratio values for model 1 (the optimised ANN model using all data) showing the relationship between actual and predicted values.</note><note type="content">Fig. 2: Graphs of model 1 predictions of the NC-S/NC-R biomass ratio response to AOT40 at a range of: (A) Tmean values, (B) VPD values and (C) Raindays values. Three-dimensional graphs have had their viewpoint altered for clarity of presentation. The shaded region indicates area where values of AOT40 and Tmean/VPD occurred. For the two-dimensional graph the number of raindays is indicated as follows 18 (+), 24 (◊), 30 (■), 36 (○), 42 (•), 48 (X).</note><note type="content">Fig. 3: Actual versus predicted NC-S/NC-R biomass ratio values for the equation extracted from model 1 showing the relationship between actual and predicted value.Fig. 1.</note><note type="content">Table 1: Location of ICP-crops sites and summary values of the environmental variables used in the modela</note><note type="content">Table 2: Correlation matrix for the database used to develop the model</note><note type="content">Table 3: Performance of models for training and test data, trained with a number of permutations of inputs and indicating the number of hidden nodes required for optimum performance and the importance of the inputs used relative to the model using all inputs (selected combinations presented)</note><note type="content">Table 4: Results of retraining the ANN model without the residuals from the earlier ANN model using different permutations of inputs</note><subject lang="en"><genre>Keywords</genre><topic>Artificial neural networks</topic><topic>Equation extraction</topic><topic>Ozone</topic><topic>AOT40</topic><topic>Biomass dose–response</topic><topic>Clover clones</topic><topic>Biomonitoring</topic><topic>Climatic factors</topic></subject><relatedItem type="host"><titleInfo><title>Ecological Modelling</title></titleInfo><titleInfo type="abbreviated"><title>ECOMOD</title></titleInfo><genre type="journal">journal</genre><originInfo><dateIssued encoding="w3cdtf">20000530</dateIssued></originInfo><identifier type="ISSN">0304-3800</identifier><identifier type="PII">S0304-3800(00)X0098-1</identifier><part><date>20000530</date><detail type="volume"><number>129</number><caption>vol.</caption></detail><detail type="issue"><number>2–3</number><caption>no.</caption></detail><extent unit="issue pages"><start>113</start><end>312</end></extent><extent unit="pages"><start>153</start><end>168</end></extent></part></relatedItem><identifier type="istex">F582E4C071EA7ACB5B971367009B0D03CC26EACD</identifier><identifier type="DOI">10.1016/S0304-3800(00)00234-9</identifier><identifier type="PII">S0304-3800(00)00234-9</identifier><accessCondition type="use and reproduction" contentType="copyright">©2000 Elsevier Science B.V.</accessCondition><recordInfo><recordContentSource>ELSEVIER</recordContentSource><recordOrigin>Elsevier Science B.V., ©2000</recordOrigin></recordInfo></mods></metadata><serie></serie></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Agronomie/explor/SisAgriV1/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000998 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000998 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Agronomie
|area= SisAgriV1
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:F582E4C071EA7ACB5B971367009B0D03CC26EACD
|texte= Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks
}}
| This area was generated with Dilib version V0.6.28. |  |