Statistical models for prediction of dry weight and nitrogen accumulation based on visible and near-infrared hyper-spectral reflectance of rice canopies

Much information is obtainable from hyper-spectral data, which measure solar radiation consecutively at less than about 10-nm intervals. In constructing statistical prediction models, however, problems of overfitting may arise due to the excessive number of variables, and multicollinearity may occur...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Plant production science 2000, Vol.3 (4), p.377-386
Hauptverfasser: Takahashi, W. (National Agriculture Research Center, Tsukuba, Ibaraki (Japan)), Nguyen-Cong, V, Kawaguchi, S, Minamiyama, M, Ninomiya, S
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 386
container_issue 4
container_start_page 377
container_title Plant production science
container_volume 3
creator Takahashi, W. (National Agriculture Research Center, Tsukuba, Ibaraki (Japan))
Nguyen-Cong, V
Kawaguchi, S
Minamiyama, M
Ninomiya, S
description Much information is obtainable from hyper-spectral data, which measure solar radiation consecutively at less than about 10-nm intervals. In constructing statistical prediction models, however, problems of overfitting may arise due to the excessive number of variables, and multicollinearity may occur between variables ; thus a few specific wavelengths must be chosen. Various multivariate regression models were examined with ten-fold cross-validation to develop efficient, accurate models to predict dry weight and nitrogen accumulation of rice crops from the maximum tiller number stage to the meiosis stage, using plant-canopy reflectance of hyper-spectra within the 400-1100 nm domain without any variable selection. The results showed that the principal component regression using hyperspectra gave better fits and predictability than that using specific wavelengths. On the other hand, partial least squares regression was the most useful among the models tested ; this method avoided overfitting andmulticollinearity by using all wavelength information without variable selection and by inclusion of both x and y variations in its latent variables.
doi_str_mv 10.1626/pps.3.377
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1626_pps_3_377</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_cf811f88155a41e5875e7003b096c236</doaj_id><sourcerecordid>3115578791</sourcerecordid><originalsourceid>FETCH-LOGICAL-c5627-f55fcfdb5f023055103bcefdb1da4573df462d9e4e4d8be12564186605d278ac3</originalsourceid><addsrcrecordid>eNptkk2LFDEQhhtRcF09-AOEgCcPPSadj84cZfFjZUFBBW-hOqnMZunptJUel_kn_lyz07p48FRF8dRb4X3TNM8F3wjTmdfzXDZyI_v-QXMmpNq2gnP78NTLdqvk98fNk1JuOJeKG3XW_PqywJLKkjyMbJ8DjoXFTGwmDMkvKU8sRxboyG4x7a4XBlNgU1oo73Bi4P1hfxjhxA1QMLDa_EwlDSOuKAK1aYoEVZBdH2ektszoF6r3CONYW5g83l2hVKuHKc8Jy9PmUYSx4LM_9bz59u7t14sP7dWn95cXb65ar03Xt1Hr6GMYdOSd5FoLLgePdSACKN3LEJXpwhYVqmAHFJ02SlhjuA5db8HL8-Zy1Q0ZbtxMaQ90dBmSOw0y7RxQtWdE56MVIlortAYlUNteY1-dHPjW-E6aqvVy1Zop_zhgWdxNPtBUn--EUr2VQvNtpV6tlKdcSvXg_qrg7i5EV0N00tUQ_1GEUhOqNk4-lfsFa7jQqlJqparRmfZwm2kMboHjmOnvivyf-It1LUJ2sKNKffzccV6_jLSql78BH4S5TQ</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1447831509</pqid></control><display><type>article</type><title>Statistical models for prediction of dry weight and nitrogen accumulation based on visible and near-infrared hyper-spectral reflectance of rice canopies</title><source>J-STAGE (Free - Japanese)</source><source>Taylor &amp; Francis</source><source>EZB Electronic Journals Library</source><creator>Takahashi, W. (National Agriculture Research Center, Tsukuba, Ibaraki (Japan)) ; Nguyen-Cong, V ; Kawaguchi, S ; Minamiyama, M ; Ninomiya, S</creator><creatorcontrib>Takahashi, W. (National Agriculture Research Center, Tsukuba, Ibaraki (Japan)) ; Nguyen-Cong, V ; Kawaguchi, S ; Minamiyama, M ; Ninomiya, S</creatorcontrib><description>Much information is obtainable from hyper-spectral data, which measure solar radiation consecutively at less than about 10-nm intervals. In constructing statistical prediction models, however, problems of overfitting may arise due to the excessive number of variables, and multicollinearity may occur between variables ; thus a few specific wavelengths must be chosen. Various multivariate regression models were examined with ten-fold cross-validation to develop efficient, accurate models to predict dry weight and nitrogen accumulation of rice crops from the maximum tiller number stage to the meiosis stage, using plant-canopy reflectance of hyper-spectra within the 400-1100 nm domain without any variable selection. The results showed that the principal component regression using hyperspectra gave better fits and predictability than that using specific wavelengths. On the other hand, partial least squares regression was the most useful among the models tested ; this method avoided overfitting andmulticollinearity by using all wavelength information without variable selection and by inclusion of both x and y variations in its latent variables.</description><identifier>ISSN: 1343-943X</identifier><identifier>EISSN: 1349-1008</identifier><identifier>DOI: 10.1626/pps.3.377</identifier><language>eng</language><publisher>Tokyo: Taylor &amp; Francis</publisher><subject>Agronomy. Soil science and plant productions ; Biological and medical sciences ; Canopies ; CANOPY ; Cereal crops ; Cross-validation ; Dry weight ; FORECASTING ; Fundamental and applied biological sciences. Psychology ; General agronomy. Plant production ; Generalities. Agricultural and farming systems. Agricultural development ; Generalities. Production, biomass, yield. Quality ; Hyper-spectra ; INFRARED RADIATION ; IRRIGATED RICE ; MATHEMATICAL MODELS ; Nitrogen ; Nitrogen accumulation ; NITROGEN CONTENT ; PLS ; Prediction model ; Prediction models ; REFLECTANCE ; Rice ; Solar radiation ; Spectral measurement ; SPECTROMETRY ; STATISTICAL METHODS ; Statistical models ; Wavelengths ; WEIGHT</subject><ispartof>Plant production science, 2000, Vol.3 (4), p.377-386</ispartof><rights>2000 Crop Science Society of Japan 2000</rights><rights>2001 INIST-CNRS</rights><rights>Copyright Japan Science and Technology Agency 2000</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c5627-f55fcfdb5f023055103bcefdb1da4573df462d9e4e4d8be12564186605d278ac3</citedby><cites>FETCH-LOGICAL-c5627-f55fcfdb5f023055103bcefdb1da4573df462d9e4e4d8be12564186605d278ac3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.tandfonline.com/doi/pdf/10.1626/pps.3.377$$EPDF$$P50$$Ginformaworld$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.tandfonline.com/doi/full/10.1626/pps.3.377$$EHTML$$P50$$Ginformaworld$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,4024,27502,27923,27924,27925,59143,59144</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=860154$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Takahashi, W. (National Agriculture Research Center, Tsukuba, Ibaraki (Japan))</creatorcontrib><creatorcontrib>Nguyen-Cong, V</creatorcontrib><creatorcontrib>Kawaguchi, S</creatorcontrib><creatorcontrib>Minamiyama, M</creatorcontrib><creatorcontrib>Ninomiya, S</creatorcontrib><title>Statistical models for prediction of dry weight and nitrogen accumulation based on visible and near-infrared hyper-spectral reflectance of rice canopies</title><title>Plant production science</title><description>Much information is obtainable from hyper-spectral data, which measure solar radiation consecutively at less than about 10-nm intervals. In constructing statistical prediction models, however, problems of overfitting may arise due to the excessive number of variables, and multicollinearity may occur between variables ; thus a few specific wavelengths must be chosen. Various multivariate regression models were examined with ten-fold cross-validation to develop efficient, accurate models to predict dry weight and nitrogen accumulation of rice crops from the maximum tiller number stage to the meiosis stage, using plant-canopy reflectance of hyper-spectra within the 400-1100 nm domain without any variable selection. The results showed that the principal component regression using hyperspectra gave better fits and predictability than that using specific wavelengths. On the other hand, partial least squares regression was the most useful among the models tested ; this method avoided overfitting andmulticollinearity by using all wavelength information without variable selection and by inclusion of both x and y variations in its latent variables.</description><subject>Agronomy. Soil science and plant productions</subject><subject>Biological and medical sciences</subject><subject>Canopies</subject><subject>CANOPY</subject><subject>Cereal crops</subject><subject>Cross-validation</subject><subject>Dry weight</subject><subject>FORECASTING</subject><subject>Fundamental and applied biological sciences. Psychology</subject><subject>General agronomy. Plant production</subject><subject>Generalities. Agricultural and farming systems. Agricultural development</subject><subject>Generalities. Production, biomass, yield. Quality</subject><subject>Hyper-spectra</subject><subject>INFRARED RADIATION</subject><subject>IRRIGATED RICE</subject><subject>MATHEMATICAL MODELS</subject><subject>Nitrogen</subject><subject>Nitrogen accumulation</subject><subject>NITROGEN CONTENT</subject><subject>PLS</subject><subject>Prediction model</subject><subject>Prediction models</subject><subject>REFLECTANCE</subject><subject>Rice</subject><subject>Solar radiation</subject><subject>Spectral measurement</subject><subject>SPECTROMETRY</subject><subject>STATISTICAL METHODS</subject><subject>Statistical models</subject><subject>Wavelengths</subject><subject>WEIGHT</subject><issn>1343-943X</issn><issn>1349-1008</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2000</creationdate><recordtype>article</recordtype><sourceid>0YH</sourceid><sourceid>DOA</sourceid><recordid>eNptkk2LFDEQhhtRcF09-AOEgCcPPSadj84cZfFjZUFBBW-hOqnMZunptJUel_kn_lyz07p48FRF8dRb4X3TNM8F3wjTmdfzXDZyI_v-QXMmpNq2gnP78NTLdqvk98fNk1JuOJeKG3XW_PqywJLKkjyMbJ8DjoXFTGwmDMkvKU8sRxboyG4x7a4XBlNgU1oo73Bi4P1hfxjhxA1QMLDa_EwlDSOuKAK1aYoEVZBdH2ektszoF6r3CONYW5g83l2hVKuHKc8Jy9PmUYSx4LM_9bz59u7t14sP7dWn95cXb65ar03Xt1Hr6GMYdOSd5FoLLgePdSACKN3LEJXpwhYVqmAHFJ02SlhjuA5db8HL8-Zy1Q0ZbtxMaQ90dBmSOw0y7RxQtWdE56MVIlortAYlUNteY1-dHPjW-E6aqvVy1Zop_zhgWdxNPtBUn--EUr2VQvNtpV6tlKdcSvXg_qrg7i5EV0N00tUQ_1GEUhOqNk4-lfsFa7jQqlJqparRmfZwm2kMboHjmOnvivyf-It1LUJ2sKNKffzccV6_jLSql78BH4S5TQ</recordid><startdate>2000</startdate><enddate>2000</enddate><creator>Takahashi, W. (National Agriculture Research Center, Tsukuba, Ibaraki (Japan))</creator><creator>Nguyen-Cong, V</creator><creator>Kawaguchi, S</creator><creator>Minamiyama, M</creator><creator>Ninomiya, S</creator><general>Taylor &amp; Francis</general><general>Crop Science Society of Japan</general><general>Taylor &amp; Francis Ltd</general><general>Taylor &amp; Francis Group</general><scope>FBQ</scope><scope>0YH</scope><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QO</scope><scope>7ST</scope><scope>7T7</scope><scope>8FD</scope><scope>C1K</scope><scope>FR3</scope><scope>P64</scope><scope>RC3</scope><scope>SOI</scope><scope>DOA</scope></search><sort><creationdate>2000</creationdate><title>Statistical models for prediction of dry weight and nitrogen accumulation based on visible and near-infrared hyper-spectral reflectance of rice canopies</title><author>Takahashi, W. (National Agriculture Research Center, Tsukuba, Ibaraki (Japan)) ; Nguyen-Cong, V ; Kawaguchi, S ; Minamiyama, M ; Ninomiya, S</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c5627-f55fcfdb5f023055103bcefdb1da4573df462d9e4e4d8be12564186605d278ac3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2000</creationdate><topic>Agronomy. Soil science and plant productions</topic><topic>Biological and medical sciences</topic><topic>Canopies</topic><topic>CANOPY</topic><topic>Cereal crops</topic><topic>Cross-validation</topic><topic>Dry weight</topic><topic>FORECASTING</topic><topic>Fundamental and applied biological sciences. Psychology</topic><topic>General agronomy. Plant production</topic><topic>Generalities. Agricultural and farming systems. Agricultural development</topic><topic>Generalities. Production, biomass, yield. Quality</topic><topic>Hyper-spectra</topic><topic>INFRARED RADIATION</topic><topic>IRRIGATED RICE</topic><topic>MATHEMATICAL MODELS</topic><topic>Nitrogen</topic><topic>Nitrogen accumulation</topic><topic>NITROGEN CONTENT</topic><topic>PLS</topic><topic>Prediction model</topic><topic>Prediction models</topic><topic>REFLECTANCE</topic><topic>Rice</topic><topic>Solar radiation</topic><topic>Spectral measurement</topic><topic>SPECTROMETRY</topic><topic>STATISTICAL METHODS</topic><topic>Statistical models</topic><topic>Wavelengths</topic><topic>WEIGHT</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Takahashi, W. (National Agriculture Research Center, Tsukuba, Ibaraki (Japan))</creatorcontrib><creatorcontrib>Nguyen-Cong, V</creatorcontrib><creatorcontrib>Kawaguchi, S</creatorcontrib><creatorcontrib>Minamiyama, M</creatorcontrib><creatorcontrib>Ninomiya, S</creatorcontrib><collection>AGRIS</collection><collection>Taylor &amp; Francis</collection><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Biotechnology Research Abstracts</collection><collection>Environment Abstracts</collection><collection>Industrial and Applied Microbiology Abstracts (Microbiology A)</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>Genetics Abstracts</collection><collection>Environment Abstracts</collection><collection>Directory of Open Access Journals(OpenAccess)</collection><jtitle>Plant production science</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Takahashi, W. (National Agriculture Research Center, Tsukuba, Ibaraki (Japan))</au><au>Nguyen-Cong, V</au><au>Kawaguchi, S</au><au>Minamiyama, M</au><au>Ninomiya, S</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Statistical models for prediction of dry weight and nitrogen accumulation based on visible and near-infrared hyper-spectral reflectance of rice canopies</atitle><jtitle>Plant production science</jtitle><date>2000</date><risdate>2000</risdate><volume>3</volume><issue>4</issue><spage>377</spage><epage>386</epage><pages>377-386</pages><issn>1343-943X</issn><eissn>1349-1008</eissn><abstract>Much information is obtainable from hyper-spectral data, which measure solar radiation consecutively at less than about 10-nm intervals. In constructing statistical prediction models, however, problems of overfitting may arise due to the excessive number of variables, and multicollinearity may occur between variables ; thus a few specific wavelengths must be chosen. Various multivariate regression models were examined with ten-fold cross-validation to develop efficient, accurate models to predict dry weight and nitrogen accumulation of rice crops from the maximum tiller number stage to the meiosis stage, using plant-canopy reflectance of hyper-spectra within the 400-1100 nm domain without any variable selection. The results showed that the principal component regression using hyperspectra gave better fits and predictability than that using specific wavelengths. On the other hand, partial least squares regression was the most useful among the models tested ; this method avoided overfitting andmulticollinearity by using all wavelength information without variable selection and by inclusion of both x and y variations in its latent variables.</abstract><cop>Tokyo</cop><pub>Taylor &amp; Francis</pub><doi>10.1626/pps.3.377</doi><tpages>10</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1343-943X
ispartof Plant production science, 2000, Vol.3 (4), p.377-386
issn 1343-943X
1349-1008
language eng
recordid cdi_crossref_primary_10_1626_pps_3_377
source J-STAGE (Free - Japanese); Taylor & Francis; EZB Electronic Journals Library
subjects Agronomy. Soil science and plant productions
Biological and medical sciences
Canopies
CANOPY
Cereal crops
Cross-validation
Dry weight
FORECASTING
Fundamental and applied biological sciences. Psychology
General agronomy. Plant production
Generalities. Agricultural and farming systems. Agricultural development
Generalities. Production, biomass, yield. Quality
Hyper-spectra
INFRARED RADIATION
IRRIGATED RICE
MATHEMATICAL MODELS
Nitrogen
Nitrogen accumulation
NITROGEN CONTENT
PLS
Prediction model
Prediction models
REFLECTANCE
Rice
Solar radiation
Spectral measurement
SPECTROMETRY
STATISTICAL METHODS
Statistical models
Wavelengths
WEIGHT
title Statistical models for prediction of dry weight and nitrogen accumulation based on visible and near-infrared hyper-spectral reflectance of rice canopies
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T09%3A40%3A57IST&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=Statistical%20models%20for%20prediction%20of%20dry%20weight%20and%20nitrogen%20accumulation%20based%20on%20visible%20and%20near-infrared%20hyper-spectral%20reflectance%20of%20rice%20canopies&rft.jtitle=Plant%20production%20science&rft.au=Takahashi,%20W.%20(National%20Agriculture%20Research%20Center,%20Tsukuba,%20Ibaraki%20(Japan))&rft.date=2000&rft.volume=3&rft.issue=4&rft.spage=377&rft.epage=386&rft.pages=377-386&rft.issn=1343-943X&rft.eissn=1349-1008&rft_id=info:doi/10.1626/pps.3.377&rft_dat=%3Cproquest_cross%3E3115578791%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1447831509&rft_id=info:pmid/&rft_doaj_id=oai_doaj_org_article_cf811f88155a41e5875e7003b096c236&rfr_iscdi=true