Use of near‐infrared spectroscopy to distinguish carbon and nitrogen originating from char and forest‐floor material in soils: usefulness of a genetic algorithm
Identifieur interne : 000933 ( Main/Exploration ); précédent : 000932; suivant : 000934Use of near‐infrared spectroscopy to distinguish carbon and nitrogen originating from char and forest‐floor material in soils: usefulness of a genetic algorithm
Auteurs : Michael Vohland [Allemagne] ; Kerstin Michel [Autriche] ; Bernard Ludwig [Allemagne]Source :
- Journal of Plant Nutrition and Soil Science [ 1436-8730 ] ; 2011-10.
Descripteurs français
- Pascal (Inist)
- Wicri :
English descriptors
- KwdEn :
- Algorithm, Applied mathematics, Forest soil, Genetics, Least squares method, Litter, Materials, NIR spectroscopy, Near infrared spectrometry, Nitrogen, Organic carbon, PLS regression, Reflection spectrometry, Soil plant relation, Soil science, char, genetic algorithm, partial least squares regression, soil organic carbon.
Abstract
Several algorithms exist for the calibration procedures of near‐infrared spectra in soil‐scientific studies, but the potential of a genetic algorithm (GA) for spectral feature selection and interpretation has not yet been sufficiently explored. Objectives were (1) to test the usefulness of near‐infrared spectroscopy (NIRS) for a prediction of C and N from char and forest‐floor Oa material in soils using either a partial least squares (PLS) method or a GA‐PLS approach and (2) to discuss the mechanisms of GA feature selection for the examined constituents. Calibration and validation were carried out for measured reflectance spectra in the visible and near‐IR region (400–2500 nm) on an existing set of 432 artificial mixtures of C‐free soil, char (lignite, anthracite, charcoal, or a mixture of the three coals), and forest‐floor Oa material. For all constituents (total C and N, C and N from all coals and from the Oa material, C derived from mixed coal, charcoal, lignite, and anthracite), the GA‐PLS approach was superior over the full‐spectrum PLS method. The RPD values (ratio of standard deviation of the laboratory results to standard error of prediction) ranged from 2.4 to 5.1 in the validation and indicated a better category of prediction for three constituents: “approximate quantitative” instead of a “distinction between high and low” for C derived from mixed coal and “good” instead of “approximate quantitative” for C and N derived from all coals. Overall, this study indicates that the approach using GA may have a greater potential than the PLS method in NIRS.
Url:
DOI: 10.1002/jpln.201000226
Affiliations:
- Allemagne, Autriche
- Rhénanie-Palatinat, Vienne (Autriche)
- Trèves (Allemagne), Vienne (Autriche)
- Université de Trèves
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001707
- to stream Istex, to step Curation: 001594
- to stream Istex, to step Checkpoint: 000146
- to stream Main, to step Merge: 000964
- to stream PascalFrancis, to step Corpus: 000369
- to stream PascalFrancis, to step Curation: 000982
- to stream PascalFrancis, to step Checkpoint: 000244
- to stream Main, to step Merge: 000A77
- to stream Main, to step Curation: 000933
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Use of near‐infrared spectroscopy to distinguish carbon and nitrogen originating from char and forest‐floor material in soils: usefulness of a genetic algorithm</title><author><name sortKey="Vohland, Michael" sort="Vohland, Michael" uniqKey="Vohland M" first="Michael" last="Vohland">Michael Vohland</name></author><author><name sortKey="Michel, Kerstin" sort="Michel, Kerstin" uniqKey="Michel K" first="Kerstin" last="Michel">Kerstin Michel</name></author><author><name sortKey="Ludwig, Bernard" sort="Ludwig, Bernard" uniqKey="Ludwig B" first="Bernard" last="Ludwig">Bernard Ludwig</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:A57092B3D2E142EFAF62E095A8AC0B259D7DCA44</idno><date when="2011" year="2011">2011</date><idno type="doi">10.1002/jpln.201000226</idno><idno type="url">https://api.istex.fr/document/A57092B3D2E142EFAF62E095A8AC0B259D7DCA44/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001707</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">001707</idno><idno type="wicri:Area/Istex/Curation">001594</idno><idno type="wicri:Area/Istex/Checkpoint">000146</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000146</idno><idno type="wicri:doubleKey">1436-8730:2011:Vohland M:use:of:near</idno><idno type="wicri:Area/Main/Merge">000964</idno><idno type="wicri:source">INIST</idno><idno type="RBID">Pascal:11-0476727</idno><idno type="wicri:Area/PascalFrancis/Corpus">000369</idno><idno type="wicri:Area/PascalFrancis/Curation">000982</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000244</idno><idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">000244</idno><idno type="wicri:doubleKey">1436-8730:2011:Vohland M:use:of:near</idno><idno type="wicri:Area/Main/Merge">000A77</idno><idno type="wicri:Area/Main/Curation">000933</idno><idno type="wicri:Area/Main/Exploration">000933</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Use of near‐infrared spectroscopy to distinguish carbon and nitrogen originating from char and forest‐floor material in soils: usefulness of a genetic algorithm</title><author><name sortKey="Vohland, Michael" sort="Vohland, Michael" uniqKey="Vohland M" first="Michael" last="Vohland">Michael Vohland</name><affiliation wicri:level="4"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Remote Sensing Department, University of Trier, Campus II, 54286 Trier</wicri:regionArea><orgName type="university">Université de Trèves</orgName><placeName><settlement type="city">Trèves (Allemagne)</settlement><region type="land" nuts="1">Rhénanie-Palatinat</region></placeName></affiliation></author><author><name sortKey="Michel, Kerstin" sort="Michel, Kerstin" uniqKey="Michel K" first="Kerstin" last="Michel">Kerstin Michel</name><affiliation wicri:level="3"><country xml:lang="fr">Autriche</country><wicri:regionArea>Unit of Soil Biology, Federal Research and Training Centre for Forests, Natural Hazards and Landscape (BFW), Seckendorff‐Gudent‐Weg 8, 1131 Wien</wicri:regionArea><placeName><region type="land" nuts="2">Vienne (Autriche)</region><settlement type="city">Vienne (Autriche)</settlement></placeName></affiliation></author><author><name sortKey="Ludwig, Bernard" sort="Ludwig, Bernard" uniqKey="Ludwig B" first="Bernard" last="Ludwig">Bernard Ludwig</name><affiliation wicri:level="1"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Department of Environmental Chemistry, University of Kassel, Nordbahnhofstraße 1a, 37213 Witzenhausen</wicri:regionArea><wicri:noRegion>37213 Witzenhausen</wicri:noRegion><wicri:noRegion>37213 Witzenhausen</wicri:noRegion></affiliation><affiliation wicri:level="1"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Department of Environmental Chemistry, University of Kassel, Nordbahnhofstraße 1a, 37213 Witzenhausen</wicri:regionArea><wicri:noRegion>37213 Witzenhausen</wicri:noRegion><wicri:noRegion>37213 Witzenhausen</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="j">Journal of Plant Nutrition and Soil Science</title><title level="j" type="abbrev">Z. Pflanzenernähr. Bodenk.</title><idno type="ISSN">1436-8730</idno><idno type="eISSN">1522-2624</idno><imprint><publisher>WILEY‐VCH Verlag</publisher><pubPlace>Weinheim</pubPlace><date type="published" when="2011-10">2011-10</date><biblScope unit="volume">174</biblScope><biblScope unit="issue">5</biblScope><biblScope unit="page" from="695">695</biblScope><biblScope unit="page" to="701">701</biblScope></imprint><idno type="ISSN">1436-8730</idno></series><idno type="istex">A57092B3D2E142EFAF62E095A8AC0B259D7DCA44</idno><idno type="DOI">10.1002/jpln.201000226</idno><idno type="ArticleID">JPLN201000226</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">1436-8730</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithm</term><term>Applied mathematics</term><term>Forest soil</term><term>Genetics</term><term>Least squares method</term><term>Litter</term><term>Materials</term><term>NIR spectroscopy</term><term>Near infrared spectrometry</term><term>Nitrogen</term><term>Organic carbon</term><term>PLS regression</term><term>Reflection spectrometry</term><term>Soil plant relation</term><term>Soil science</term><term>char</term><term>genetic algorithm</term><term>partial least squares regression</term><term>soil organic carbon</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Algorithme</term><term>Azote</term><term>Carbone organique</term><term>Génétique</term><term>Litière</term><term>Mathématiques appliquées</term><term>Matériau</term><term>Méthode moindre carré</term><term>Relation sol plante</term><term>Régression PLS</term><term>Science du sol</term><term>Sol forestier</term><term>Spectrométrie IR proche</term><term>Spectrométrie réflexion</term></keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Azote</term><term>Génétique</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Several algorithms exist for the calibration procedures of near‐infrared spectra in soil‐scientific studies, but the potential of a genetic algorithm (GA) for spectral feature selection and interpretation has not yet been sufficiently explored. Objectives were (1) to test the usefulness of near‐infrared spectroscopy (NIRS) for a prediction of C and N from char and forest‐floor Oa material in soils using either a partial least squares (PLS) method or a GA‐PLS approach and (2) to discuss the mechanisms of GA feature selection for the examined constituents. Calibration and validation were carried out for measured reflectance spectra in the visible and near‐IR region (400–2500 nm) on an existing set of 432 artificial mixtures of C‐free soil, char (lignite, anthracite, charcoal, or a mixture of the three coals), and forest‐floor Oa material. For all constituents (total C and N, C and N from all coals and from the Oa material, C derived from mixed coal, charcoal, lignite, and anthracite), the GA‐PLS approach was superior over the full‐spectrum PLS method. The RPD values (ratio of standard deviation of the laboratory results to standard error of prediction) ranged from 2.4 to 5.1 in the validation and indicated a better category of prediction for three constituents: “approximate quantitative” instead of a “distinction between high and low” for C derived from mixed coal and “good” instead of “approximate quantitative” for C and N derived from all coals. Overall, this study indicates that the approach using GA may have a greater potential than the PLS method in NIRS.</div></front></TEI><affiliations><list><country><li>Allemagne</li><li>Autriche</li></country><region><li>Rhénanie-Palatinat</li><li>Vienne (Autriche)</li></region><settlement><li>Trèves (Allemagne)</li><li>Vienne (Autriche)</li></settlement><orgName><li>Université de Trèves</li></orgName></list><tree><country name="Allemagne"><region name="Rhénanie-Palatinat"><name sortKey="Vohland, Michael" sort="Vohland, Michael" uniqKey="Vohland M" first="Michael" last="Vohland">Michael Vohland</name></region><name sortKey="Ludwig, Bernard" sort="Ludwig, Bernard" uniqKey="Ludwig B" first="Bernard" last="Ludwig">Bernard Ludwig</name><name sortKey="Ludwig, Bernard" sort="Ludwig, Bernard" uniqKey="Ludwig B" first="Bernard" last="Ludwig">Bernard Ludwig</name></country><country name="Autriche"><region name="Vienne (Autriche)"><name sortKey="Michel, Kerstin" sort="Michel, Kerstin" uniqKey="Michel K" first="Kerstin" last="Michel">Kerstin Michel</name></region></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Rhénanie/explor/UnivTrevesV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000933 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000933 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Rhénanie
|area= UnivTrevesV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:A57092B3D2E142EFAF62E095A8AC0B259D7DCA44
|texte= Use of near‐infrared spectroscopy to distinguish carbon and nitrogen originating from char and forest‐floor material in soils: usefulness of a genetic algorithm
}}
| This area was generated with Dilib version V0.6.31. |  |