Variable selection in near infrared spectra for the biological characterization of soil and earthworm casts
Near infrared reflectance spectroscopy (NIRS) was used to predict six biological properties of soil and earthworm casts including extracellular soil enzymes, microbial carbon, potential nitrification and denitrification. Partial least squares regression (PLSR) models were developed with a selection...
Gespeichert in:
| Veröffentlicht in: | Soil biology & biochemistry 2008-07, Vol.40 (7), p.1975-1979 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1979 |
|---|---|
| container_issue | 7 |
| container_start_page | 1975 |
| container_title | Soil biology & biochemistry |
| container_volume | 40 |
| creator | Cécillon, Lauric Cassagne, Nathalie Czarnes, Sonia Gros, Raphaël Brun, Jean-Jacques |
| description | Near infrared reflectance spectroscopy (NIRS) was used to predict six biological properties of soil and earthworm casts including extracellular soil enzymes, microbial carbon, potential nitrification and denitrification. Partial least squares regression (PLSR) models were developed with a selection of the most important near infrared wavelengths. They reached coefficients of determination ranging from 0.81 to 0.91 and ratios of performance-to-deviation above 2.3. Variable selection with the variable importance in the projection (VIP) method increased dramatically the prediction performance of all models with an important contribution from the 1750–2500
nm region. We discuss whether selected wavelengths can be attributed to macronutrient availability or to microbial biomass. Wavelength selection in NIR spectra is recommended for improving PLSR models in soil research. |
| doi_str_mv | 10.1016/j.soilbio.2008.03.016 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_hal_p</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_hal_00396129v3</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0038071708001260</els_id><sourcerecordid>19660579</sourcerecordid><originalsourceid>FETCH-LOGICAL-c541t-d559557e7b749f26f671150befd73f79325b7d3a1d06428886193151830376283</originalsourceid><addsrcrecordid>eNqFkU9v1DAQxS1EJZaFj4DwBSQOCeN4bScnVFWUIq3EoX-u1sSxu1688WKnRfDp65BVr5xGGv_mzfg9Qt4xqBkw-Xlf5-hD72PdALQ18Lp0X5AVa1VX8U3TviQrAN5WoJh6RV7nvAeARjC-Ij_vMHnsg6XZBmsmH0fqRzpaTKW6hMkONB_LS0LqYqLTztKyKsR7bzBQs8OEZrLJ_8V_w9HR-RqK40CLyLT7HdOBGsxTfkPOHIZs357qmtxefr25uKq2P759vzjfVkZs2FQNQnRCKKt6telcI51UjAnorRsUd6rjjejVwJENIMvn2layjjPBWg5cyabla_Jp0d1h0MfkD5j-6IheX51v9dwrZnSSNd0jL-zHhT2m-OvB5kkffDY2BBxtfMiadVKCKEvXRCygSTHnZN2zMgM9x6D3-hSDnmPQwHXplrkPpwWYi2HF0dH4_DzcwEZJ0c6HvF84h1HjfSrM7XUDjAN0rOhDIb4shC3ePXqbdDbejsYOPpV89BD9f255AolUqLU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>19660579</pqid></control><display><type>article</type><title>Variable selection in near infrared spectra for the biological characterization of soil and earthworm casts</title><source>Elsevier ScienceDirect Journals</source><creator>Cécillon, Lauric ; Cassagne, Nathalie ; Czarnes, Sonia ; Gros, Raphaël ; Brun, Jean-Jacques</creator><creatorcontrib>Cécillon, Lauric ; Cassagne, Nathalie ; Czarnes, Sonia ; Gros, Raphaël ; Brun, Jean-Jacques</creatorcontrib><description>Near infrared reflectance spectroscopy (NIRS) was used to predict six biological properties of soil and earthworm casts including extracellular soil enzymes, microbial carbon, potential nitrification and denitrification. Partial least squares regression (PLSR) models were developed with a selection of the most important near infrared wavelengths. They reached coefficients of determination ranging from 0.81 to 0.91 and ratios of performance-to-deviation above 2.3. Variable selection with the variable importance in the projection (VIP) method increased dramatically the prediction performance of all models with an important contribution from the 1750–2500
nm region. We discuss whether selected wavelengths can be attributed to macronutrient availability or to microbial biomass. Wavelength selection in NIR spectra is recommended for improving PLSR models in soil research.</description><identifier>ISSN: 0038-0717</identifier><identifier>EISSN: 1879-3428</identifier><identifier>DOI: 10.1016/j.soilbio.2008.03.016</identifier><identifier>CODEN: SBIOAH</identifier><language>eng</language><publisher>Oxford: Elsevier Ltd</publisher><subject>Agricultural sciences ; Agronomy. Soil science and plant productions ; Biochemistry and biology ; Biological and medical sciences ; carbon ; Chemical, physicochemical, biochemical and biological properties ; denitrification ; earthworms ; forest soils ; Fundamental and applied biological sciences. Psychology ; least squares ; Life Sciences ; microbial activity ; Microbiological activity ; Microbiology ; near-infrared spectroscopy ; NIRS ; nitrification ; nutrients ; Physical properties ; Physics, chemistry, biochemistry and biology of agricultural and forest soils ; PLSR ; prediction ; Soil biogenic structures ; soil biological properties ; soil enzymes ; Soil macrofauna ; soil microorganisms ; Soil science ; Soil study ; Structure, texture, density, mechanical behavior. Heat and gas exchanges ; Wavelength selection ; worm casts ; Zoology (interactions between soil fauna and agricultural or forest soils)</subject><ispartof>Soil biology & biochemistry, 2008-07, Vol.40 (7), p.1975-1979</ispartof><rights>2008 Elsevier Ltd</rights><rights>2008 INIST-CNRS</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c541t-d559557e7b749f26f671150befd73f79325b7d3a1d06428886193151830376283</citedby><cites>FETCH-LOGICAL-c541t-d559557e7b749f26f671150befd73f79325b7d3a1d06428886193151830376283</cites><orcidid>0000-0001-7795-2382 ; 0000-0002-7612-5577 ; 0000-0001-6296-0558</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0038071708001260$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>230,314,776,780,881,3537,27901,27902,65534</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=20476583$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://hal.science/hal-00396129$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Cécillon, Lauric</creatorcontrib><creatorcontrib>Cassagne, Nathalie</creatorcontrib><creatorcontrib>Czarnes, Sonia</creatorcontrib><creatorcontrib>Gros, Raphaël</creatorcontrib><creatorcontrib>Brun, Jean-Jacques</creatorcontrib><title>Variable selection in near infrared spectra for the biological characterization of soil and earthworm casts</title><title>Soil biology & biochemistry</title><description>Near infrared reflectance spectroscopy (NIRS) was used to predict six biological properties of soil and earthworm casts including extracellular soil enzymes, microbial carbon, potential nitrification and denitrification. Partial least squares regression (PLSR) models were developed with a selection of the most important near infrared wavelengths. They reached coefficients of determination ranging from 0.81 to 0.91 and ratios of performance-to-deviation above 2.3. Variable selection with the variable importance in the projection (VIP) method increased dramatically the prediction performance of all models with an important contribution from the 1750–2500
nm region. We discuss whether selected wavelengths can be attributed to macronutrient availability or to microbial biomass. Wavelength selection in NIR spectra is recommended for improving PLSR models in soil research.</description><subject>Agricultural sciences</subject><subject>Agronomy. Soil science and plant productions</subject><subject>Biochemistry and biology</subject><subject>Biological and medical sciences</subject><subject>carbon</subject><subject>Chemical, physicochemical, biochemical and biological properties</subject><subject>denitrification</subject><subject>earthworms</subject><subject>forest soils</subject><subject>Fundamental and applied biological sciences. Psychology</subject><subject>least squares</subject><subject>Life Sciences</subject><subject>microbial activity</subject><subject>Microbiological activity</subject><subject>Microbiology</subject><subject>near-infrared spectroscopy</subject><subject>NIRS</subject><subject>nitrification</subject><subject>nutrients</subject><subject>Physical properties</subject><subject>Physics, chemistry, biochemistry and biology of agricultural and forest soils</subject><subject>PLSR</subject><subject>prediction</subject><subject>Soil biogenic structures</subject><subject>soil biological properties</subject><subject>soil enzymes</subject><subject>Soil macrofauna</subject><subject>soil microorganisms</subject><subject>Soil science</subject><subject>Soil study</subject><subject>Structure, texture, density, mechanical behavior. Heat and gas exchanges</subject><subject>Wavelength selection</subject><subject>worm casts</subject><subject>Zoology (interactions between soil fauna and agricultural or forest soils)</subject><issn>0038-0717</issn><issn>1879-3428</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2008</creationdate><recordtype>article</recordtype><recordid>eNqFkU9v1DAQxS1EJZaFj4DwBSQOCeN4bScnVFWUIq3EoX-u1sSxu1688WKnRfDp65BVr5xGGv_mzfg9Qt4xqBkw-Xlf5-hD72PdALQ18Lp0X5AVa1VX8U3TviQrAN5WoJh6RV7nvAeARjC-Ij_vMHnsg6XZBmsmH0fqRzpaTKW6hMkONB_LS0LqYqLTztKyKsR7bzBQs8OEZrLJ_8V_w9HR-RqK40CLyLT7HdOBGsxTfkPOHIZs357qmtxefr25uKq2P759vzjfVkZs2FQNQnRCKKt6telcI51UjAnorRsUd6rjjejVwJENIMvn2layjjPBWg5cyabla_Jp0d1h0MfkD5j-6IheX51v9dwrZnSSNd0jL-zHhT2m-OvB5kkffDY2BBxtfMiadVKCKEvXRCygSTHnZN2zMgM9x6D3-hSDnmPQwHXplrkPpwWYi2HF0dH4_DzcwEZJ0c6HvF84h1HjfSrM7XUDjAN0rOhDIb4shC3ePXqbdDbejsYOPpV89BD9f255AolUqLU</recordid><startdate>20080701</startdate><enddate>20080701</enddate><creator>Cécillon, Lauric</creator><creator>Cassagne, Nathalie</creator><creator>Czarnes, Sonia</creator><creator>Gros, Raphaël</creator><creator>Brun, Jean-Jacques</creator><general>Elsevier Ltd</general><general>Elsevier Science</general><general>Elsevier</general><scope>FBQ</scope><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SN</scope><scope>7T7</scope><scope>8FD</scope><scope>C1K</scope><scope>FR3</scope><scope>P64</scope><scope>1XC</scope><scope>VOOES</scope><orcidid>https://orcid.org/0000-0001-7795-2382</orcidid><orcidid>https://orcid.org/0000-0002-7612-5577</orcidid><orcidid>https://orcid.org/0000-0001-6296-0558</orcidid></search><sort><creationdate>20080701</creationdate><title>Variable selection in near infrared spectra for the biological characterization of soil and earthworm casts</title><author>Cécillon, Lauric ; Cassagne, Nathalie ; Czarnes, Sonia ; Gros, Raphaël ; Brun, Jean-Jacques</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c541t-d559557e7b749f26f671150befd73f79325b7d3a1d06428886193151830376283</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Agricultural sciences</topic><topic>Agronomy. Soil science and plant productions</topic><topic>Biochemistry and biology</topic><topic>Biological and medical sciences</topic><topic>carbon</topic><topic>Chemical, physicochemical, biochemical and biological properties</topic><topic>denitrification</topic><topic>earthworms</topic><topic>forest soils</topic><topic>Fundamental and applied biological sciences. Psychology</topic><topic>least squares</topic><topic>Life Sciences</topic><topic>microbial activity</topic><topic>Microbiological activity</topic><topic>Microbiology</topic><topic>near-infrared spectroscopy</topic><topic>NIRS</topic><topic>nitrification</topic><topic>nutrients</topic><topic>Physical properties</topic><topic>Physics, chemistry, biochemistry and biology of agricultural and forest soils</topic><topic>PLSR</topic><topic>prediction</topic><topic>Soil biogenic structures</topic><topic>soil biological properties</topic><topic>soil enzymes</topic><topic>Soil macrofauna</topic><topic>soil microorganisms</topic><topic>Soil science</topic><topic>Soil study</topic><topic>Structure, texture, density, mechanical behavior. Heat and gas exchanges</topic><topic>Wavelength selection</topic><topic>worm casts</topic><topic>Zoology (interactions between soil fauna and agricultural or forest soils)</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Cécillon, Lauric</creatorcontrib><creatorcontrib>Cassagne, Nathalie</creatorcontrib><creatorcontrib>Czarnes, Sonia</creatorcontrib><creatorcontrib>Gros, Raphaël</creatorcontrib><creatorcontrib>Brun, Jean-Jacques</creatorcontrib><collection>AGRIS</collection><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Ecology 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>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><jtitle>Soil biology & biochemistry</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cécillon, Lauric</au><au>Cassagne, Nathalie</au><au>Czarnes, Sonia</au><au>Gros, Raphaël</au><au>Brun, Jean-Jacques</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Variable selection in near infrared spectra for the biological characterization of soil and earthworm casts</atitle><jtitle>Soil biology & biochemistry</jtitle><date>2008-07-01</date><risdate>2008</risdate><volume>40</volume><issue>7</issue><spage>1975</spage><epage>1979</epage><pages>1975-1979</pages><issn>0038-0717</issn><eissn>1879-3428</eissn><coden>SBIOAH</coden><abstract>Near infrared reflectance spectroscopy (NIRS) was used to predict six biological properties of soil and earthworm casts including extracellular soil enzymes, microbial carbon, potential nitrification and denitrification. Partial least squares regression (PLSR) models were developed with a selection of the most important near infrared wavelengths. They reached coefficients of determination ranging from 0.81 to 0.91 and ratios of performance-to-deviation above 2.3. Variable selection with the variable importance in the projection (VIP) method increased dramatically the prediction performance of all models with an important contribution from the 1750–2500
nm region. We discuss whether selected wavelengths can be attributed to macronutrient availability or to microbial biomass. Wavelength selection in NIR spectra is recommended for improving PLSR models in soil research.</abstract><cop>Oxford</cop><cop>New York, NY</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.soilbio.2008.03.016</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0001-7795-2382</orcidid><orcidid>https://orcid.org/0000-0002-7612-5577</orcidid><orcidid>https://orcid.org/0000-0001-6296-0558</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0038-0717 |
| ispartof | Soil biology & biochemistry, 2008-07, Vol.40 (7), p.1975-1979 |
| issn | 0038-0717 1879-3428 |
| language | eng |
| recordid | cdi_hal_primary_oai_HAL_hal_00396129v3 |
| source | Elsevier ScienceDirect Journals |
| subjects | Agricultural sciences Agronomy. Soil science and plant productions Biochemistry and biology Biological and medical sciences carbon Chemical, physicochemical, biochemical and biological properties denitrification earthworms forest soils Fundamental and applied biological sciences. Psychology least squares Life Sciences microbial activity Microbiological activity Microbiology near-infrared spectroscopy NIRS nitrification nutrients Physical properties Physics, chemistry, biochemistry and biology of agricultural and forest soils PLSR prediction Soil biogenic structures soil biological properties soil enzymes Soil macrofauna soil microorganisms Soil science Soil study Structure, texture, density, mechanical behavior. Heat and gas exchanges Wavelength selection worm casts Zoology (interactions between soil fauna and agricultural or forest soils) |
| title | Variable selection in near infrared spectra for the biological characterization of soil and earthworm casts |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-15T00%3A12%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_hal_p&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Variable%20selection%20in%20near%20infrared%20spectra%20for%20the%20biological%20characterization%20of%20soil%20and%20earthworm%20casts&rft.jtitle=Soil%20biology%20&%20biochemistry&rft.au=C%C3%A9cillon,%20Lauric&rft.date=2008-07-01&rft.volume=40&rft.issue=7&rft.spage=1975&rft.epage=1979&rft.pages=1975-1979&rft.issn=0038-0717&rft.eissn=1879-3428&rft.coden=SBIOAH&rft_id=info:doi/10.1016/j.soilbio.2008.03.016&rft_dat=%3Cproquest_hal_p%3E19660579%3C/proquest_hal_p%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=19660579&rft_id=info:pmid/&rft_els_id=S0038071708001260&rfr_iscdi=true |