Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia
Identifieur interne : 000D72 ( Istex/Corpus ); précédent : 000D71; suivant : 000D73Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia
Auteurs : Elisabeth Bui ; Brent Henderson ; Karin ViergeverSource :
- Global Biogeochemical Cycles [ 0886-6236 ] ; 2009-12.
Abstract
We present a piecewise linear decision tree model for predicting percent of soil organic C (SOC) in the agricultural zones of Australia generated using a machine learning approach. The inputs for the model are a national database of soil data, national digital surfaces of climate, elevation, and terrain variables, Landsat multispectral scanner data, lithology, land use, and soil maps. The model and resulting map are evaluated, and insights into biogeological surficial processes are discussed. The decision tree splits the overall data set into more homogenous subsets, thus in this case, it identifies areas where SOC responds closely to climatic and other environmental variables. The spatial pattern of SOC corresponds well to maps of estimated primary productivity and bioclimatic zones. Topsoil organic C levels are highest in the high rainfall, temperate regions of Tasmania, Victoria, and Western Australia, along the coast of New South Wales and in the wet tropics of Queensland; and lowest in arid and semiarid inland regions. While this pattern broadly follows continental vegetation, soil moisture, and temperature patterns, it is governed by a spatially variable hierarchy of different climatic and other variables across bioregions of Australia. At the continental scale, soil moisture level, rather than temperature, seems most important in controlling SOC.
Url:
DOI: 10.1029/2009GB003506
Links to Exploration step
ISTEX:343D8590C12435A6A6F6723AAB31136235AB078ELe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia</title><author><name sortKey="Bui, Elisabeth" sort="Bui, Elisabeth" uniqKey="Bui E" first="Elisabeth" last="Bui">Elisabeth Bui</name><affiliation><mods:affiliation>Land and Water, CSIRO, Canberra, ACT, Australia</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: elisabeth.bui@csiro.au</mods:affiliation></affiliation></author><author><name sortKey="Henderson, Brent" sort="Henderson, Brent" uniqKey="Henderson B" first="Brent" last="Henderson">Brent Henderson</name><affiliation><mods:affiliation>Mathematical and Information Sciences, CSIRO, Canberra, ACT, Australia</mods:affiliation></affiliation></author><author><name sortKey="Viergever, Karin" sort="Viergever, Karin" uniqKey="Viergever K" first="Karin" last="Viergever">Karin Viergever</name><affiliation><mods:affiliation>Ecometrica, Edinburgh, UK</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:343D8590C12435A6A6F6723AAB31136235AB078E</idno><date when="2009" year="2009">2009</date><idno type="doi">10.1029/2009GB003506</idno><idno type="url">https://api.istex.fr/document/343D8590C12435A6A6F6723AAB31136235AB078E/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000D72</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000D72</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia</title><author><name sortKey="Bui, Elisabeth" sort="Bui, Elisabeth" uniqKey="Bui E" first="Elisabeth" last="Bui">Elisabeth Bui</name><affiliation><mods:affiliation>Land and Water, CSIRO, Canberra, ACT, Australia</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: elisabeth.bui@csiro.au</mods:affiliation></affiliation></author><author><name sortKey="Henderson, Brent" sort="Henderson, Brent" uniqKey="Henderson B" first="Brent" last="Henderson">Brent Henderson</name><affiliation><mods:affiliation>Mathematical and Information Sciences, CSIRO, Canberra, ACT, Australia</mods:affiliation></affiliation></author><author><name sortKey="Viergever, Karin" sort="Viergever, Karin" uniqKey="Viergever K" first="Karin" last="Viergever">Karin Viergever</name><affiliation><mods:affiliation>Ecometrica, Edinburgh, UK</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j">Global Biogeochemical Cycles</title><title level="j" type="abbrev">Global Biogeochem. Cycles</title><idno type="ISSN">0886-6236</idno><idno type="eISSN">1944-9224</idno><imprint><publisher>Blackwell Publishing Ltd</publisher><date type="published" when="2009-12">2009-12</date><biblScope unit="volume">23</biblScope><biblScope unit="issue">4</biblScope><biblScope unit="page" from="/">n/a</biblScope><biblScope unit="page" to="/">n/a</biblScope></imprint><idno type="ISSN">0886-6236</idno></series><idno type="istex">343D8590C12435A6A6F6723AAB31136235AB078E</idno><idno type="DOI">10.1029/2009GB003506</idno><idno type="ArticleID">2009GB003506</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0886-6236</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract">We present a piecewise linear decision tree model for predicting percent of soil organic C (SOC) in the agricultural zones of Australia generated using a machine learning approach. The inputs for the model are a national database of soil data, national digital surfaces of climate, elevation, and terrain variables, Landsat multispectral scanner data, lithology, land use, and soil maps. The model and resulting map are evaluated, and insights into biogeological surficial processes are discussed. The decision tree splits the overall data set into more homogenous subsets, thus in this case, it identifies areas where SOC responds closely to climatic and other environmental variables. The spatial pattern of SOC corresponds well to maps of estimated primary productivity and bioclimatic zones. Topsoil organic C levels are highest in the high rainfall, temperate regions of Tasmania, Victoria, and Western Australia, along the coast of New South Wales and in the wet tropics of Queensland; and lowest in arid and semiarid inland regions. While this pattern broadly follows continental vegetation, soil moisture, and temperature patterns, it is governed by a spatially variable hierarchy of different climatic and other variables across bioregions of Australia. At the continental scale, soil moisture level, rather than temperature, seems most important in controlling SOC.</div></front></TEI><istex><corpusName>wiley</corpusName><author><json:item><name>Elisabeth Bui</name><affiliations><json:string>Land and Water, CSIRO, Canberra, ACT, Australia</json:string><json:string>E-mail: elisabeth.bui@csiro.au</json:string></affiliations></json:item><json:item><name>Brent Henderson</name><affiliations><json:string>Mathematical and Information Sciences, CSIRO, Canberra, ACT, Australia</json:string></affiliations></json:item><json:item><name>Karin Viergever</name><affiliations><json:string>Ecometrica, Edinburgh, UK</json:string></affiliations></json:item></author><subject><json:item><lang><json:string>eng</json:string></lang><value>soil organic C mapping</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>C stock</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>bioregional landscape processes</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>driving factors</value></json:item><json:item><lang><json:string>eng</json:string></lang><value>emergent thresholds</value></json:item></subject><articleId><json:string>2009GB003506</json:string></articleId><language><json:string>eng</json:string></language><originalGenre><json:string>article</json:string></originalGenre><abstract>We present a piecewise linear decision tree model for predicting percent of soil organic C (SOC) in the agricultural zones of Australia generated using a machine learning approach. The inputs for the model are a national database of soil data, national digital surfaces of climate, elevation, and terrain variables, Landsat multispectral scanner data, lithology, land use, and soil maps. The model and resulting map are evaluated, and insights into biogeological surficial processes are discussed. The decision tree splits the overall data set into more homogenous subsets, thus in this case, it identifies areas where SOC responds closely to climatic and other environmental variables. The spatial pattern of SOC corresponds well to maps of estimated primary productivity and bioclimatic zones. Topsoil organic C levels are highest in the high rainfall, temperate regions of Tasmania, Victoria, and Western Australia, along the coast of New South Wales and in the wet tropics of Queensland; and lowest in arid and semiarid inland regions. While this pattern broadly follows continental vegetation, soil moisture, and temperature patterns, it is governed by a spatially variable hierarchy of different climatic and other variables across bioregions of Australia. At the continental scale, soil moisture level, rather than temperature, seems most important in controlling SOC.</abstract><qualityIndicators><score>7.96</score><pdfVersion>1.4</pdfVersion><pdfPageSize>612 x 792 pts (letter)</pdfPageSize><refBibsNative>true</refBibsNative><abstractCharCount>1375</abstractCharCount><pdfWordCount>8382</pdfWordCount><pdfCharCount>50583</pdfCharCount><pdfPageCount>15</pdfPageCount><abstractWordCount>205</abstractWordCount></qualityIndicators><title>Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia</title><genre><json:string>article</json:string></genre><host><volume>23</volume><publisherId><json:string>GBC</json:string></publisherId><pages><total>15</total><last>n/a</last><first>n/a</first></pages><issn><json:string>0886-6236</json:string></issn><issue>4</issue><subject><json:item><value>BIOGEOSCIENCES</value></json:item><json:item><value>Carbon cycling</value></json:item><json:item><value>OCEANOGRAPHY: BIOLOGICAL AND CHEMICAL</value></json:item><json:item><value>Carbon cycling</value></json:item></subject><genre><json:string>journal</json:string></genre><language><json:string>unknown</json:string></language><eissn><json:string>1944-9224</json:string></eissn><title>Global Biogeochemical Cycles</title><doi><json:string>10.1002/(ISSN)1944-9224</json:string></doi></host><categories><wos><json:string>science</json:string><json:string>meteorology & atmospheric sciences</json:string><json:string>geosciences, multidisciplinary</json:string><json:string>environmental sciences</json:string></wos><scienceMetrix><json:string>natural sciences</json:string><json:string>earth & environmental sciences</json:string><json:string>meteorology & atmospheric sciences</json:string></scienceMetrix></categories><publicationDate>2009</publicationDate><copyrightDate>2009</copyrightDate><doi><json:string>10.1029/2009GB003506</json:string></doi><id>343D8590C12435A6A6F6723AAB31136235AB078E</id><score>0.040845852</score><fulltext><json:item><extension>pdf</extension><original>true</original><mimetype>application/pdf</mimetype><uri>https://api.istex.fr/document/343D8590C12435A6A6F6723AAB31136235AB078E/fulltext/pdf</uri></json:item><json:item><extension>zip</extension><original>false</original><mimetype>application/zip</mimetype><uri>https://api.istex.fr/document/343D8590C12435A6A6F6723AAB31136235AB078E/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/343D8590C12435A6A6F6723AAB31136235AB078E/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main" xml:lang="en">Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia</title></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>Blackwell Publishing Ltd</publisher><availability><p>Copyright 2009 by the American Geophysical Union.</p></availability><date>2009</date></publicationStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a" type="main" xml:lang="en">Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia</title><author xml:id="author-1"><persName><forename type="first">Elisabeth</forename><surname>Bui</surname></persName><email>elisabeth.bui@csiro.au</email><affiliation>Land and Water, CSIRO, Canberra, ACT, Australia</affiliation></author><author xml:id="author-2"><persName><forename type="first">Brent</forename><surname>Henderson</surname></persName><affiliation>Mathematical and Information Sciences, CSIRO, Canberra, ACT, Australia</affiliation></author><author xml:id="author-3"><persName><forename type="first">Karin</forename><surname>Viergever</surname></persName><affiliation>Ecometrica, Edinburgh, UK</affiliation></author></analytic><monogr><title level="j">Global Biogeochemical Cycles</title><title level="j" type="abbrev">Global Biogeochem. Cycles</title><idno type="pISSN">0886-6236</idno><idno type="eISSN">1944-9224</idno><idno type="DOI">10.1002/(ISSN)1944-9224</idno><imprint><publisher>Blackwell Publishing Ltd</publisher><date type="published" when="2009-12"></date><biblScope unit="volume">23</biblScope><biblScope unit="issue">4</biblScope><biblScope unit="page" from="/">n/a</biblScope><biblScope unit="page" to="/">n/a</biblScope></imprint></monogr><idno type="istex">343D8590C12435A6A6F6723AAB31136235AB078E</idno><idno type="DOI">10.1029/2009GB003506</idno><idno type="ArticleID">2009GB003506</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>2009</date></creation><langUsage><language ident="en">en</language></langUsage><abstract><p>We present a piecewise linear decision tree model for predicting percent of soil organic C (SOC) in the agricultural zones of Australia generated using a machine learning approach. The inputs for the model are a national database of soil data, national digital surfaces of climate, elevation, and terrain variables, Landsat multispectral scanner data, lithology, land use, and soil maps. The model and resulting map are evaluated, and insights into biogeological surficial processes are discussed. The decision tree splits the overall data set into more homogenous subsets, thus in this case, it identifies areas where SOC responds closely to climatic and other environmental variables. The spatial pattern of SOC corresponds well to maps of estimated primary productivity and bioclimatic zones. Topsoil organic C levels are highest in the high rainfall, temperate regions of Tasmania, Victoria, and Western Australia, along the coast of New South Wales and in the wet tropics of Queensland; and lowest in arid and semiarid inland regions. While this pattern broadly follows continental vegetation, soil moisture, and temperature patterns, it is governed by a spatially variable hierarchy of different climatic and other variables across bioregions of Australia. At the continental scale, soil moisture level, rather than temperature, seems most important in controlling SOC.</p></abstract><textClass><keywords scheme="keyword"><list><head>keywords</head><item><term>soil organic C mapping</term></item><item><term>C stock</term></item><item><term>bioregional landscape processes</term></item><item><term>driving factors</term></item><item><term>emergent thresholds</term></item></list></keywords></textClass><textClass><keywords scheme="Journal Subject"><list><head>index-terms</head><item><term>BIOGEOSCIENCES</term></item><item><term>Carbon cycling</term></item><item><term>OCEANOGRAPHY: BIOLOGICAL AND CHEMICAL</term></item><item><term>Carbon cycling</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="2009-03-03">Received</change><change when="2009-09-03">Registration</change><change when="2009-12">Published</change></revisionDesc></teiHeader></istex:fulltextTEI><json:item><extension>txt</extension><original>false</original><mimetype>text/plain</mimetype><uri>https://api.istex.fr/document/343D8590C12435A6A6F6723AAB31136235AB078E/fulltext/txt</uri></json:item></fulltext><metadata><istex:metadataXml wicri:clean="Wiley, elements deleted: body"><istex:xmlDeclaration>version="1.0" encoding="UTF-8" standalone="yes"</istex:xmlDeclaration><istex:document><component type="serialArticle" version="2.0" xml:lang="en" xml:id="gbc1645"><header><publicationMeta level="product"><doi>10.1002/(ISSN)1944-9224</doi><issn type="print">0886-6236</issn><issn type="electronic">1944-9224</issn><idGroup><id type="product" value="GBC"></id><id type="coden" value="GBCYEP"></id></idGroup><titleGroup><title type="main" xml:lang="en" sort="GLOBAL BIOGEOCHEMICAL CYCLES">Global Biogeochemical Cycles</title><title type="short">Global Biogeochem. Cycles</title></titleGroup></publicationMeta><publicationMeta level="part" position="40"><doi>10.1002/gbc.v23.4</doi><numberingGroup><numbering type="journalVolume" number="23">23</numbering><numbering type="journalIssue">4</numbering></numberingGroup><coverDate startDate="2009-12">December 2009</coverDate></publicationMeta><publicationMeta level="unit" position="10" type="article" status="forIssue"><doi>10.1029/2009GB003506</doi><idGroup><id type="editorialOffice" value="2009GB003506"></id><id type="society" value="GB4033"></id><id type="unit" value="GBC1645"></id></idGroup><countGroup><count type="pageTotal" number="15"></count></countGroup><copyright ownership="thirdParty">Copyright 2009 by the American Geophysical Union.</copyright><eventGroup><event type="manuscriptReceived" date="2009-03-03"></event><event type="manuscriptRevised" date="2009-07-27"></event><event type="manuscriptAccepted" date="2009-09-03"></event><event type="firstOnline" date="2009-12-31"></event><event type="publishedOnlineFinalForm" date="2009-12-31"></event><event type="xmlConverted" agent="SPi Global Converter:AGUv3.44_TO_WileyML3Gv1.0.3 version:1.3; WileyML 3G Packaging Tool v1.0" date="2012-12-30"></event><event type="xmlConverted" agent="Converter:WILEY_ML3G_TO_WILEY_ML3GV2 version:3.8.8" date="2014-01-25"></event><event type="xmlConverted" agent="Converter:WML3G_To_WML3G version:4.1.7 mode:FullText,remove_FC" date="2014-10-24"></event></eventGroup><numberingGroup><numbering type="pageFirst">n/a</numbering><numbering type="pageLast">n/a</numbering></numberingGroup><subjectInfo><subject href="http://psi.agu.org/taxonomy5/0400">BIOGEOSCIENCES</subject><subjectInfo><subject href="http://psi.agu.org/taxonomy5/0428">Carbon cycling</subject></subjectInfo><subject role="crossTerm" href="http://psi.agu.org/taxonomy5/4800">OCEANOGRAPHY: BIOLOGICAL AND CHEMICAL</subject><subjectInfo><subject role="crossTerm" href="http://psi.agu.org/taxonomy5/4806">Carbon cycling</subject></subjectInfo></subjectInfo><selfCitationGroup><citation xml:id="gbc1645-cit-0000" type="self"><author><familyName>Bui</familyName>, <givenNames>E.</givenNames></author>, <author><givenNames>B.</givenNames> <familyName>Henderson</familyName></author>, and <author><givenNames>K.</givenNames> <familyName>Viergever</familyName></author> (<pubYear year="2009">2009</pubYear>), <articleTitle>Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia</articleTitle>, <journalTitle>Global Biogeochem. Cycles</journalTitle>, <vol>23</vol>, GB4033, doi:<accessionId ref="info:doi/10.1029/2009GB003506">10.1029/2009GB003506</accessionId>.</citation></selfCitationGroup><linkGroup><link type="toTypesetVersion" href="file:GBC.GBC1645.pdf"></link></linkGroup></publicationMeta><contentMeta><countGroup><count type="figureTotal" number="8"></count><count type="tableTotal" number="3"></count></countGroup><titleGroup><title type="main">Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia</title><title type="short">DATA MINING TO MAP SOIL CARBON</title><title type="shortAuthors">Bui <i>et al</i>.</title></titleGroup><creators><creator creatorRole="author" xml:id="gbc1645-cr-0001" affiliationRef="#gbc1645-aff-0001"><personName><givenNames>Elisabeth</givenNames> <familyName>Bui</familyName></personName><contactDetails><email normalForm="elisabeth.bui@csiro.au">elisabeth.bui@csiro.au</email></contactDetails></creator><creator creatorRole="author" xml:id="gbc1645-cr-0002" affiliationRef="#gbc1645-aff-0002"><personName><givenNames>Brent</givenNames> <familyName>Henderson</familyName></personName></creator><creator creatorRole="author" xml:id="gbc1645-cr-0003" affiliationRef="#gbc1645-aff-0003"><personName><givenNames>Karin</givenNames> <familyName>Viergever</familyName></personName></creator></creators><affiliationGroup><affiliation countryCode="AU" type="organization" xml:id="gbc1645-aff-0001"><orgName>Land and Water, CSIRO</orgName><address><city>Canberra, ACT</city><country>Australia</country></address></affiliation><affiliation countryCode="AU" type="organization" xml:id="gbc1645-aff-0002"><orgName>Mathematical and Information Sciences, CSIRO</orgName><address><city>Canberra, ACT</city><country>Australia</country></address></affiliation><affiliation countryCode="GB" type="organization" xml:id="gbc1645-aff-0003"><orgName>Ecometrica</orgName><address><city>Edinburgh</city><country>UK</country></address></affiliation></affiliationGroup><keywordGroup type="author"><keyword xml:id="gbc1645-kwd-0001">soil organic C mapping</keyword><keyword xml:id="gbc1645-kwd-0002">C stock</keyword><keyword xml:id="gbc1645-kwd-0003">bioregional landscape processes</keyword><keyword xml:id="gbc1645-kwd-0004">driving factors</keyword><keyword xml:id="gbc1645-kwd-0005">emergent thresholds</keyword></keywordGroup><supportingInformation xml:id="gbc1645-sup-0000"><p xml:id="gbc1645-para-0001">Auxiliary material for this article contains the complete list of environmental variables used as predictors in ASRIS modeling and the complete output of the Cubist model for SOC in the topsoil (0–30 cm).</p><p xml:id="gbc1645-para-0002">Auxiliary material files may require downloading to a local drive depending on platform, browser, configuration, and size. To open auxiliary materials in a browser, click on the label. To download, Right‐click and select “Save Target As…” (PC) or CTRL‐click and select “Download Link to Disk” (Mac).</p><p xml:id="gbc1645-para-0003">See <url href="/pubs/plugins.html">Plugins</url> for a list of applications and supported file formats.</p><p xml:id="gbc1645-para-0004">Additional file information is provided in the readme.txt.</p><supportingInfoItem><mediaResource alt="supplementary data" mimeType="text/plain" href="urn-x:wiley:08866236:media:gbc1645:gbc1645-sup-0001-readme"></mediaResource><caption>readme.txt</caption></supportingInfoItem><supportingInfoItem><mediaResource alt="supplementary data" mimeType="text/plain" href="urn-x:wiley:08866236:media:gbc1645:gbc1645-sup-0002-ts01"></mediaResource><caption>Table S1. Table describing lithology classes used as predictors in the Cubist model.</caption></supportingInfoItem><supportingInfoItem><mediaResource alt="supplementary data" mimeType="text/plain" href="urn-x:wiley:08866236:media:gbc1645:gbc1645-sup-0003-ts02"></mediaResource><caption>Table S2. Table describing terrain attributes derived from interim 9 sec DEM.</caption></supportingInfoItem><supportingInfoItem><mediaResource alt="supplementary data" mimeType="text/plain" href="urn-x:wiley:08866236:media:gbc1645:gbc1645-sup-0004-ts03"></mediaResource><caption>Table S3. Table describing climate variables.</caption></supportingInfoItem><supportingInfoItem><mediaResource alt="supplementary data" mimeType="text/plain" href="urn-x:wiley:08866236:media:gbc1645:gbc1645-sup-0005-ts04"></mediaResource><caption>Table S4. Table describing land use classes.</caption></supportingInfoItem><supportingInfoItem><mediaResource alt="supplementary data" mimeType="text/plain" href="urn-x:wiley:08866236:media:gbc1645:gbc1645-sup-0006-txts01"></mediaResource><caption>Text S1. Listing of the output from the Cubist model giving the complete 29 rules of the topsoil SOC model.</caption></supportingInfoItem><supportingInfoItem><mediaResource alt="supplementary data" mimeType="text/plain" href="urn-x:wiley:08866236:media:gbc1645:gbc1645-sup-0007-t01"></mediaResource><caption>Tab‐delimited Table 1.</caption></supportingInfoItem><supportingInfoItem><mediaResource alt="supplementary data" mimeType="text/plain" href="urn-x:wiley:08866236:media:gbc1645:gbc1645-sup-0008-t02"></mediaResource><caption>Tab‐delimited Table 2.</caption></supportingInfoItem><supportingInfoItem><mediaResource alt="supplementary data" mimeType="text/plain" href="urn-x:wiley:08866236:media:gbc1645:gbc1645-sup-0009-t03"></mediaResource><caption>Tab‐delimited Table 3.</caption></supportingInfoItem></supportingInformation><abstractGroup><abstract type="main"><p xml:id="gbc1645-para-0005" label="1">We present a piecewise linear decision tree model for predicting percent of soil organic C (SOC) in the agricultural zones of Australia generated using a machine learning approach. The inputs for the model are a national database of soil data, national digital surfaces of climate, elevation, and terrain variables, Landsat multispectral scanner data, lithology, land use, and soil maps. The model and resulting map are evaluated, and insights into biogeological surficial processes are discussed. The decision tree splits the overall data set into more homogenous subsets, thus in this case, it identifies areas where SOC responds closely to climatic and other environmental variables. The spatial pattern of SOC corresponds well to maps of estimated primary productivity and bioclimatic zones. Topsoil organic C levels are highest in the high rainfall, temperate regions of Tasmania, Victoria, and Western Australia, along the coast of New South Wales and in the wet tropics of Queensland; and lowest in arid and semiarid inland regions. While this pattern broadly follows continental vegetation, soil moisture, and temperature patterns, it is governed by a spatially variable hierarchy of different climatic and other variables across bioregions of Australia. At the continental scale, soil moisture level, rather than temperature, seems most important in controlling SOC.</p></abstract></abstractGroup></contentMeta></header></component></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia</title></titleInfo><titleInfo type="abbreviated" lang="en"><title>DATA MINING TO MAP SOIL CARBON</title></titleInfo><titleInfo type="alternative" contentType="CDATA" lang="en"><title>Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia</title></titleInfo><name type="personal"><namePart type="given">Elisabeth</namePart><namePart type="family">Bui</namePart><affiliation>Land and Water, CSIRO, Canberra, ACT, Australia</affiliation><affiliation>E-mail: elisabeth.bui@csiro.au</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Brent</namePart><namePart type="family">Henderson</namePart><affiliation>Mathematical and Information Sciences, CSIRO, Canberra, ACT, Australia</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Karin</namePart><namePart type="family">Viergever</namePart><affiliation>Ecometrica, Edinburgh, UK</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="article" displayLabel="article"></genre><originInfo><publisher>Blackwell Publishing Ltd</publisher><dateIssued encoding="w3cdtf">2009-12</dateIssued><dateCaptured encoding="w3cdtf">2009-03-03</dateCaptured><dateValid encoding="w3cdtf">2009-09-03</dateValid><edition>Bui, E., B. Henderson, and K. Viergever (2009), Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia, Global Biogeochem. Cycles, 23, GB4033, doi:10.1029/2009GB003506.</edition><copyrightDate encoding="w3cdtf">2009</copyrightDate></originInfo><language><languageTerm type="code" authority="rfc3066">en</languageTerm><languageTerm type="code" authority="iso639-2b">eng</languageTerm></language><physicalDescription><internetMediaType>text/html</internetMediaType><extent unit="figures">8</extent><extent unit="tables">3</extent></physicalDescription><abstract>We present a piecewise linear decision tree model for predicting percent of soil organic C (SOC) in the agricultural zones of Australia generated using a machine learning approach. The inputs for the model are a national database of soil data, national digital surfaces of climate, elevation, and terrain variables, Landsat multispectral scanner data, lithology, land use, and soil maps. The model and resulting map are evaluated, and insights into biogeological surficial processes are discussed. The decision tree splits the overall data set into more homogenous subsets, thus in this case, it identifies areas where SOC responds closely to climatic and other environmental variables. The spatial pattern of SOC corresponds well to maps of estimated primary productivity and bioclimatic zones. Topsoil organic C levels are highest in the high rainfall, temperate regions of Tasmania, Victoria, and Western Australia, along the coast of New South Wales and in the wet tropics of Queensland; and lowest in arid and semiarid inland regions. While this pattern broadly follows continental vegetation, soil moisture, and temperature patterns, it is governed by a spatially variable hierarchy of different climatic and other variables across bioregions of Australia. At the continental scale, soil moisture level, rather than temperature, seems most important in controlling SOC.</abstract><subject><genre>keywords</genre><topic>soil organic C mapping</topic><topic>C stock</topic><topic>bioregional landscape processes</topic><topic>driving factors</topic><topic>emergent thresholds</topic></subject><relatedItem type="host"><titleInfo><title>Global Biogeochemical Cycles</title></titleInfo><titleInfo type="abbreviated"><title>Global Biogeochem. Cycles</title></titleInfo><genre type="journal">journal</genre><note type="content"> Auxiliary material for this article contains the complete list of environmental variables used as predictors in ASRIS modeling and the complete output of the Cubist model for SOC in the topsoil (0–30 cm). Auxiliary material files may require downloading to a local drive depending on platform, browser, configuration, and size. To open auxiliary materials in a browser, click on the label. To download, Right‐click and select “Save Target As…” (PC) or CTRL‐click and select “Download Link to Disk” (Mac). See Plugins for a list of applications and supported file formats. Additional file information is provided in the readme.txt. Auxiliary material for this article contains the complete list of environmental variables used as predictors in ASRIS modeling and the complete output of the Cubist model for SOC in the topsoil (0–30 cm). Auxiliary material files may require downloading to a local drive depending on platform, browser, configuration, and size. To open auxiliary materials in a browser, click on the label. To download, Right‐click and select “Save Target As…” (PC) or CTRL‐click and select “Download Link to Disk” (Mac). See Plugins for a list of applications and supported file formats. Additional file information is provided in the readme.txt. Auxiliary material for this article contains the complete list of environmental variables used as predictors in ASRIS modeling and the complete output of the Cubist model for SOC in the topsoil (0–30 cm). Auxiliary material files may require downloading to a local drive depending on platform, browser, configuration, and size. To open auxiliary materials in a browser, click on the label. To download, Right‐click and select “Save Target As…” (PC) or CTRL‐click and select “Download Link to Disk” (Mac). See Plugins for a list of applications and supported file formats. Additional file information is provided in the readme.txt. Auxiliary material for this article contains the complete list of environmental variables used as predictors in ASRIS modeling and the complete output of the Cubist model for SOC in the topsoil (0–30 cm). Auxiliary material files may require downloading to a local drive depending on platform, browser, configuration, and size. To open auxiliary materials in a browser, click on the label. To download, Right‐click and select “Save Target As…” (PC) or CTRL‐click and select “Download Link to Disk” (Mac). See Plugins for a list of applications and supported file formats. Additional file information is provided in the readme.txt.Supporting Info Item: readme.txt - Table S1. Table describing lithology classes used as predictors in the Cubist model. - Table S2. Table describing terrain attributes derived from interim 9 sec DEM. - Table S3. Table describing climate variables. - Table S4. Table describing land use classes. - Text S1. Listing of the output from the Cubist model giving the complete 29 rules of the topsoil SOC model. - Tab‐delimited Table 1. - Tab‐delimited Table 2. - Tab‐delimited Table 3. - </note><subject><genre>index-terms</genre><topic authorityURI="http://psi.agu.org/taxonomy5/0400">BIOGEOSCIENCES</topic><topic authorityURI="http://psi.agu.org/taxonomy5/0428">Carbon cycling</topic><topic authorityURI="http://psi.agu.org/taxonomy5/4800">OCEANOGRAPHY: BIOLOGICAL AND CHEMICAL</topic><topic authorityURI="http://psi.agu.org/taxonomy5/4806">Carbon cycling</topic></subject><identifier type="ISSN">0886-6236</identifier><identifier type="eISSN">1944-9224</identifier><identifier type="DOI">10.1002/(ISSN)1944-9224</identifier><identifier type="CODEN">GBCYEP</identifier><identifier type="PublisherID">GBC</identifier><part><date>2009</date><detail type="volume"><caption>vol.</caption><number>23</number></detail><detail type="issue"><caption>no.</caption><number>4</number></detail><extent unit="pages"><start>n/a</start><end>n/a</end><total>15</total></extent></part></relatedItem><identifier type="istex">343D8590C12435A6A6F6723AAB31136235AB078E</identifier><identifier type="DOI">10.1029/2009GB003506</identifier><identifier type="ArticleID">2009GB003506</identifier><accessCondition type="use and reproduction" contentType="copyright">Copyright 2009 by the American Geophysical Union.</accessCondition><recordInfo><recordContentSource>WILEY</recordContentSource></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 000D72 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000D72 | 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:343D8590C12435A6A6F6723AAB31136235AB078E
|texte= Using knowledge discovery with data mining from the Australian Soil Resource Information System database to inform soil carbon mapping in Australia
}}
| This area was generated with Dilib version V0.6.28. |  |