Estimating regional effects of climate change and altered land use on biosphere carbon fluxes using distributed time delay neural networks with Bayesian regularized learning.
Identifieur interne : 000F21 ( Main/Exploration ); précédent : 000F20; suivant : 000F22Estimating regional effects of climate change and altered land use on biosphere carbon fluxes using distributed time delay neural networks with Bayesian regularized learning.
Auteurs : Andres Schmidt [Allemagne] ; Whitney Creason [États-Unis] ; Beverly E. Law [États-Unis]Source :
- Neural networks : the official journal of the International Neural Network Society [ 1879-2782 ] ; 2018.
Descripteurs français
- KwdFr :
- Apprentissage machine (tendances), Atmosphère (analyse), Carbone (analyse), Changement climatique (statistiques et données numériques), Cycle du carbone (MeSH), Modèles théoriques (MeSH), Orégon (MeSH), Surveillance des paramètres écologiques (statistiques et données numériques), Théorème de Bayes (MeSH).
- MESH :
- analyse : Atmosphère, Carbone.
- statistiques et données numériques : Changement climatique, Surveillance des paramètres écologiques.
- tendances : Apprentissage machine.
- Cycle du carbone, Modèles théoriques, Orégon, Théorème de Bayes.
English descriptors
- KwdEn :
- MESH :
- chemical , analysis : Carbon.
- geographic : Oregon.
- analysis : Atmosphere.
- statistics & numerical data : Climate Change, Ecological Parameter Monitoring.
- trends : Machine Learning.
- Bayes Theorem, Carbon Cycle, Models, Theoretical, Neural Networks, Computer.
Abstract
The ability to accurately predict changes of the carbon and energy balance on a regional scale is of great importance for assessing the effect of land use changes on carbon sequestration under future climate conditions. Here, a suite of land cover-specific Distributed Time Delay Neural Networks with a parameter adoption algorithm optimized through Bayesian regularization was used to model the statewide atmospheric exchange of CO2, water vapor, and energy in Oregon with its strong spatial gradients of climate and land cover. The network models were trained with eddy covariance data from 9 atmospheric flux towers. Compared to results derived with more common regression networks utilizing non-delayed input vectors, the performance of the DTDNN models was significantly improved with an average increase of the coefficients of determination of 64%. The optimized models were applied in combination with downscaled climate projections of the CMIP5 project to calculate future changes in the cycle of carbon, associated with a prescribed conversion of conventional grass-crops to hybrid poplar plantations for biofuel production in Oregon. The results show that under future RCP8.5 climate conditions the total statewide NEP increases by 0.87 TgC per decade until 2050 without any land use changes. With all non-forage grass completely converted to hybrid poplar the NEP averages 32.9 TgC in 2046-2050, an increase of 9%. Through comparisons with the results of a Bayesians inversion study, the results presented demonstrate that DTDNN models are a specifically well-suited approach to use the available data from flux networks to assess changes in biosphere-atmosphere exchange triggered by massive land use conversion superimposed on a changing climate.
DOI: 10.1016/j.neunet.2018.08.004
PubMed: 30173057
Affiliations:
Links toward previous steps (curation, corpus...)
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Estimating regional effects of climate change and altered land use on biosphere carbon fluxes using distributed time delay neural networks with Bayesian regularized learning.</title><author><name sortKey="Schmidt, Andres" sort="Schmidt, Andres" uniqKey="Schmidt A" first="Andres" last="Schmidt">Andres Schmidt</name><affiliation wicri:level="3"><nlm:affiliation>RWTH Aachen University, Department of Geography, 52062 Aachen, Germany. Electronic address: andres.schmidt@geo.rwth-aachen.de.</nlm:affiliation><country xml:lang="fr">Allemagne</country><wicri:regionArea>RWTH Aachen University, Department of Geography, 52062 Aachen</wicri:regionArea><placeName><region type="land" nuts="1">Rhénanie-du-Nord-Westphalie</region><region type="district" nuts="2">District de Cologne</region><settlement type="city">Aix-la-Chapelle</settlement></placeName></affiliation></author><author><name sortKey="Creason, Whitney" sort="Creason, Whitney" uniqKey="Creason W" first="Whitney" last="Creason">Whitney Creason</name><affiliation wicri:level="2"><nlm:affiliation>Oregon State University, Department of Forest Ecosystems and Society, Corvallis, OR 97331, USA.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Oregon State University, Department of Forest Ecosystems and Society, Corvallis, OR 97331</wicri:regionArea><placeName><region type="state">Oregon</region></placeName></affiliation></author><author><name sortKey="Law, Beverly E" sort="Law, Beverly E" uniqKey="Law B" first="Beverly E" last="Law">Beverly E. Law</name><affiliation wicri:level="2"><nlm:affiliation>Oregon State University, Department of Forest Ecosystems and Society, Corvallis, OR 97331, USA.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Oregon State University, Department of Forest Ecosystems and Society, Corvallis, OR 97331</wicri:regionArea><placeName><region type="state">Oregon</region></placeName></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2018">2018</date><idno type="RBID">pubmed:30173057</idno><idno type="pmid">30173057</idno><idno type="doi">10.1016/j.neunet.2018.08.004</idno><idno type="wicri:Area/Main/Corpus">000C82</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Corpus" wicri:corpus="PubMed">000C82</idno><idno type="wicri:Area/Main/Curation">000C82</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Curation">000C82</idno><idno type="wicri:Area/Main/Exploration">000C82</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Estimating regional effects of climate change and altered land use on biosphere carbon fluxes using distributed time delay neural networks with Bayesian regularized learning.</title><author><name sortKey="Schmidt, Andres" sort="Schmidt, Andres" uniqKey="Schmidt A" first="Andres" last="Schmidt">Andres Schmidt</name><affiliation wicri:level="3"><nlm:affiliation>RWTH Aachen University, Department of Geography, 52062 Aachen, Germany. Electronic address: andres.schmidt@geo.rwth-aachen.de.</nlm:affiliation><country xml:lang="fr">Allemagne</country><wicri:regionArea>RWTH Aachen University, Department of Geography, 52062 Aachen</wicri:regionArea><placeName><region type="land" nuts="1">Rhénanie-du-Nord-Westphalie</region><region type="district" nuts="2">District de Cologne</region><settlement type="city">Aix-la-Chapelle</settlement></placeName></affiliation></author><author><name sortKey="Creason, Whitney" sort="Creason, Whitney" uniqKey="Creason W" first="Whitney" last="Creason">Whitney Creason</name><affiliation wicri:level="2"><nlm:affiliation>Oregon State University, Department of Forest Ecosystems and Society, Corvallis, OR 97331, USA.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Oregon State University, Department of Forest Ecosystems and Society, Corvallis, OR 97331</wicri:regionArea><placeName><region type="state">Oregon</region></placeName></affiliation></author><author><name sortKey="Law, Beverly E" sort="Law, Beverly E" uniqKey="Law B" first="Beverly E" last="Law">Beverly E. Law</name><affiliation wicri:level="2"><nlm:affiliation>Oregon State University, Department of Forest Ecosystems and Society, Corvallis, OR 97331, USA.</nlm:affiliation><country xml:lang="fr">États-Unis</country><wicri:regionArea>Oregon State University, Department of Forest Ecosystems and Society, Corvallis, OR 97331</wicri:regionArea><placeName><region type="state">Oregon</region></placeName></affiliation></author></analytic><series><title level="j">Neural networks : the official journal of the International Neural Network Society</title><idno type="eISSN">1879-2782</idno><imprint><date when="2018" type="published">2018</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Atmosphere (analysis)</term><term>Bayes Theorem (MeSH)</term><term>Carbon (analysis)</term><term>Carbon Cycle (MeSH)</term><term>Climate Change (statistics & numerical data)</term><term>Ecological Parameter Monitoring (statistics & numerical data)</term><term>Machine Learning (trends)</term><term>Models, Theoretical (MeSH)</term><term>Neural Networks, Computer (MeSH)</term><term>Oregon (MeSH)</term></keywords><keywords scheme="KwdFr" xml:lang="fr"><term>Apprentissage machine (tendances)</term><term>Atmosphère (analyse)</term><term>Carbone (analyse)</term><term>Changement climatique (statistiques et données numériques)</term><term>Cycle du carbone (MeSH)</term><term>Modèles théoriques (MeSH)</term><term>Orégon (MeSH)</term><term>Surveillance des paramètres écologiques (statistiques et données numériques)</term><term>Théorème de Bayes (MeSH)</term></keywords><keywords scheme="MESH" type="chemical" qualifier="analysis" xml:lang="en"><term>Carbon</term></keywords><keywords scheme="MESH" type="geographic" xml:lang="en"><term>Oregon</term></keywords><keywords scheme="MESH" qualifier="analyse" xml:lang="fr"><term>Atmosphère</term><term>Carbone</term></keywords><keywords scheme="MESH" qualifier="analysis" xml:lang="en"><term>Atmosphere</term></keywords><keywords scheme="MESH" qualifier="statistics & numerical data" xml:lang="en"><term>Climate Change</term><term>Ecological Parameter Monitoring</term></keywords><keywords scheme="MESH" qualifier="statistiques et données numériques" xml:lang="fr"><term>Changement climatique</term><term>Surveillance des paramètres écologiques</term></keywords><keywords scheme="MESH" qualifier="tendances" xml:lang="fr"><term>Apprentissage machine</term></keywords><keywords scheme="MESH" qualifier="trends" xml:lang="en"><term>Machine Learning</term></keywords><keywords scheme="MESH" xml:lang="en"><term>Bayes Theorem</term><term>Carbon Cycle</term><term>Models, Theoretical</term><term>Neural Networks, Computer</term></keywords><keywords scheme="MESH" xml:lang="fr"><term>Cycle du carbone</term><term>Modèles théoriques</term><term>Orégon</term><term>Théorème de Bayes</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">The ability to accurately predict changes of the carbon and energy balance on a regional scale is of great importance for assessing the effect of land use changes on carbon sequestration under future climate conditions. Here, a suite of land cover-specific Distributed Time Delay Neural Networks with a parameter adoption algorithm optimized through Bayesian regularization was used to model the statewide atmospheric exchange of CO<sub>2</sub>, water vapor, and energy in Oregon with its strong spatial gradients of climate and land cover. The network models were trained with eddy covariance data from 9 atmospheric flux towers. Compared to results derived with more common regression networks utilizing non-delayed input vectors, the performance of the DTDNN models was significantly improved with an average increase of the coefficients of determination of 64%. The optimized models were applied in combination with downscaled climate projections of the CMIP5 project to calculate future changes in the cycle of carbon, associated with a prescribed conversion of conventional grass-crops to hybrid poplar plantations for biofuel production in Oregon. The results show that under future RCP8.5 climate conditions the total statewide NEP increases by 0.87 TgC per decade until 2050 without any land use changes. With all non-forage grass completely converted to hybrid poplar the NEP averages 32.9 TgC in 2046-2050, an increase of 9%. Through comparisons with the results of a Bayesians inversion study, the results presented demonstrate that DTDNN models are a specifically well-suited approach to use the available data from flux networks to assess changes in biosphere-atmosphere exchange triggered by massive land use conversion superimposed on a changing climate.</div></front></TEI><pubmed><MedlineCitation Status="MEDLINE" IndexingMethod="Curated" Owner="NLM"><PMID Version="1">30173057</PMID><DateCompleted><Year>2019</Year><Month>01</Month><Day>09</Day></DateCompleted><DateRevised><Year>2019</Year><Month>12</Month><Day>10</Day></DateRevised><Article PubModel="Print-Electronic"><Journal><ISSN IssnType="Electronic">1879-2782</ISSN><JournalIssue CitedMedium="Internet"><Volume>108</Volume><PubDate><Year>2018</Year><Month>Dec</Month></PubDate></JournalIssue><Title>Neural networks : the official journal of the International Neural Network Society</Title><ISOAbbreviation>Neural Netw</ISOAbbreviation></Journal><ArticleTitle>Estimating regional effects of climate change and altered land use on biosphere carbon fluxes using distributed time delay neural networks with Bayesian regularized learning.</ArticleTitle><Pagination><MedlinePgn>97-113</MedlinePgn></Pagination><ELocationID EIdType="pii" ValidYN="Y">S0893-6080(18)30224-7</ELocationID><ELocationID EIdType="doi" ValidYN="Y">10.1016/j.neunet.2018.08.004</ELocationID><Abstract><AbstractText>The ability to accurately predict changes of the carbon and energy balance on a regional scale is of great importance for assessing the effect of land use changes on carbon sequestration under future climate conditions. Here, a suite of land cover-specific Distributed Time Delay Neural Networks with a parameter adoption algorithm optimized through Bayesian regularization was used to model the statewide atmospheric exchange of CO<sub>2</sub>, water vapor, and energy in Oregon with its strong spatial gradients of climate and land cover. The network models were trained with eddy covariance data from 9 atmospheric flux towers. Compared to results derived with more common regression networks utilizing non-delayed input vectors, the performance of the DTDNN models was significantly improved with an average increase of the coefficients of determination of 64%. The optimized models were applied in combination with downscaled climate projections of the CMIP5 project to calculate future changes in the cycle of carbon, associated with a prescribed conversion of conventional grass-crops to hybrid poplar plantations for biofuel production in Oregon. The results show that under future RCP8.5 climate conditions the total statewide NEP increases by 0.87 TgC per decade until 2050 without any land use changes. With all non-forage grass completely converted to hybrid poplar the NEP averages 32.9 TgC in 2046-2050, an increase of 9%. Through comparisons with the results of a Bayesians inversion study, the results presented demonstrate that DTDNN models are a specifically well-suited approach to use the available data from flux networks to assess changes in biosphere-atmosphere exchange triggered by massive land use conversion superimposed on a changing climate.</AbstractText><CopyrightInformation>Copyright © 2018 Elsevier Ltd. All rights reserved.</CopyrightInformation></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Schmidt</LastName><ForeName>Andres</ForeName><Initials>A</Initials><AffiliationInfo><Affiliation>RWTH Aachen University, Department of Geography, 52062 Aachen, Germany. Electronic address: andres.schmidt@geo.rwth-aachen.de.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Creason</LastName><ForeName>Whitney</ForeName><Initials>W</Initials><AffiliationInfo><Affiliation>Oregon State University, Department of Forest Ecosystems and Society, Corvallis, OR 97331, USA.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Law</LastName><ForeName>Beverly E</ForeName><Initials>BE</Initials><AffiliationInfo><Affiliation>Oregon State University, Department of Forest Ecosystems and Society, Corvallis, OR 97331, USA.</Affiliation></AffiliationInfo></Author></AuthorList><Language>eng</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2018</Year><Month>08</Month><Day>16</Day></ArticleDate></Article><MedlineJournalInfo><Country>United States</Country><MedlineTA>Neural Netw</MedlineTA><NlmUniqueID>8805018</NlmUniqueID><ISSNLinking>0893-6080</ISSNLinking></MedlineJournalInfo><ChemicalList><Chemical><RegistryNumber>7440-44-0</RegistryNumber><NameOfSubstance UI="D002244">Carbon</NameOfSubstance></Chemical></ChemicalList><CitationSubset>IM</CitationSubset><MeshHeadingList><MeshHeading><DescriptorName UI="D001272" MajorTopicYN="N">Atmosphere</DescriptorName><QualifierName UI="Q000032" MajorTopicYN="N">analysis</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D001499" MajorTopicYN="N">Bayes Theorem</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D002244" MajorTopicYN="N">Carbon</DescriptorName><QualifierName UI="Q000032" MajorTopicYN="N">analysis</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D057486" MajorTopicYN="Y">Carbon Cycle</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D057231" MajorTopicYN="N">Climate Change</DescriptorName><QualifierName UI="Q000706" MajorTopicYN="Y">statistics & numerical data</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D064308" MajorTopicYN="N">Ecological Parameter Monitoring</DescriptorName><QualifierName UI="Q000706" MajorTopicYN="N">statistics & numerical data</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D000069550" MajorTopicYN="Y">Machine Learning</DescriptorName><QualifierName UI="Q000639" MajorTopicYN="N">trends</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D008962" MajorTopicYN="N">Models, Theoretical</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D016571" MajorTopicYN="Y">Neural Networks, Computer</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D009922" MajorTopicYN="N" Type="Geographic">Oregon</DescriptorName></MeshHeading></MeshHeadingList><KeywordList Owner="NOTNLM"><Keyword MajorTopicYN="N">Atmospheric carbon exchange modeling</Keyword><Keyword MajorTopicYN="N">Bayesian learning</Keyword><Keyword MajorTopicYN="N">Climate change</Keyword><Keyword MajorTopicYN="N">Distributed time delay neural networks</Keyword></KeywordList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="received"><Year>2018</Year><Month>04</Month><Day>06</Day></PubMedPubDate><PubMedPubDate PubStatus="revised"><Year>2018</Year><Month>06</Month><Day>18</Day></PubMedPubDate><PubMedPubDate PubStatus="accepted"><Year>2018</Year><Month>08</Month><Day>02</Day></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2018</Year><Month>9</Month><Day>3</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2019</Year><Month>1</Month><Day>10</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>2018</Year><Month>9</Month><Day>3</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>ppublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">30173057</ArticleId><ArticleId IdType="pii">S0893-6080(18)30224-7</ArticleId><ArticleId IdType="doi">10.1016/j.neunet.2018.08.004</ArticleId></ArticleIdList></PubmedData></pubmed><affiliations><list><country><li>Allemagne</li><li>États-Unis</li></country><region><li>District de Cologne</li><li>Oregon</li><li>Rhénanie-du-Nord-Westphalie</li></region><settlement><li>Aix-la-Chapelle</li></settlement></list><tree><country name="Allemagne"><region name="Rhénanie-du-Nord-Westphalie"><name sortKey="Schmidt, Andres" sort="Schmidt, Andres" uniqKey="Schmidt A" first="Andres" last="Schmidt">Andres Schmidt</name></region></country><country name="États-Unis"><region name="Oregon"><name sortKey="Creason, Whitney" sort="Creason, Whitney" uniqKey="Creason W" first="Whitney" last="Creason">Whitney Creason</name></region><name sortKey="Law, Beverly E" sort="Law, Beverly E" uniqKey="Law B" first="Beverly E" last="Law">Beverly E. Law</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Bois/explor/PoplarV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000F21 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000F21 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Bois
|area= PoplarV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= pubmed:30173057
|texte= Estimating regional effects of climate change and altered land use on biosphere carbon fluxes using distributed time delay neural networks with Bayesian regularized learning.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:30173057" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \
| NlmPubMed2Wicri -a PoplarV1
| This area was generated with Dilib version V0.6.37. |  |