BIOMOD – optimizing predictions of species distributions and projecting potential future shifts under global change
Identifieur interne : 000C17 ( Main/Exploration ); précédent : 000C16; suivant : 000C18BIOMOD – optimizing predictions of species distributions and projecting potential future shifts under global change
Auteurs : Wilfried Thuiller [France]Source :
- Global Change Biology [ 1354-1013 ] ; 2003-10.
English descriptors
- KwdEn :
Abstract
A new computation framework (BIOMOD: BIOdiversity MODelling) is presented, which aims to maximize the predictive accuracy of current species distributions and the reliability of future potential distributions using different types of statistical modelling methods. BIOMOD capitalizes on the different techniques used in static modelling to provide spatial predictions. It computes, for each species and in the same package, the four most widely used modelling techniques in species predictions, namely Generalized Linear Models (GLM), Generalized Additive Models (GAM), Classification and Regression Tree analysis (CART) and Artificial Neural Networks (ANN). BIOMOD was applied to 61 species of trees in Europe using climatic quantities as explanatory variables of current distributions. On average, all the different modelling methods yielded very good agreement between observed and predicted distributions. However, the relative performance of different techniques was idiosyncratic across species, suggesting that the most accurate model varies between species. The results of this evaluation also highlight that slight differences between current predictions from different modelling techniques are exacerbated in future projections. Therefore, it is difficult to assess the reliability of alternative projections without validation techniques or expert opinion. It is concluded that rather than using a single modelling technique to predict the distribution of several species, it would be more reliable to use a framework assessing different models for each species and selecting the most accurate one using both evaluation methods and expert knowledge.
Url:
DOI: 10.1046/j.1365-2486.2003.00666.x
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000722
- to stream Istex, to step Curation: 000722
- to stream Istex, to step Checkpoint: 000830
- to stream Main, to step Merge: 000C32
- to stream Main, to step Curation: 000C17
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">BIOMOD – optimizing predictions of species distributions and projecting potential future shifts under global change</title><author><name sortKey="Thuiller, Wilfried" sort="Thuiller, Wilfried" uniqKey="Thuiller W" first="Wilfried" last="Thuiller">Wilfried Thuiller</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:3D801CDB5D3DA44E6FB3F5B2F7AD28785ECAE5E2</idno><date when="2003" year="2003">2003</date><idno type="doi">10.1046/j.1365-2486.2003.00666.x</idno><idno type="url">https://api.istex.fr/document/3D801CDB5D3DA44E6FB3F5B2F7AD28785ECAE5E2/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000722</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000722</idno><idno type="wicri:Area/Istex/Curation">000722</idno><idno type="wicri:Area/Istex/Checkpoint">000830</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000830</idno><idno type="wicri:doubleKey">1354-1013:2003:Thuiller W:biomod:optimizing:predictions</idno><idno type="wicri:Area/Main/Merge">000C32</idno><idno type="wicri:Area/Main/Curation">000C17</idno><idno type="wicri:Area/Main/Exploration">000C17</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">BIOMOD – optimizing predictions of species distributions and projecting potential future shifts under global change</title><author><name sortKey="Thuiller, Wilfried" sort="Thuiller, Wilfried" uniqKey="Thuiller W" first="Wilfried" last="Thuiller">Wilfried Thuiller</name><affiliation wicri:level="3"><country xml:lang="fr">France</country><wicri:regionArea>Centre d'Ecologie Fonctionnelle et Evolutive, Centre National de Recherche Scientifique, 1919 route de Mende, 34293 Montpellier Cedex 5</wicri:regionArea><placeName><region type="region" nuts="2">Occitanie (région administrative)</region><region type="old region" nuts="2">Languedoc-Roussillon</region><settlement type="city">Montpellier</settlement></placeName></affiliation></author></analytic><monogr></monogr><series><title level="j">Global Change Biology</title><idno type="ISSN">1354-1013</idno><idno type="eISSN">1365-2486</idno><imprint><publisher>Blackwell Science Ltd</publisher><pubPlace>Oxford, UK</pubPlace><date type="published" when="2003-10">2003-10</date><biblScope unit="volume">9</biblScope><biblScope unit="issue">10</biblScope><biblScope unit="page" from="1353">1353</biblScope><biblScope unit="page" to="1362">1362</biblScope></imprint><idno type="ISSN">1354-1013</idno></series><idno type="istex">3D801CDB5D3DA44E6FB3F5B2F7AD28785ECAE5E2</idno><idno type="DOI">10.1046/j.1365-2486.2003.00666.x</idno><idno type="ArticleID">GCB666</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">1354-1013</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>BIOMOD</term><term>artificial neural network</term><term>climate change</term><term>future climatic envelopes</term><term>generalized additive model</term><term>generalized linear model</term><term>regression tree analysis</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">A new computation framework (BIOMOD: BIOdiversity MODelling) is presented, which aims to maximize the predictive accuracy of current species distributions and the reliability of future potential distributions using different types of statistical modelling methods. BIOMOD capitalizes on the different techniques used in static modelling to provide spatial predictions. It computes, for each species and in the same package, the four most widely used modelling techniques in species predictions, namely Generalized Linear Models (GLM), Generalized Additive Models (GAM), Classification and Regression Tree analysis (CART) and Artificial Neural Networks (ANN). BIOMOD was applied to 61 species of trees in Europe using climatic quantities as explanatory variables of current distributions. On average, all the different modelling methods yielded very good agreement between observed and predicted distributions. However, the relative performance of different techniques was idiosyncratic across species, suggesting that the most accurate model varies between species. The results of this evaluation also highlight that slight differences between current predictions from different modelling techniques are exacerbated in future projections. Therefore, it is difficult to assess the reliability of alternative projections without validation techniques or expert opinion. It is concluded that rather than using a single modelling technique to predict the distribution of several species, it would be more reliable to use a framework assessing different models for each species and selecting the most accurate one using both evaluation methods and expert knowledge.</div></front></TEI><affiliations><list><country><li>France</li></country><region><li>Languedoc-Roussillon</li><li>Occitanie (région administrative)</li></region><settlement><li>Montpellier</li></settlement></list><tree><country name="France"><region name="Occitanie (région administrative)"><name sortKey="Thuiller, Wilfried" sort="Thuiller, Wilfried" uniqKey="Thuiller W" first="Wilfried" last="Thuiller">Wilfried Thuiller</name></region></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Bois/explor/CheneBelgiqueV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000C17 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000C17 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Bois
|area= CheneBelgiqueV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:3D801CDB5D3DA44E6FB3F5B2F7AD28785ECAE5E2
|texte= BIOMOD – optimizing predictions of species distributions and projecting potential future shifts under global change
}}
| This area was generated with Dilib version V0.6.27. |  |