Predicting gully initiation: comparing data mining techniques, analytical hierarchy processes and the topographic threshold
Identifieur interne : 000447 ( Main/Exploration ); précédent : 000446; suivant : 000448Predicting gully initiation: comparing data mining techniques, analytical hierarchy processes and the topographic threshold
Auteurs : Tal Svoray [Israël] ; Evgenia Michailov [Israël] ; Avraham Cohen [Israël] ; Lior Rokah [Israël] ; Arnon Sturm [Israël]Source :
- Earth Surface Processes and Landforms [ 0197-9337 ] ; 2012-05.
Abstract
Predicting gully initiation at catchment scale was done previously by integrating a geographical information system (GIS) with physically based models, statistical procedures or with knowledge‐based expert systems. However, the reliability and validity of applying these procedures are still questionable. In this work, a data mining (DM) procedure based on decision trees was applied to identify areas of gully initiation risk. Performance was compared with the analytic hierarchy process (AHP) expert system and with the commonly used topographic threshold (TT) technique. A spatial database was used to test the models, composed of a target variable (presence or absence of initial points) and ten independent environmental, climatic and human‐induced variables. The following findings emerged: using the same input layers, DM provided better predictive ability of gully initiation points than the application of both AHP and TT. The main difference between DM and TT was the very high overestimation inherent in TT. In addition, the minimum slope observed for soil detachment was 2°, whereas in other studies it is 3°. This could be explained by soil resistance, which is substantially lower in agricultural fields, while most studies test unploughed soil. Finally, rainfall intensity events >62.2 mm h‐1 (for a period of 30 min) were found to have a significant effect on gully initiation. Copyright © 2012 John Wiley & Sons, Ltd.
Url:
DOI: 10.1002/esp.2273
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000B62
- to stream Istex, to step Curation: 000B09
- to stream Istex, to step Checkpoint: 000089
- to stream Main, to step Merge: 000447
- to stream Main, to step Curation: 000447
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Predicting gully initiation: comparing data mining techniques, analytical hierarchy processes and the topographic threshold</title><author><name sortKey="Svoray, Tal" sort="Svoray, Tal" uniqKey="Svoray T" first="Tal" last="Svoray">Tal Svoray</name></author><author><name sortKey="Michailov, Evgenia" sort="Michailov, Evgenia" uniqKey="Michailov E" first="Evgenia" last="Michailov">Evgenia Michailov</name></author><author><name sortKey="Cohen, Avraham" sort="Cohen, Avraham" uniqKey="Cohen A" first="Avraham" last="Cohen">Avraham Cohen</name></author><author><name sortKey="Rokah, Lior" sort="Rokah, Lior" uniqKey="Rokah L" first="Lior" last="Rokah">Lior Rokah</name></author><author><name sortKey="Sturm, Arnon" sort="Sturm, Arnon" uniqKey="Sturm A" first="Arnon" last="Sturm">Arnon Sturm</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:F8E60D5074B007B1D19B679776AA24854197765E</idno><date when="2012" year="2012">2012</date><idno type="doi">10.1002/esp.2273</idno><idno type="url">https://api.istex.fr/document/F8E60D5074B007B1D19B679776AA24854197765E/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000B62</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000B62</idno><idno type="wicri:Area/Istex/Curation">000B09</idno><idno type="wicri:Area/Istex/Checkpoint">000089</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000089</idno><idno type="wicri:doubleKey">0197-9337:2012:Svoray T:predicting:gully:initiation</idno><idno type="wicri:Area/Main/Merge">000447</idno><idno type="wicri:Area/Main/Curation">000447</idno><idno type="wicri:Area/Main/Exploration">000447</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Predicting gully initiation: comparing data mining techniques, analytical hierarchy processes and the topographic threshold</title><author><name sortKey="Svoray, Tal" sort="Svoray, Tal" uniqKey="Svoray T" first="Tal" last="Svoray">Tal Svoray</name><affiliation wicri:level="1"><country xml:lang="fr">Israël</country><wicri:regionArea>Department of Geography and Environmental Development, Ben‐Gurion University of the Negev, 84105, Beer‐Sheva</wicri:regionArea><wicri:noRegion>Beer‐Sheva</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Israël</country></affiliation></author><author><name sortKey="Michailov, Evgenia" sort="Michailov, Evgenia" uniqKey="Michailov E" first="Evgenia" last="Michailov">Evgenia Michailov</name><affiliation wicri:level="1"><country xml:lang="fr">Israël</country><wicri:regionArea>Department of Information Systems Engineering, Ben‐Gurion University of the Negev, 84105, Beer‐Sheva</wicri:regionArea><wicri:noRegion>Beer‐Sheva</wicri:noRegion></affiliation></author><author><name sortKey="Cohen, Avraham" sort="Cohen, Avraham" uniqKey="Cohen A" first="Avraham" last="Cohen">Avraham Cohen</name><affiliation wicri:level="1"><country xml:lang="fr">Israël</country><wicri:regionArea>Department of Information Systems Engineering, Ben‐Gurion University of the Negev, 84105, Beer‐Sheva</wicri:regionArea><wicri:noRegion>Beer‐Sheva</wicri:noRegion></affiliation></author><author><name sortKey="Rokah, Lior" sort="Rokah, Lior" uniqKey="Rokah L" first="Lior" last="Rokah">Lior Rokah</name><affiliation wicri:level="1"><country xml:lang="fr">Israël</country><wicri:regionArea>Department of Information Systems Engineering, Ben‐Gurion University of the Negev, 84105, Beer‐Sheva</wicri:regionArea><wicri:noRegion>Beer‐Sheva</wicri:noRegion></affiliation></author><author><name sortKey="Sturm, Arnon" sort="Sturm, Arnon" uniqKey="Sturm A" first="Arnon" last="Sturm">Arnon Sturm</name><affiliation wicri:level="1"><country xml:lang="fr">Israël</country><wicri:regionArea>Department of Information Systems Engineering, Ben‐Gurion University of the Negev, 84105, Beer‐Sheva</wicri:regionArea><wicri:noRegion>Beer‐Sheva</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="j">Earth Surface Processes and Landforms</title><title level="j" type="abbrev">Earth Surf. Process. Landforms</title><idno type="ISSN">0197-9337</idno><idno type="eISSN">1096-9837</idno><imprint><publisher>John Wiley & Sons, Ltd</publisher><pubPlace>Chichester, UK</pubPlace><date type="published" when="2012-05">2012-05</date><biblScope unit="volume">37</biblScope><biblScope unit="issue">6</biblScope><biblScope unit="page" from="607">607</biblScope><biblScope unit="page" to="619">619</biblScope></imprint><idno type="ISSN">0197-9337</idno></series><idno type="istex">F8E60D5074B007B1D19B679776AA24854197765E</idno><idno type="DOI">10.1002/esp.2273</idno><idno type="ArticleID">ESP2273</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0197-9337</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract">Predicting gully initiation at catchment scale was done previously by integrating a geographical information system (GIS) with physically based models, statistical procedures or with knowledge‐based expert systems. However, the reliability and validity of applying these procedures are still questionable. In this work, a data mining (DM) procedure based on decision trees was applied to identify areas of gully initiation risk. Performance was compared with the analytic hierarchy process (AHP) expert system and with the commonly used topographic threshold (TT) technique. A spatial database was used to test the models, composed of a target variable (presence or absence of initial points) and ten independent environmental, climatic and human‐induced variables. The following findings emerged: using the same input layers, DM provided better predictive ability of gully initiation points than the application of both AHP and TT. The main difference between DM and TT was the very high overestimation inherent in TT. In addition, the minimum slope observed for soil detachment was 2°, whereas in other studies it is 3°. This could be explained by soil resistance, which is substantially lower in agricultural fields, while most studies test unploughed soil. Finally, rainfall intensity events >62.2 mm h‐1 (for a period of 30 min) were found to have a significant effect on gully initiation. Copyright © 2012 John Wiley & Sons, Ltd.</div></front></TEI><affiliations><list><country><li>Israël</li></country></list><tree><country name="Israël"><noRegion><name sortKey="Svoray, Tal" sort="Svoray, Tal" uniqKey="Svoray T" first="Tal" last="Svoray">Tal Svoray</name></noRegion><name sortKey="Cohen, Avraham" sort="Cohen, Avraham" uniqKey="Cohen A" first="Avraham" last="Cohen">Avraham Cohen</name><name sortKey="Michailov, Evgenia" sort="Michailov, Evgenia" uniqKey="Michailov E" first="Evgenia" last="Michailov">Evgenia Michailov</name><name sortKey="Rokah, Lior" sort="Rokah, Lior" uniqKey="Rokah L" first="Lior" last="Rokah">Lior Rokah</name><name sortKey="Sturm, Arnon" sort="Sturm, Arnon" uniqKey="Sturm A" first="Arnon" last="Sturm">Arnon Sturm</name><name sortKey="Svoray, Tal" sort="Svoray, Tal" uniqKey="Svoray T" first="Tal" last="Svoray">Tal Svoray</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Agronomie/explor/SisAgriV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000447 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000447 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Agronomie
|area= SisAgriV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:F8E60D5074B007B1D19B679776AA24854197765E
|texte= Predicting gully initiation: comparing data mining techniques, analytical hierarchy processes and the topographic threshold
}}
| This area was generated with Dilib version V0.6.28. |  |