6533b7dcfe1ef96bd1272634
RESEARCH PRODUCT
Démarche statistique pour la sélection des indicateurs par Random Forests pour la surveillance de la qualité des sols
Olivier FaureHassani TaibiJ. -C Thoisy-durPatrice LepelletierJ. BodinNadia Laurent-bennegadiJ. -J BessouleAntionio BispoJ. BodilisRémi ChaussodNathalie ChevironJérôme CortetJ. CriquetJérôme DantanSamuel DequiedtChristophe GangneuxJennifer Harris-hellalMickael HeddeA. HitmiM. Le GuedardMarc LegrasGuenola PeresC. RepinçaisL. RougeN. RuizIsabelle Trinsoutrot-gattinCécile Villenavesubject
Analyse discriminanteRandom Forestscontaminantes orgánicosindicateurs pédologiquesland use.organic pollutantspolluants organiques[ SHS.ENVIR ] Humanities and Social Sciences/Environmental studies[ SHS.GEO ] Humanities and Social Sciences/Geography[SHS]Humanities and Social Sciencesbioindicateurs[ SHS ] Humanities and Social Sciencesoccupation des sols.sélectionméthodes statiquesbioindicadoresRandom Forets[ SHS.STAT ] Humanities and Social Sciences/Methods and statisticsComputingMilieux_MISCELLANEOUS[SHS.STAT]Humanities and Social Sciences/Methods and statisticspédologieuso del sueloDiscriminant Analysis[SHS.GEO]Humanities and Social Sciences/Geographysols[SDE.ES]Environmental Sciences/Environmental and Societymetal contaminationETMselección[SHS.ENVIR]Humanities and Social Sciences/Environmental studiesbioindicatorsanálisis discriminante[SDE.ES] Environmental Sciences/Environmental and Society[ SDE.ES ] Environmental Sciences/Environmental and Societyqualité des solsdescription
The volume of data, and the large number of biological variables to be tested (one hundred), require analytical techniques, such asRandom Forests, which can overcome the problem of multi-colinearity for the selection of indicators, sensitive to various factors.Random Forests methodology is appropriate for the selection of the most discriminant variables. So, we searched for the best wayto select them, by bringing together all biological variables, representing the Microflora and Fauna. This approach focuses on impactindicators from the Bio2 program, indicators of flora and indicators of accumulation (snails) were not included.This work has been implemented on the three factors of discrimination : land use, metallic contamination levels and organic contaminationlevels.We grouped the most discriminating variables from each RF analysis. Linear discriminant analysis was then implemented for each factor,in order to develop a predictive model.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2013-01-01 |