Prediction and comparison of urban growth by land suitability index mapping using GIS and RS in Sout.docx
- 文档编号:30207815
- 上传时间:2023-08-07
- 格式:DOCX
- 页数:38
- 大小:106.58KB
Prediction and comparison of urban growth by land suitability index mapping using GIS and RS in Sout.docx
《Prediction and comparison of urban growth by land suitability index mapping using GIS and RS in Sout.docx》由会员分享,可在线阅读,更多相关《Prediction and comparison of urban growth by land suitability index mapping using GIS and RS in Sout.docx(38页珍藏版)》请在冰豆网上搜索。
PredictionandcomparisonofurbangrowthbylandsuitabilityindexmappingusingGISandRSinSout
PredictionandcomparisonofurbangrowthbylandsuitabilityindexmappingusingGISandRSinSouthKorea
SoyoungParka,
SeongwooJeonb,
ShinyupKimc,
andChuluongChoia,
aDepartmentofGeoinformaticEngineering,PukyungNationalUniversity,599-1Daeyeon3-Dong,Nam-Gu,Busan608-737,SouthKorea
bKoreaAdaptationCenterforClimateChange,KoreaEnvironmentInstitute,290Jinheung-Ro,Eunpyong-Gu,Seoul122-706,SouthKorea
cDepartmentofEnvironmentalDataandInformationOffice,MinistryofEnvironmentRepublicofKorea,88Gwanmoon-Ro,Gwacheon-Si,Gyeonggi-Do427-729,SouthKorea
Received6April2010;
revised17August2010;
accepted19September2010.
Availableonline10November2010.
Abstract
Thisstudycompareslandsuitabilityindex(LSI)mapscreatedusingageographicinformationsystem(GIS)withfrequencyratio(FR),analyticalhierarchyprocess(AHP),logisticregression(LR),andartificialneuralnetwork(ANN)approachestoforecastingurbanland-usechanges.Varioussocial,political,topographic,andgeographicfactorswereusedaspredictorsofland-usechange,includingelevation,slope,aspect,distancefromroadsandurbanareas,roadratio,landuse,environmentalscore,andlegalrestrictions.Then,LSImapswerecreatedusingFR,AHP,LR,andANNapproaches,andsignificanceandcorrelationwereexaminedamongthemodelsusingrelativeoperatingcharacteristic(ROC),overallaccuracy,andkappaanalyses.TheROCanalysesgaveresultsof0.940,0.937,0.922,and0.891fortheLR,FR,AHP,andANNLSImaps,respectively.ThehighestcorrelationwasfoundbetweentheLRandAHPLSImaps(0.816911),andthelowestcorrelationwasbetweentheANNandFRLSImaps(0.759701).TheANNapproachproducedthehighestoverallaccuracyat92.3%,followedby91.74%forFR,89.12%forAHP,and88.93%forLR.Inthekappaanalysis,thehighest
statisticwas45.38%forFR,followedby40.84%forANN,30representingthecityarea,theANNmethodhadarelativelyhighvalueof71.71%,andtheFR,LR,andAHPmethodshadsimilaraccuraciesof57.68,55.05,and54.31%,respectively.TheseresultsindicatethattheFR,AHP,LR,andANNapproachesproducedsimilarLSImapsforKorea.
Graphicalabstract
Full-sizeimage(23K)
Researchhighlights
Acomparativeanalysisonthemethodologicalapproachestoforecastingurbanland-usechanges.
TheusingoftheFR,AHP,LR,andANNmethodsforanalysisoflandsuitabilityindex.
Eachlandsuitabilityindexmapshowingthedifferentspatialdistribution.
Inthecaseofaccuracyanalysis,eachlandsuitabilityindexmapshowingasimilarresults.
Rangesof0.891–0.939forROC,88.33–92.93%foroverallaccuracy,and24.78–45.38%for
.
Keywords:
Landsuitabilityindexmap;Geographicinformationsystem;Frequencyratio;Analyticalhierarchyprocess;Logisticregression;Artificialneuralnetwork
ArticleOutline
1.
Introduction
2.
Studyareaandmaterials
2.1.Studyarea
2.2.Materials
3.
Methods
3.1.Mappingurbangrowthsuitability
3.1.1.Frequencyratio(FR)model
3.1.2.Analyticalhierarchyprocess(AHP)model
3.1.3.Logisticregression(LR)model
3.1.4.Artificialneuralnetwork(ANN)model
3.2.Validationinurbangrowthsuitabilitymaps
3.2.1.Analysisoftherelativeoperatingcharacteristic(ROC)
3.2.2.AnalysisofaccuracyusingtheLULCmap
4.
Results
4.1.Calculationofthelandsuitability
4.1.1.Frequencyratio(FR)
4.1.2.Analyticalhierarchyprocess(AHP)
4.1.3.Logisticregression(LR)
4.1.4.Artificialneuralnetwork(ANN)
4.2.Comparisonofthelandsuitabilityindex(LSI)maps
4.3.Validation
4.3.1.Relativeoperatingcharacteristic(ROC)
4.3.2.Accuracyanalysis
5.
Discussion
6.
Conclusions
Acknowledgements
References
1.Introduction
CitieshavedevelopedrapidlysincetheIndustrialRevolution,expandingworldwideinconjunctionwithsocioeconomicdevelopment.However,therapidgrowthofurbanareashasledtocomplexproblems,includingtrafficcongestion,environmentalpollution,reducedopenspace,thedeteriorationofold,downtowncenters,andunplannedorpoorlyplannedlanddevelopment(Lee,2008).
Toaddresstheseurbanproblemsandtoidentifyapproachesforsustainabledevelopment,manyresearchershavefocusedondevelopingurbangrowth-predictionmodels.Establishedmodelsincludethecellularautomata(CA)-basedUrbanGrowthModel(UGM),LandTransformationModel(LTM),ConversionofLandUseEffects(CLUE)model,andSlope,Landuse,Exclusion,Urbanextent,roadTransportation,andHillshade(SLEUTH)model,whichcanincorporatedatafromremotesensing(RS)andgeographicinformationsystems(GIS)([Clarkeetal.,1997],[Tobler,1970],[VeldkampandFresco,1996],[Pijanowskietal.,2002],[Verburgetal.,2002]and[SilvaandClarke,2002]).
Theseurbangrowthmodelsidentifythebestcoefficientforpredictinggrowthuntilthepresentusingdatafromthepasttothepresentasinputforpredictingurbangrowth(Jeongetal.,2002).Acriticalissueinsuchsimulationistheprovisionofproperparametervaluesorweightssothatrealisticresultsaregenerated(Wu,2000).
Empiricaldatacanbeusedtocalibrateland-useandland-cover(LULC)changemodelstofindsuitableparametervalues(LombardoandRabino,1986).Empiricaldata,suchasslope,elevation,distancefromroads,protectionstatus,anddistancefromurbanareas,canbecombinedwithoneormoremapsofhistoricallandcovertocompletethecalibration.
Additionally,eachmodelrunusesamapofsuitabilitytogenerateamapofsimulatedfuturechange,placingsimulatedchangeincellsthathavethelargestsuitabilityvalues(PontiusandSchneider,2001).Themapofsuitabilityisgeneratedusingstatisticalmethods,whichcanbequalitativeorquantitative.
Qualitativeorheuristicmethodsarebasedonintrinsicpropertiesasthemaininputfactordeterminingurbangrowthoccurrence.Quantitativeordeterministicmethodsinvolvetheestimationofquantitativevaluesofstabilityvariables,knownassafetyfactors,overadefinedarea([Yilmaz,2009]and[Bednariketal.,2010]).
RecentadvancesincomputertechnologyandGIShaveledtowide-ranginguseofquantitativemethods.Forexample,LeeandSambath(2006),Leeetal.(2000),andAngillieri(2010)createdlandslidesusceptibilitymapsusingthefrequencyratio(FR)andanalyzedthepossibilityoflandslideoccurrence;theirresultssuggestedthattheFRmightserveasasuitableindex.HuandLo(2007)andWuandYeh(1997)usedlogisticregression(LR)toanalyzethespatialdistributionandregionalcharacteristicsofurbangrowth.VeldkampandFresco(1996)andVerburgetal.(2002)usedLRtocalculatethesuitabilityofinputvaluesfortheCLUEmodel;inthatmodel,land-usesuitabilitycanchangeduringasimulationthroughfeedbackmechanismsinvolvingland-usepracticesandsuitabilityeffects.Additionally,WuandWebster(1998)usedtheanalytichierarchyprocess(AHP),amulti-criteriadecision-making(MCDM)method,todefineparametervaluesforCAsimulationempirically.Daietal.(2001)producedadevelopment-suitabilitymapofthegeo-environmentaroundLanzhouCity,China,andUyandNakagoshi(2008)usedtheAHPtechniqueinurbanlandsuitabilityanalysis(LSA).
However,suchstatisticalandquantitativemethodscanbeconstrainedbyinsufficientknowledgeoffield,limitedreproducibilityoftheresults,andsubjectivityinthevariableweight.Quantitativemethodstendtowardsoversimplificationwhendataareincomplete.Datarequirementsfordeterministicmodelscanbeprohibitive,anditisoftenimpossibletoacquiretheinputdatanecessarytouseamodeleffectively([TurnerandSchuster,1996]and[GomezandKavzoglu,2005]).
Toaddresstheselimitations,newtechniquessuchasartificialneuralnetworks(ANNs)andfuzzylogichavebeenimplemented.Pijanowskietal.(2002)usedanANNtoimprovetheLTMmodel,andLiandYeh(2001)usedANNtechniquestocalibrateCA.LiuandPhinn(2003)appliedfuzzylogictoCAcalibration,andDragicevicandMarceau(2000)usedfuzzylogicinaGISsimulationofrural-to-urbantransition.
Asreviewedabove,suitabilitymapscanbegeneratedbyvariousmethods.Somestudieshaveusedseveralmethodstogeneratesuitabilitymapsandthencomparedtheresultsusingrelativeoperatingcharacteristic(ROC)curveanalysis;examplesofthemethodscomparedinthiswayincludeFR–LR–ANN(Yilmaz,2009),FR–LR([LeeandPradhan,2007]and[Angillieri,2010]),ANN–LR(LiandYeh,2001),andAHP–LR(Longetal.,2009).However,noreportedworkhascomparedtheFR,AHP,LR,andANNmethods.
Thus,thisstudyaimstopredictfutureurbangrowthbyanalyzingandcomparingtheresultsoflandsuitabilityindex(LSI)analysisinconjunctionwithtopographic,geographic,andsocialfactors.TheLSIrepresentsthepossibilityforurbangrowth,withahigherLSIvalueindicatingahigherpossibilityforurbanization.Forthesepurposes,weusedabasictechnique(FR),statisticaltechniques(LRandAHP),andasoftcomputingtechnique(ANN)tomodeltherelationshipsofeachdrivertogenerateLSI.Then,ROC,contingency,andKappaanalyseswereusedtoidentifythemostaccuratemethod.AhighlyaccurateLSIvaluecanbeusedasapossibilityfactorforurbangrowthmodelingandcancontributetoproducingsimulationsthatmorecloselymatchrealworldsituations.
2.Studyareaandmaterials
2.1.Studyarea
ThestudyistheentirelandareaofRepublicofKorea(hereafter,SouthKorea),includingJejuIsland,excludingsomesmallerislands,suchasUlleungIslandandDokdo.Thisarealiesbetween34°18′42″Nand37°22′43″Nand124°19′
- 配套讲稿:
如PPT文件的首页显示word图标,表示该PPT已包含配套word讲稿。双击word图标可打开word文档。
- 特殊限制:
部分文档作品中含有的国旗、国徽等图片,仅作为作品整体效果示例展示,禁止商用。设计者仅对作品中独创性部分享有著作权。
- 关 键 词:
- Prediction and comparison of urban growth by land suitability index mapping using GIS RS in Sout
链接地址:https://www.bdocx.com/doc/30207815.html