简介：Bydrawingonstudiesofdomesticandinternationalforestlandscapeassessmentandvisualevaluationofurbansoundscape,wesummarizedthemainfactorsaffectingtheforestsoundscape.Onthisbasis,weestablishedanevaluationsystemforlevel2class3forestsoundscape.Elevenindicatorsoftheforestsoundlandscapeaestheticevaluationsystemandtheweightoftheproductwerescored,andthentheaccumulatedscoredvaluesweredefinedasthesoundlandscapeaestheticindex.Theacousticlandscapeindexwasusedtomeasurethesizeoftheforestlandscapebeautifuldegree.

简介：现在的调查被执行决定通过最佳索引因素(OIF)选择的特征是否能作为与一起考虑的所有特征相比象二不同的年的叠的图象一样在单个年的卫星图象上提供各种各样的范畴的改进分类精确性。进一步，以便决定是否在那里发生有特征的OIF价值的相应增加的不同范畴的分类精确性的增加从两个提取了单个年并且叠了图象，我们与特征的不同联合的OIF价值执行了在各种各样的范畴的制片人精确性(PA)之间的线性回归。调查证明那在那里发生在二不可渗透的范畴viz的PA的重要改进。中等布满建筑物、低密度布满建筑物从作为与所有乐队相比与最高的OIF值联系的乐队和主要部件和为两个的主要部件的分类坚定单个年和叠的图象分别地。回归分析为决定单个年并且叠了分别地意味着与OIF价值的相应增加的在信息内容的增加之间的直接关系的流行的图象的各种各样的范畴展出了在回归系数和OIF价值之间的积极趋势。研究证明特征提取了通过从单个年和叠的图象的OIF能够作为与一起分享的所有特征相比提供显著地改进的PA。

简介：Basedupon3widelyusedbasemodels,atotalof8ADA/GADAsiteindexmodelswerederived.Thedataforthesemodelsinthisstudywereobtainedfrom79pith-splitstemanalysisplotsandtheestimationmethodwas"indicatorvariableapproach".Weusedbothfitstatisticsandvisualanalysistoselectthebest-fitmodel,andattachedmoreimportancetothevisualanalysis.Acomprehensiveapplicationanalysiswasalsogiventotheselectedmodel.Theresultsshowed:1)GADAoutperformedADAwithrespecttopredictions.2)AGADAmodelderivedfromHossfeldⅣpresentedthebestpredictionability.Itwassuggestedthatthemodelbeusedtopredictdominantheightandtoestimatesiteindexforponderosapinestandsranging30-200yearsinBritishColumbia,Canada.3)Thebestsiteindexagewasageof100years,baseduponrelativeerrorsofpredictions.

简介：Keerqin沙土地位于在向东北平凡、内部的蒙古之间的过渡地面(42°41′-45°15′N，118°35′-123°30′E)在东北Chinaand，它被沙漠化严重影响。根据地球表面的配置和生态环境，植被，赤裸的砂土的职业比率和土壤质地的范围被使用地调查数据作为评估索引选择。Keerqin沙的沙漠化的评估索引系统被使用遥感数据建立，并且赤裸的砂土的职业比率被混合光谱模型获得。这个索引系统被域调查数据验证，结果显示它对Keerqin的thedesertification评估合适。

简介：TwoclonaltrialstandsofChineseFir（Cunninghamialanceolata）wereusedinthisstudy,onewas19-year-oldstandwhichincluded38clones,andtheotherwas17-year-oldstandincluding102clones.Thestatisticalanalysesshowedthattherewereverysignificantgeneticvariationsinheight,DBH,volumeandratioofheartwood(Rhw),woodbasicdensity（ρb）oftheclonesinthetwostands.Therepeatabilityofcloneswasinmediantohighlevel,andthegeneticCVwasdifferentovertheallfivetraits.Therewereverysignificantphenotypicandgeneticcorrelationsamongheight,DBHandvolume,andnegativecorrelationsamonggrowth,Rhwandρb.Theselectionmethodexperimentindicatedthatindexselectioncouldimprovevolume,Rhwandρb,showingsyntheticallysuperiorselectioneffectscomparedtoanyindividualtraitselectionmethods.

简介：Background:LeafAreaIndex(LAI)isanimportantparameterusedinmonitoringandmodelingofforestecosystems.Theaimofthisstudywastoevaluateperformanceoftheartificialneuralnetwork(ANN)modelstopredicttheLAIbycomparingtheregressionanalysismodelsastheclassicalmethodinthesepureandeven-agedCrimeanpineforeststands.Methods:OnehundredeighttemporarysampleplotswerecollectedfromCrimeanpineforeststandstoestimatestandparameters.EachsampleplotwasimagedwithhemisphericalphotographstodetecttheLAI.ThepartialcorrelationanalysiswasusedtoassesstherelationshipsbetweenthestandLAIvaluesandstandparameters,andthemultivariatelinearregressionanalysiswasusedtopredicttheLAIfromstandparameters.DifferentartificialneuralnetworkmodelscomprisingdifferentnumberofneuronandtransferfunctionsweretrainedandusedtopredicttheLAIofforeststands.Results:ThecorrelationcoefficientsbetweenLAIandstandparameters(standnumberoftrees,basalarea,thequadraticmeandiameter,standdensityandstandage)weresignificantatthelevelof0.01.Thestandage,numberoftrees,siteindex,andbasalareawereindependentparametersinthemostsuccessfulregressionmodelpredictedLAIvaluesusingstandparameters(/?;adj=0.5431).AscorrespondingmethodtopredicttheinteractionsbetweenthestandLAIvaluesandstandparameters,theneuralnetworkarchitecturebasedontheRBF4-19-1withGaussianactivationfunctioninhiddenlayerandtheidentityactivationfunctioninoutputlayerperformedbetterinpredictingLAI(SSE(12.1040),MSE(0.1223),RM5E(0.3497),AIC(0.1040),BIC(-777310)andR2(0.6392))comparedtotheotherstudiedtechniques.Conclusion:TheANNoutperformedthemultivariateregressiontechniquesinpredictingLAIfromstandparameters.TheANNmodels,developedinthisstudy,mayaidinmakingforestmanagementplanninginstudyforeststands.