简介:Thispaperisasummarizationonevaluationofvalueofartificialforest.Themaincontentsinclude:(i)thedifferenceinconceptsbetweenecologicalfunction,ecologicalefficiencyandecologicalbenefitsofartificialforest;(ii)themotiveandseveraltachesofeconomicfeedbackorcompensationforecologicalbenefit;(iii)theecologicalefficienciesofartificialforestandthemaincorrelativefactorswhichincludestheecologicalefficienciesofartificialforestandthemaincorrelationfactorsinfectingtheecologicalefficiency;(iv)thebasicmathcorrelationsbetweenecologicalefficienciesofartificialforestandtherelatedfactors;(v)servicerangeoftheecologicalefficienciesofartificialforest;and(vi)thebasicprincipleofmeasurementofecologicalefficienciesofartificialforest.Attheend,thebasicmethodsofmainecologicalefficienciesofartificialforestareexpatiated.
简介:详细土壤调查包含昂贵、费时间的工作并且要求专家知识。因为土壤调查提供信息满足大量需要,新方法是必要的快速并且精确地印射土壤。在这研究,多层的视感控器人工的神经网络(ANN)被开发单位使用印射土壤数字举起模型(DEM)属性。几最佳的ANN基于很多个输入数据被生产并且隐藏单位。途径使用了测试和确认区域计算插入内推并且外推的数据的精确性。结果证明采用的土壤分类的系统和水平在结果的精确性上有直接效果。在底层,更小的错误比土壤分类(圣)系统与世界引用库(世界佛教徙联谊会)分类标准被观察,但是当使用圣时,更多的土壤类能被预言(在圣的情况中的7土壤对5与世界佛教徙联谊会)。训练错误为当测试错误(插值错误)和确认错误(推测错误)分别地象50%和70%一样高时,模型使用了的所有ANN低于11%。是期望,用分类的高水平的土壤预言介绍了精确性的更好全面的水平。获得更好的预言除了DEM属性,与是的地形或岩性学有关的数据形成土壤的因素,应该被用作ANN输入数据。
简介:Inordertostudyseedqualitychangesofmainafforestationspeciesunderhightemperatureandhighrelativehumidity,thedeteriorationmechanismofseedsofRobiniapesudoacaciaandPinustabulaeformisfromaridandsemiaridareasofNorthernChinawaselucidatedinthisstudy.Theseedswereartificiallyagedfor2and6datthetemperatureof45oCandtherelativehumidity(RH)of50%,75%and100%,respectively.Theresultsshowedthatthegerminabilitydecreasedandthecellmembranedeteriorated...
简介:Inordertoraisetheprecisionofstresswaveimagingtechnology(SWIT),undertheconditionsofdifferentareaandoutlineofsimulatedcavitydefectsintimberdiscsofspruce,differentnumberofusedsensors,therelationshipbetweenimaginggraphdefectsandrealdefectsisstudied.Theresultshows:SWITcandisplaygraphofdefects,theprecisionofimaginggraphrelatestorateofrealdefectareaandareaofthetestedwoodcrosssection,thenumberofusedsensorsandoutlineshapeofthedefects.Whentheraterisesfrom1.6%to25.0%,therelativeerrorofgraphdefectareaandrealdefectareadropsfrom22.6%to9.7%.Whenthenumberofusedsensorsisfrom6to24,thegraphofSWITcanshowtheexistenceofrealdefect.ButthenumberofsensorsusedinfluencestheprecisionofSWIT.Outlineshapeofdefectshascertaineffectondetectionofdefects.Undertheconditionofthesamedefectarea,thedefectsoflongandnarrowshapeareeasytobeshownbygraph.Therelationerrorofdefectareaofsuborbicularshapeissmallerthanthatoflongandnarrowshape.
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.