Please wait a minute...
img

官方微信

遥感技术与应用  2014, Vol. 29 Issue (3): 394-400    DOI: doi:10.11873/j.issn.1004-0323.2014.3.0394
模型与反演     
基于分类回归树的密云水库上游森林覆盖度遥感估算
张瑾,李晓松,吴炳方
(中国科学院遥感与数字地球研究所,北京100101)
Forest Cover Estimation based on Classification and Regression Trees of Miyun Reservoir Upstream Area
Zhang Jin,Li Xiaosong,Wu Bingfang
(Institute of Remote Sensing and Digital Earth,Chinese Academy of Sciences,Beijing 100101,China)
 全文: PDF(14357 KB)  
摘要:

森林覆盖度是描述森林生态状况的重要指标,也是气候、水文模型的重要输入参数。以多时相的HJ星 CCD数据为主要数据源,利用分类回归树的方法对密云水库上游的森林覆盖度进行了遥感估算,通过基于高分航片提取的样本数据对估算结果进行了验证,并与传统回归模型进行了比较分析。结果表明:以HJ星及其他辅助数据为数据源,采用分类回归树的方法估测森林覆盖度可以达到较高的精度,拟合决定系数R2达到0.749,建模均方根及验证均方根误差分别为0.068和0.118,均明显优于传统回归模型,适用于大区域的森林覆盖度遥感估算。

关键词: 森林覆盖度分类回归树密云水库上游    
Abstract:

Forest cover is an important forest condition indicator and a climate and hydrologic model parameter.In this study,a new statistic model was proposed,Classification and Regression Trees (CART) model is used to estimate tree cover by remote sensing.Chinese Environment and Disaster Monitoring and Forecasting Satellite(HJ) CCD data is used as main data source to estimate tree cover in Miyun reservoir upstream area by regression tree model .The estimation was validated by samples extracted from high spatial resolution aerial image,and the accuracy was compared with traditional regression models.The result shows that CART model used in HJ data has higher accuracy than regression models,with a higher R2(0.749)and lower RMSE in both modeling samples (0.068) and test samples (0.118).The study provided a new strategy for estimating forest cover by remote sensing in large area.


Key words: Forest cover    Classification and Regression Trees    Miyun reservoir upstream area
收稿日期: 2012-11-27 出版日期: 2014-06-23
ZTFLH:  TP 79  
基金资助:

国家自然科学基金项目( 41101399)。

通讯作者: 李晓松(1981-),男,内蒙赤峰人,副研究员,主要从事生态遥感研究。Email:lixs@radi.ac.cn。    
作者简介: 张瑾(1988-),女,山东淄博人,硕士研究生,主要从事植被遥感研究。Email:zhangjin@irsa.ac.cn。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
张瑾
李晓松
吴炳方

引用本文:

张瑾,李晓松,吴炳方. 基于分类回归树的密云水库上游森林覆盖度遥感估算[J]. 遥感技术与应用, 2014, 29(3): 394-400.

Zhang Jin,Li Xiaosong,Wu Bingfang. Forest Cover Estimation based on Classification and Regression Trees of Miyun Reservoir Upstream Area. Remote Sensing Technology and Application, 2014, 29(3): 394-400.

链接本文:

http://www.rsta.ac.cn/CN/doi:10.11873/j.issn.1004-0323.2014.3.0394        http://www.rsta.ac.cn/CN/Y2014/V29/I3/394

[1]Pu R L,Gong P.Wavelet Transform Applied to EO-1 Byperspectral Data for Forest LAI and Crown Closure Mapping[J].Remote Sensing of Environment,2004,91:212-224.

[2]Anatoly A G,Yoram J K,Robert S,et al.Novel Algorithms for Remote Estimation of Vegetation Fraction[J].Remote Sensing of Environment,2002,80(1):76-87.

[3]Chen Yunhao,Li Xiaobing,Shi Peijun,et al.Estimating Vegetation Coverage Change Using Remote Sensing Data in Haidian District,Beijing[J].Acta Phytoecologica Sinica,2001,25(5):588-593.[陈云浩,李晓兵,史培军,等.北京海淀区植被覆盖的遥感动态研究[J].植物生态学报,2001,25(5):588-593.]

[4]Lu H,Michael R R,Tim R M,et al.Decomposition of Vegetation Cover into Woody and Herbaceous Components Using AVHRR NDVI Time Series[J].Remote Sensing of Environment,2003,(86):1-18.

[5]James M P,Jerome J K,Donald G.Overstory-understory Biomass Changes over a 35-year Period in Southcentral Oregon[J].Forest Ecology and Management,2011,150:267-277.

[6]Ian O,Douglas J K,Lautenschlager R A.Overstory and Understory Leaf Area Index as Indicators of Forest Response to Ice Storm Damage[J].Ecological Indicators,2003,3:49-64.

[7]Xing Zhurong,Feng Yougui,Yang Guijun,et al.Method of Estimating Vegetation Coverage based on Remote Sensing[J].Remote Sensing Technology and Application,2009,24(6):849-854.[邢著荣,冯幼贵,杨贵军,等.基于遥感的植被覆盖度估算方法述评[J].遥感技术与应用,2009,24(6):849-854.]

[8]Choudhury B J,Ahmed N U,Idso S B,et al.Relations between Evaporation Coefficients and Vegetation Indices Studied by Model Simulations[J].Remote Sensing of Environment,1994,50:1-17.

[9]Huang Jianxi,Wu Bingfang,Zeng Yuan,et al.Review of Tree,Shrub,Grass Cover of Horizontal and Vertical Scale Retrieval from Remotely Sensed Data[J].Advances in Earth Sciences,2005,20(8):871-881.[黄健熙,吴炳方,曾源,等.水平和垂直尺度乔、灌、草覆盖度遥感提取研究进展[J].地球科学进展,2005,20(8):871-881.]

[10]Huang C Q,Yang L M,Bruce W,et al.A strategy for Estimating Tree Canopy Density using Landsat 7 ETM+ and High Resolution Images over Large Areas[C]//The Third International Conference on Geospatial Information in Agriculture and Forestry held in Denver,Colorado,5-7 November,2001.CD-ROM,1 disk.

[11]Chen Jin,Chen Yunhao,He Chunyang,et al.Sub-pixel Model for Vegetation Fraction Estimation based on Land Cover Classification[J].Journal of Remote Sensing,2001,5(6):416-422.[陈晋,陈云浩,何春阳,等.基于土地覆盖分类的植被覆盖率估算亚像元模型与应用[J].遥感学报,2001,5(6):416-422.]

[12]Wang Minghai,Zhang Haibo,Liu Wei.Study of the Method of Determinedly Spectral Feature Matching based on the Theory of Scale Space[J].Hydrogaphic Surveying and Charting,2010,30(1):14-17[王明海,张海波,刘伟.基于决策树理论的高光谱影像目标提取技术研究[J].海洋测绘,2010,30(1):14-17.

[13]Matthew C H,David P R,Lindquist E,et al.A Method for Integrating MODIS and Landsat Data for Systematic Monitoring of Forest Cover and Change in the Congo Basin[J].Remote sensing of Environment,2008,(112):2495-2513.

[14]Scott J G,Robb K W,Andrew J S,et al.IKONOS Imagery for Resource Management:Tree Cover,Impervious Surfaces,and Riparian Buffer Analyses in The Mid-Atlantic Region[J].Remote Sensing of Environment,2003,(88):195-208.

[15]Tottrup C,Rasmussen M S,Eklundh L,et al.Mapping Fractional Forest Cover across the Highlands of Mainland Southeast Asia Using MODIS Data and Regression Tree Modeling[J].International Journal of Remote Sensing,2007,28(1):23-46.

[16]Wickham J D,Stehman S V,Fry J A,et al.Thematic Accuracy of the NLCD 2001 Land Cover for the Conterminous United States[J].Remote Sensing of Environment,2010,(114):1286-1296.

[17]Hansen M C,DeFries R S,Townshend J R G,et al.Towards an Operational MODIS Continuous Field of Percent Tree Cover Algorithm:Examples Using AVHRR and MODIS Data[J].Remote Sensing of Environment,2002,(83),303-319.

[18]George X,Collin H.Updating the 2001 National Land Cover Database Impervious Surface Products to 2006 Using Landsat Imagery Change Detection Methods[J].Remote Sensing of Environment,2010,(114):1676-1686.

[19]Xie Yihui.The Application of The Classification and Regression Tree based on the Package Rpart in R—Language[J].Statistics&Information Forum,2007,22(5):67-70[谢益辉.基于R软件rpart包的分类与回归树应用[J].统计与信息论坛,2007,22(5):67-70.]

[1] 董立新. 基于直方图与像元分解模型的森林覆盖度遥感估算[J]. 遥感技术与应用, 2019, 34(1): 136-145.