Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Liaoning Technical University(Natural Science)》 2008-02
Add to Favorite Get Latest Update

Stand volume estimation based on RS,GIS and k-nearest neighbor methods

XU Dong 1,2,DAI Limin 1,SHAO Guofan 1,3,TANG Lei 4,GU Huiyan5(1.Institute of Applied Ecology,Chinese Academy of Sciences,Shenyang 110016,China;2.Graduate School of Chinese Academy of Sciences,Beijing 100039,China;3.Department of Forestry and Natural Resources,Purdue University,West Lafayette IN 47907,USA;4.Department of Management,Shenyang Institute of Aeronautical Engineering,Shenyang 110034,China;5.School of Forestry,Northeast Forestry University,Haerbin 150040,China)  
Volume is a fundamental variable for forest planning and management.Considerable efforts have been made to develop techniques for stand volume estimation.A new method based on RS,GIS and the k-nearest neighbors(kNN) method is put forward for improving volume estimation.The procedures of this method are illustrated and tested in Baihe Forestry Bureau.Using the nearest neighbor(k=13),Euclidean distance,a Landsat ETM+ image,DEM,and feature weighting parameters,volumes are estimated.The root mean square error(RMSE) is 20.93m3/ha,and Biasτ is 6.58%,which shows that the overall accuracy is over 90%.Recommendations for applying the method for volume estimation are provided at last.
【Fund】: 国家自然科学基金资助项目(NSFC70373044与NSFC30470302)
【CateGory Index】: S758
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved