文献类型：期刊文献

英文题名：Improvement of mapping vegetation cover for arid and semiarid areas using a local nonlinear modelling method and landsat images

作者：Sun, H.[1,2,3] Wang, Q.[4] Wang, G. X.[4] Luo, P.[5] Jiang, F. G.[1,2,3]

第一作者：Sun, H.

通信作者：Wang, GX[1]

机构：[1]Cent South Univ Forestry & Technol, Res Ctr Forestry Remote Sensing & Informat Engn, Changsha 410004, Hunan, Peoples R China;[2]Key Lab Forestry Remote Sensing Based Big Data &, Changsha 410004, Hunan, Peoples R China;[3]Key Lab Natl Forestry & Grassland Adm Forest Reso, Changsha 410004, Peoples R China;[4]Southern Illinois Univ, Dept Geog & Environm Resources, Carbondale, IL 62901 USA;[5]Chinese Acad Forestry, Res Inst Forest Resources Informat Tech, Beijing 100091, Peoples R China

年份：2020

卷号：42

期号：3

起止页码：161-169

外文期刊名：RANGELAND JOURNAL

收录：;Scopus(收录号：2-s2.0-85095437692);WOS:【SCI-EXPANDED(收录号:WOS:000582762700001)】；

基金：This work was supported by The National Bureau to Combat Desertification, State Forestry Administration of China (101-9899); Training Fund of Young Professors from Hunan Provincial Education Department (70702-20190001); Scientific Innovation Fund for Post-graduates of Central South University of Forestry and Technology (CX20192025) and Scientific Innovation Fund for Post-graduates of Hunan Province (CX20190622).

语种：英文

外文关键词：accurate estimation; desertification; geographically weighted logistic regression; Kangbao County; land degradation; northern China; remote sensing; spatial variability; vegetation cover

摘要：Accurately estimating and mapping vegetation cover for monitoring land degradation and desertification of arid and semiarid areas using remotely sensed images is promising but challenging in remote, sparsely vegetated and large areas. In this study, a novel method - geographically weighted logistic regression (GWLR - integrating geographically weighted regression (GWR) and a logistic model) was proposed to improve vegetation cover mapping of Kangbao County, Hebei of China using Landsat 8 image and field data. Additionally, a new method to determine the bandwidth of GWLR is presented. Using cross-validation, GWLR was compared with a globally linear stepwise regression (LSR), a local linear modelling method GWR and a nonparametric method, k-nearest neighbours (kNN) with varying numbers of nearest plots. Results demonstrated (1) the red and near infrared relevant band ratios and vegetation indices significantly improved mapping; (2) the GWLR, GWR and kNN methods led to more accurate predictions than LSR; (3) GWLR reduced overestimations and underestimations compared with LSR, kNN and GWR, and also eliminated negative and very large estimates caused by GWR and LSR; and (4) The maximum distance of spatial autocorrelation could be used to determine the bandwidth for GWLR. Overall, GWLR proved more promising for mapping vegetation cover of arid and semiarid areas.