Based on Chinese vegetation classification criteria described in the book “Chinese Vegetation”, the vegetation classification system suitable for the farming-pastoral ectones in Northwestern China was established with the field investigation. Using the Landsat images, the terrain data and field data of the study area, the vegetation information in the study area was refined according to the implementation strategy as "hierarchical classification and layer by layer verification". During the extraction process, the mixed pixels decomposition of preprocessed remotely sensed images was performed by using the fully constrained least-squares model, and the vegetation fraction of the study area was obtained. We classified the study area into vegetation area where the vegetation fraction is larger than 5% and non-vegetation area where the vegetation fraction is less than 5%. In the vegetation area, it was further classified into 7 main vegetation type groups which include the tree group, shrub group and grassland group using the CART decision tree based on the spectral characteristic, texture characteristic (Mean) and terrain characteristic (Digital Elevation Model, DEM). Each vegetation type group was again further classified into different sub types based on the refined indexes. The tree group and shrub group were categorized into evergreen vegetation type and deciduous vegetation type based on the NDVI difference ratio index which was established using the seasonal variations of their NDVIs of different plants. The grassland type group was categorized into desert grassland, the typical grassland and meadow grassland using the temperature vegetation dryness index (TVDI). After this step, the spatial distribution of each vegetation type was obtained. It was proved that the overall accuracy of the final classification can reach 79.51% and the kappa coefficient is 0.773. The classification method used in this study makes full use of the spectral information and texture information of the remotely sensed images, and cooperates with terrain information. Experimental result shows that the method of using hierarchical classification and multiple indexes could extract the vegetation information efficiently from the images of the farming-pastoral ectones with high accuracy. The classification result in this area provides the basic data for the further research on the relationship between surface hydrothermal process and land cover change, especially vegetation cover change. Meanwhile, it provides reference for the conservation of vegetation area and ecological environment construction in this area.
[1]李秋月, 潘学标. 气候变化对我国北方农牧交错带空间位移的影响[J]. 干旱区资源与环境,2012, 26(10):1-6. [LI Qiuyue, PAN Xuebiao. The impact of climate change on boundary shift of farming pasture ecotone in northern China [J]. Journal of Arid Land Resources and Environment, 2012, 26(10):1-6.]<br />
[2]贾科利. 基于遥感、GIS的陕北农牧交错带土地利用与生态环境效应研究[D]. 陕西：西北农林科技大学, 2007.[JIA Keli. A study on the land use and eco-environment effects assessment based on remote sensing and GIS in agriculture and pasturage interlaced zone of northern Shaanxi[D]. Northwest A&F University, 2007.]<br />
[3]刘强, 宋松柏, 步永伟. 基于RS和GIS的水土流失综合评价方法——以安吉县为例[J]. 浙江水利科技, 2016, 44(3):31-34. [LIU Qiang, SONG Songbai, BU Yongwei. The comprehensive evaluation method of soil erosion based on RS and GIS:Taking Anji County as an example[J]. Zhejiang Hydrotechnics, 2016, 44(3):31-34.]<br />
[4]刘炜. 土地利用/覆被变化信息遥感图像自动分类识别与提取方法研究[D]. 陕西：西北农林科技大学, 2012.[LIU Wei. Auto-identify classification technology for LUCC information based on remote sensing data[D]. Northwest A&F University, 2012.]<br />
[5]LIU T, YANG X. Mapping vegetation in an urban area with stratified classification and multiple endmember spectral mixture analysis [J]. Remote Sensing of Environment, 2013, 133(12):251-264.<br />
[6]于文婧, 刘晓娜, 孙丹峰,等. 基于HJ-CCD数据和决策树法的干旱半干旱灌区土地利用分类[J]. 农业工程学报, 2016, 32(2):212-219.[ YU Wenjing, LIU Xiaona, SUN Danfeng, et al. Land use classification in arid and semi-arid irrigated area based on HJ-CCD data and decision tree method[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(2): 212-219.]<br />
[7]张熙, 鹿琳琳, 王萍,等. 基于决策树的漓江上游土地覆盖分类[J]. 测绘科学, 2016, 41(3):100-103.[ZHANG Xi, LU Linlin, WANG Ping, et al. Classification of land cover in upstream of Lijiang river basin based on decision tree technologies[J]. Science of Surveying and Mapping, 2016, 41(3):100-103.]<br />
[8]马骊驰, 王金亮, 刘广杰,等. 基于改进型决策树遥感分类的土地利用变化研究[J]. 地理空间信息, 2016, 14(7):12-16.[MA Lichi, WANG Jinliang, LIU Guangjie, et al. Research on land use change based on improved decision tree’s remote sensing classification[J]. Geospatial Information, 2016, 14(7):12-16.]<br />
[9] 王晓学, 沈会涛, 林田苗,等. 利用多信息源提高半干旱地区TM影像的森林类型制图精度:以北京西部山区为例[J]. 自然资源学报, 2017, 32(7):1217-1228.[WANG Xiaoxue, SHEN Huitao, LIN Tianmiao, et al. Improving the forest type mapping accuracy in semiarid mountainous areas based on TM images: Take the West Mountain of Beijing as an example[J]. Journal of Natural Resources, 2017, 32(7):1217-1228.]<br />
[10]方朝阳,邬浩,陶长华,等.鄱阳湖南矶湿地景观信息高分辨率遥感提取[J].地球信息科学学报,2016,18(6):847-856. [ FANG Chaoyang , WU Hao,TAO Changhua, et al. 2016. The wetland information extraction research of Nanji wetland in Poyang Lake based on high resolution remote sensing image[J]. Journal of Geo-information Science, 18(6):847-856.]<br />
[11]Al-Bassam B F. Land use/cover change analysis using remote sensing data: A case study, Zhengzhou Area, Henan Province, China [J]. Al-Khawarizmi Engineering Journal, 2010, 6(2): 72-82.<br />
[12]裴欢, 房世峰. 基于地物光谱特征和空间特征的干旱区绿洲土地分类[J]. 地理科学, 2013, 33(11):1395-1399. [PEI Huan, FANG Shifeng.Land classification of arid oasis based on spectral and spatial feature of ground objects [J]. Scientia Geographica Sinica, 2013, 33(11):1395-1399. ]<br />
[13]LI W, DU J, YI B. Study on classification for vegetation spectral feature extraction method based on decision tree algorithm[C]// Image Analysis and Signal Processing (IASP), 2011 International Conference on. IEEE, 2011:665-669.<br />
[14]KHATAMI R, MOUNTRAKIS G, STEHMAN S V. A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: General guidelines for practitioners and future research [J]. Remote Sensing of Environment, 2016, 177:89-100. <br />
[15]候智庭. 时间序列遥感数据植被分类中的特征选择方法研究[D]. 昆明：云南师范大学, 2017. [HOU Zhiting. Study on the feature selection method in time series remote sensing data vegetation classification [D]. Kunming：Yunnan Normal University,2017] <br />
[16]靳彦华, 熊黑钢, 张芳. 水浇地与旱地春小麦冠层高光谱反射特征比较[J]. 国土资源遥感, 2014, 26(3):24-30. [JIN Yanhua, XIONG Heigang, ZHANG Fang. Comparative study of canopy spectral reflectance characteristics of spring wheat in irrigated land and dry land[J].Remote Sensing for Land & Resources, 2014, 26(3):24-30.]<br />
[17]雷光斌, 李爱农, 边金虎,等. 基于阈值法的山区森林常绿、落叶特征遥感自动识别方法——以贡嘎山地区为例[J]. 生态学报, 2014, 34(24):7210-7221.[LEI Guangbin, LI Ainong, BIAN Jinhu,et al.An practical method for automatically identifying the evergreen and deciduous characteristic of forests at mountainous areas: A case study in Mt.Gongga Region [J].Acta Ecologica Sinica,2014, 34(24):7210-7221.]<br />
[18]中国植被编委会. 中国植被[M]. 北京：科学出版社,1980.[China Vegetation Editorial Board. Chinese vegetation [M].Beijing: Science Press, 1980.]<br />
[19]Wu J, Peng D L. A Research on Extracting Information of the Arid Regions' Vegetation Coverage Using Improved Model of Spectral Mixture Analysis[C]// Multimedia Technology (ICMT), 2010 International Conference on. IEEE, 2010:1-5.<br />
[20]刘欣. 利用CART算法从LandSat8卫星影像提取居民地的研究[D]. 兰州：兰州大学, 2015.[LIU Xin.Using CART algorithm to extract residential land from LandSat8 satellite image [D]. Lanzhou:Lanzhou University,2015.]<br />
[21]张娟. 绿洲开发对干旱区生态环境的影响评价[D]. 兰州:兰州大学, 2016.[ZHANG Juan. The impact of the oasis development on ecological environment [D]. Lanzhou :Lanzhou University, 2016.]<br />
[22]丁小辉, 李华朋, 张树清. 基于多态蚁群算法的高光谱遥感影像最优波段选择[J]. 遥感技术与应用, 2016, 31(2):275-284. [DING Xiaohui, LI Huapeng, ZHANG Shuqing. Optimized band selection of hyperspectral remote sensing image based on polymorphic ant colony algorithm [J]. Remote Sensing Technology and Application, 2016, 31(2):275-284.]<br />
[23]Rao P V N, Sai M V R S, Sreenivas K, et al. Textural analysis of IRS-1D panchromatic data for land cover classification[J]. International Journal of Remote Sensing, 2002, 23(17): 3327-3345.
