The Detection and Analysis of Land Use Change in the Laoha River Basin During the Past Four Decades
FANG Xiu-qin1, REN Li-liang2, LI Qiong-fang2
1. School of Earth Sciences and Engineering, Hohai University, Nanjing 210098, China; 2. State Key Laboratory of Hydrology, Water Resources and Hydraulic Engineering, Hohai University, Nanjing, 210098, China
摘要利用决策树和支持向量机分类方法,基于多期Landsat MSS, TM and ETM+遥感图像和其他辅助数据,对1970s以来近40年半干旱的老哈河流域土地利用变化(land use and land cover change, LUCC)进行动态监测,并利用GIS方法对LUCC进行了定量分析和空间分布制图。结果显示,利用支持向量机分类方法对该地区1976年、1989年、1999年和2007年土地覆盖类型分类可达到较满意的效果; 近40年老哈河流域土地利用变化显著,水体和草地减少,城乡用地持续扩张,耕地大幅增加,林地和未利用地大幅度波动、总体减少。LUCC主要发生在林地、草地和耕地之间,表明农、林、牧用地之间转换显著,且在各个时期的空间分布差别较大。从变化强度来看,土地利用的年综合变化率最大值渐趋增大,年均土地动态度在空间分布上差异很大,另外在各研究期赤峰市区周边动态度都很大,反映了赤峰市持续性的城市化进程。
Abstract：On the basis of the multiple remote sensing images of Landsat MSS, TM and ETM+ and other auxiliary data, two classification approaches of decision tree and support vector machine were applied to land use/cover classifications in the semiarid Laoha river basin over the past 40 years since the 1970s. The land use changes and their spatial distribution were analyzed quantitatively and mapped with GIS techniques. The results show that land use/cover maps in 1976, 1989, 1999 and 2007 could be generated based on the implementation of support vector machine classification with satisfying results. The analysis shows that land use has changed very obviously in the study area over the last 40 years. The areas of water body and grassland have decreased while rural and urban areas increased persistently. The cultivated land area has increased substantially. Forest land and fallow land have changed in fluctuation with a decrease on the whole. It’s obvious that the most remarkable change has been the interconversion of lands for agriculture (cultivated land), for forestry (forest land), and for animal husbandry (grassland). Moreover, the spatial distribution of the conversion was greatly different in different periods. An analysis of the intensity of land use changes indicates that the highest annual rate of land use change has been increased gradually and the annual intensity has been spatially heterogeneous. Moreover, the suburbs surrounding Chifeng city always have changed intensively during the past decades, suggesting the persistent urbanization of Chifeng city.
方秀琴, 任立良, 李琼芳. 近40年老哈河流域土地利用变化监测与分析 [J]. 国土资源遥感, 2012, 24(2): 125-131.
FANG Xiu-qin, REN Li-liang, LI Qiong-fang. The Detection and Analysis of Land Use Change in the Laoha River Basin During the Past Four Decades. REMOTE SENSING FOR LAND & RESOURCES, 2012, 24(2): 125-131.
[1] 于兴修,杨桂山,王瑶.土地利用/覆被变化的环境效应研究进展与动向[J].地理科学,2004,24(5):627-633. [2] 李天宏,韩鹏.厦门市土地利用/覆盖动态变化的遥感检测与分析[J].地理科学,2001,21(6):537-543. [3] Alberti M,Weeks R,Coe S,et al.Urban Land Cover Change Analysis in Central Puget Sound[J].Photogrammetric Engineering & Remote Sensing,2004,70(9):1043-1052. [4] Goetz S J,Varlyguin D,Smith A J,et al.Application of Multitemporal Landsat Data to Map and Monitor Land Cover and Land Use Change in the Chesapeake Bay Watershed[C]//Smits P C,Bruzzone L.Proceedings of the Second International Workshop on the Analysis of Multi-temporal Remote Sensing Images.Singapore:World Scientific Publishing Co,2004. [5] Yang X J.Satellite Monitoring of Urban Spatial Growth in the Atlanta Metropolitan Area[J].Photogrammetric Engineering & Remote Sensing,2002,68(7):725-734. [6] Knorn J,Rabe A,Radeloff V C,et al.Land Cover Mapping of Large Areas Using Chain Classification of Neighboring Landsat Satellite Images[J].Remote Sens Environ,2009,113(3):957-964. [7] 方秀琴,任立良.西辽河的老哈河流域土地利用遥感动态监测[J].地球信息科学学报,2009,11(1):125-131. [8] Elvidge C D,Sutton P C,Wagner T W.Urbanization [C]//Gutman G,Janetos A,Justice C,et al.Land Change Science:Observing, Monitoring,and Understanding Trajectories of Change on the Earth’s Surface.Dordrecht,Netherlands:Kluwer Academic Publishers:315-328. [9] 刘勇洪,牛铮,王长耀.基于MODIS数据的决策树分类方法研究与应用[J].遥感学报,2005,9(4):405-412. [10] Hanson M C,Dubayah R,DeFries R S.Classification Trees:an Alternative to Traditional Land Cover Classifiers[J].Int J Remote Sens,1996,17(5):1075-1081. [11] Friedl M A,McIver D K,Hodges J C F,et al.Global Land CoverMapping from MODIS:Algorithms and Early Results[J].Remote Sens Environ,2002,83(1/2):287-302. [12] Joy S M,Reich R M,Reynolds R T.A Non-parametric,Supervised Classification of Vegetation Types on the Kaibab National Forest Using Decision Trees[J].Int J Remote Sens,2003,24(9):1835-1852. [13] Sesnie S E,Gessler P E,Finegan B,et al.Integrating Landsat TM and SRTM-DEM Derived Variables with Decision Trees for Habitat Classification and Change Detection in Complex Neotropical Environments[J].Remote Sens Environ,2008,112(5):2145-2159. [14] 赵萍,傅云飞,郑刘根,等.基于分类回归树分析的遥感影像土地利用/覆被分类研究[J].遥感学报,2005,9(6):708-716. [15] 张友静,高云霄,黄浩,等.基于SVM决策支持树的城市植被类型遥感分类研究[J].遥感学报,2006,10(2):191-196. [16] 陈艳华,张万昌.地理信息系统支持下的山区遥感影像决策树分类[J].国土资源遥感,2006(1):69-74 [17] Vapnik V N.The Nature of Statistical Learning Theory[M].New York:Springer Verlag,1995. [18] 骆剑承,周成虎,梁怡,等.支撑向量机及其遥感影像空间特征提取和分类的应用研究[J].遥感学报,2002,6(1):50-55. [19] Zhu G B,Blumberg D G.Classification Using ASTER Data and SVM Algorithms:The Case Study of Beer Sheva,Israel[J].Remote Sens Environ,2002,80(2):233-240. [20] 赵书河,冯学智,都金康,等.基于支持向量机的SPIN-2影像与SPOT-4多光谱影像融合研究[J].遥感学报,2003,7(5):407-411. [21] Foody G M,Mathur A.Toward Intelligent Training of Supervised Image Classifications: Directing Training Data Acquisition for SVM Classification[J].Remote Sens Environ,2004,93(1/2):107-117. [22] Foody G M,Mathur A.The Use of Small Training Sets Containing Mixed Pixels for Accurate Hard Image Classification:Training on Mixed Spectral Responses for Classification by a SVM[J].Remote Sens Environ,2006,103(2):179-189. [23] 张锦水,何春阳,潘耀忠,等.基于SVM的多源信息复合的高空间分辨率遥感数据分类研究[J].遥感学报,2006,10(1):49-57. [24] Mazzoni D,Garay M J,Davies R,et al.An Operational MISR Pixel Classifier Using Support Vector Machines[J].Remote Sens Environ,2007,107(1/2):149-158. [25] Su L H,Chopping M J,Rango A,et al.Support Vector Machines for Recognition of Semi-arid Vegetation Types Using MISR Multi-angle Imagery[J].Remote Sens Environ,2007,107(1/2):299-311. [26] Huang C,Song K,Kim S,et al.Use of a Dark Object Concept and Support Vector Machines to Automate Forest Cover Change Analysis[J].Remote Sens Environ,2008,112(3):970-985. [27] Esch T,Himmler V,Schorcht G,et al.Large-area Assessment of Impervious Surface Based on Integrated Analysis of Single-date Landsat-7 Images and Geospatial Vector Data[J].Remote Sens Environ,2009,113(8):1678-1690. [28] 李建平,张柏,张泠,等.湿地遥感监测研究现状与展望[J].地理科学进展,2007,26(1):33-43. [29] 符淙斌,延晓冬,郭维栋.北方干旱化与人类适应——以地球系统科学观回答面向国家重大需求的全球变化的区域响应和适应问题[J].自然科学进展,2006,16(10):1216-1223. [30] Rouse J W,Haas R H,Schell J A.Monitoring the Vernal Advancement of Retrogradation of Natural Vegetation[R].Greenbelt,MD:NASA/GSFC(Type III,Final Report),1974. [31] McFeeters S K.The Use of the Normalized Difference Water Index (NDWI) in the Delineation of Open Water Features[J].Int J Remote Sens,1996,17(7):1425-1432. [32] 查勇,倪绍祥,杨山.一种利用TM图像自动提取城镇用地信息的有效方法[J].地理学报,2003,7(1):37-41. [33] 何灵敏,沈掌泉,孔繁胜,等.SVM在多源遥感图像分类中的应用研究[J].中国图象图形学报,2007,12(4):648-654. [34] 张锦水,潘耀忠,韩立建,等.光谱与纹理信息复合的土地利用/覆盖变化动态监测研究[J].遥感学报,2007,11(4):500-510. [35] 朱会义,李秀彬.关于区域土地利用变化指数模型方法的讨论[J].地理学报,2003,58(5):643-650.
2012, Vol. 24 
