A Rule-based Land Cover Classification Method for the Heihe River Basin

  • 1. Center for Hydrologic Cycle and Water Resources Research in Arid Region, College of Earth and Environmental Science, Lanzhou University, Lanzhou 730000, China;
    2. Department of Civil and Environmental Engineering, University of Pittsburgh, Pittsburgh, PA, 15261, USA;
    3. Cold and Arid Regions Environmental and Engineering Research Institute, CAS, Lanzhou 730000, China

Received date: 2010-07-22

  Revised date: 2010-12-20

  Online published: 2011-04-20

Supported by

MOST 863 Project No.2008AA12Z205; Knowledge Innovation Project CAS, No.KZCX2-YW-Q10-1


A novel rule-based land use/land cover classification approach is presented in this study. Rule tables were generated based on geographic characteristics of each class of the China land use classification schema and its possible transferability into other classes of the USGS schema. The USGS land use/land cover (LULC) data product, with a 1-km spatial resolution, was used to locate clustering centers, referred as NDVI fingerprints, of each land use class. A minimum distance approach was then applied to the 1 km NDVI of the year 2009 and 90 m DEM of the Heihe River Basin (HRB), with rule tables considered, to produce a land use/land cover map with schema and attributes consistent with USGS's. The produced map can be used in atmospheric models and land surface models. A comparison to the previous work and satellite images indicates that our rule-based approach is better in distinguishing land cover characteristics, especially for snow-cover, frozen soil and desert types.

Cite this article

HOU Yuting, WANG Shugong, NAN Zhuotong . A Rule-based Land Cover Classification Method for the Heihe River Basin[J]. Acta Geographica Sinica, 2011 , 66(4) : 549 -561 . DOI: 10.11821/xb201104011


[1] Vorosmarty C, Lettenmaier D, Leveque C et al. Humans transforming the global water system. Eos., 2004, 85(48): 509-513.

[2] Zhu Deqin, Gao Xiaoqing, Chen Wen. Validation of SSiB model over gobi in Dunhuang and its sensitivity to vegetationparameters. Journal of Desert Research, 2006, 26(3): 466-472. [朱德琴, 高晓清, 陈文. 陆面模式(SSiB) 对敦煌荒漠戈壁下垫面陆面过程的模拟及敏感性试验. 中国沙漠, 2006, 26(3): 466-472.]

[3] Pielke R A, Lee T J, Dalu G A et al. Nonlinear influence of mesoscale land use on weather and climate. Journal of Climate,1991, 4(11): 1053-1069.

[4] Pielke S, Roger A. Influence of the spatial distribution of vegetation and soils on the prediction of cumulus convectiverainfall. Rev. Geophys., 2001, 39(2): 151-177.

[5] Xue Y, Zeng F J, Mitchell K E et al. The impact of land surface processes on simulations of the US hydrological cycle: Acase study of the 1993 flood using the SSiB land surface model in the NCEP Eta regional model. Monthly Weather Review,2001, 129(12): 2833-2860.

[6] Chen F, Dudhia J. Coupling an advanced land surface-hydrology model with the Penn State--NCAR MM5 modelingsystem. Part I: Model implementation and sensitivity. MonthlyWeather Review, 2001, 129(4): 569-585.

[7] Elguindi N, Bi X, Giorgi F et al. RegCM Version 3.1 User's Guide [EB/OL]. PWCG Abdus Salam ICTP, 2006.

[8] Xiu A, Pleim J E. Development of a land surface model (Part I): Application in a mesoscale meteorological model. Journalof Applied Meteorology, 2001, 40(2): 192-209.

[9] Sertel E, Robock A, Ormeci C. Impacts of land cover data quality on regional climate simulations. International Journal ofClimatology, 2009, doi: 10.1002/joc.2036.

[10] Byun D, Kim S, Cheng F Y et al. Utilization of satellite-derived high resolution land use/land cover data for themeteorological, emissions, and air quality modeling. Fifth Conference on Urban Environment. Amer. Meteor. Soc., 2004.

[11] Civerolo K L. Simulating the effects of urban-scale land use change on surface meteorology and ozone concentrations inthe New York City metropolitan region. Seventh Conference on Atmospheric Chemistry, 2005.

[12] Cheng F Y, Byun D W. Application of high resolution land use and land cover data for atmospheric modeling in theHouston-Galveston metropolitan area (Part I): Meteorological simulation results. Atmospheric Environment, 2008, 42(33): 7795-7811.

[13] Lam J S L, Lau A K H, Fung J C H. Application of refined land-use categories for high resolution mesoscale atmosphericmodelling. Boundary-Layer Meteorology, 2006, 119(2): 263-288.

[14] Burian S J, Stetson S W, Han W et al. High-resolution dataset of urban canopy parameters for Houston, Texas. FifthConference on Urban Environment, 2004: 23-26.

[15] Hagemann S. An improved land surface parameter dataset for global and regional climate models. Max-Planck-Institut fürMeteorologie, 2002: 1-21.

[16] Hagemann S, Botzet M, Dümenil L et al. Derivation of global GCM boundary conditions from 1 km land use satellitedata. Max-Planck-Institut für Meteorologie, 1999: 1-20.

[17] Sellers P J, Los S O, Tucker C J et al. A revised land surface parameterization (SiB2) for atmospheric GCMs (Part II): Thegeneration of global fields of terrestrial biophysical parameters from satellite data. Journal of Climate, 1996, 9(4):706-737.

[18] Anderson J R, Hardy E E, Roach J T et al. A land use and land cover classification system for use with remote sensor data.Washington, DC US Geological Survey: Professional Paper 964, 1976.

[19] WangW, Barker D, Bruyere C et al. WRF Version 2 Modeling System User's Guide, 2004.

[20] Frey K E, Smith L C. How well do we know northern land cover? Comparison of four global vegetation and wetlandproducts with a new ground-truth database forWest Siberia. Global Biogeochem. Cycles, 2007, 21: B1016.

[21] Sedano F, Gong P, Ferrao M. Land cover assessment with MODIS imagery in southern African Miombo ecosystems.Remote Sensing of Environment, 2005, 98(4): 429-441.

[22] Gong Peng. Accuracy assessment of global land cover datasets based on global field stations. Progress in Natural Science,2009, 19(7): 754-759. [宫鹏. 基于全球通量观测站的全球土地覆盖图精度检验. 自然科学进展, 2009, 19(7): 754-759.]

[23] Herold M, Mayaux P, Woodcock C E et al. Some challenges in global land cover mapping: An assessment of agreementand accuracy in existing 1 km datasets. Remote Sensing of Environment, 2008, 112(5): 2538-2556.

[24] Ran Youhua, Li Xin, Lu Ling. Accuracy evaluation of the four remote sensing based land cover products over China.Journal of Glaciology and Geocryology, 2009, 31(3): 490-500. [冉有华, 李新, 卢玲. 四种常用的全球1 km土地覆盖数据中国区域的精度评价. 冰川冻土, 2009, 31(3): 490-500.]

[25] Ran Youhua, Li Xin, Lu Ling. China land cover classification at 1 km spatial resolution based on a multi-source datafusion approach. Advances in Earth Science, 2009, 24(2): 192-203. [冉有华, 李新, 卢玲. 基于多源数据融合方法的中国1 km土地覆盖分类制图. 地球科学进展, 2009, 24(2): 192-203.]

[26] Liu Wei, Gao Yanhong, Li Haiying et al. Landuse patterns of Heihe River Basin and its impact modeling. PlateauMeteorology, 2007, 26(2): 278-285. [刘伟, 高艳红, 李海英等. 黑河流域土地覆盖分类数据的建立及其影响的模拟. 高原气象, 2007, 26(2): 278-285.]

[27] Chen Feng, Xie Zhenghui. A land cover dataset based on Chinese vegetation data and its impact on land surfacesimulations. Chinese Journal of Atmospheric Sciences, 2009, 33(4): 681-697. [陈锋, 谢正辉. 基于中国植被数据的陆面覆盖及其对陆面过程模拟的影响. 大气科学, 2009, 33(4): 681-697.]

[28] Liu J, Liu M, Tian H et al. Spatial and temporal patterns of China's cropland during 1990-2000: An analysis based onLandsat TM data. Remote Sensing of Environment, 2005, 98(4): 442-456.

[29] Liu J, Liu M, Deng X et al. The land use and land cover change database and its relative studies in China. Journal ofGeographical Sciences, 2002, 12(3): 275-282.

[30] Yellow River Conservancy Committee. Overview of the Heihe River Basin. http://www.yellowriver.gov.cn/vh/heihe/lykk.php, 2010-06-22. [黄河水利委员会. 黑河概览. http://www.yellowriver.gov.cn/vh/heihe/lykk.php, 2010-06-22.]

[31] Gallo K, Ji L, Reed B et al. Comparison of MODIS and AVHRR 16-day normalized difference vegetation index compositedata. Geophys. Res. Lett., 2004, 31: L7502.

[32] Assessment F R. Global land cover characteristics data base version 2.0. 2000.

[33] Brown J F, Reed B C, Huewe L. Advanced strategy for multi-source analysis and visualization in land covercharacterization. Proceedings, Pecora 13, Human Interactions with the Environment: Perspectives from Space, 1998:367-382.

[34] Wang Rongjing. SVM-based MODIS land cover classification feature select and application [D]. Beijing: ChinaAgricultural University, 2005. [王荣静. 基于SVM的MODIS 数据土地覆盖分类方法研究[D]. 北京: 中国农业大学,2005.]

[35] Pan Yaozhong, Li Xiaobing, He Chunyang. Research on comprehensive land cover classification in China: Based onNOAA/AVHRR and Holdridge PE index. Quaternary Sciences, 2000, 20(3): 270-281. [潘耀忠, 李晓兵, 何春阳. 中国土地覆盖综合分类研究: 基于NOAA/AVHRR和Holdridge PE. 第四纪研究, 2000, 20(3): 270-281.]

[36] Du Mingyi, Wu Wenbo, Guo Dazhi. Research on multi-source geographic information based classification ofdesertification. Journal of Image and Graphics, 2002, 7(7): 740-743. [杜明义, 武文波, 郭达志. 多源地学信息在土地荒漠化遥感分类中的应用研究. 中国图象图形学报: A 辑, 2002, 7(7): 740-743.]

[37] Li Daofeng, Tian Yuying, Hao Fanghua. NDVI data based study on complex classification of vegetation cover of YellowRiver Basin. Research of Soil and Water Conservation, 2003, 10(4): 88-91. [李道峰, 田英, 郝芳华. 基于NDVI 数据的黄河流域地表植被覆盖综合分类研究. 水土保持研究, 2003, 10(4): 88-91.]

[38] Yu Q, Gong P, Tian Y Q et al. Factors affecting spatial variation of classification uncertainty in an image object-basedvegetation mapping. Photogrammetric Engineering & Remote Sensing, 2008, 74(8): 1007-1018.

[39] Wang Jinye, Che Kejun, Yan Kelin et al. Analysis of the runoff components in the forestry areas of the Qilian Mountainsand temporal and spatial variation. Journal of Glaciolgy and Geocryology, 1999, 21(1): 59-63. [王金叶, 车克钧, 闰克林等. 祁连山森林覆盖区河川径流组成与时空变化分析. 冰川冻土, 1999, 21(1): 59-63.]

[40] Chen Rensheng, Kang Ersi, Ji Xibin et al. Preliminary study of the hydrological processes in the alpine meadow andpermafrost regions at the Headwaters of Heihe River. Journal of Glaciology and Geocryology, 2007, 29(3): 387-396. [陈仁升, 康尔泗, 吉喜斌等. 黑河源区高山草甸的冻土及水文过程初步研究. 冰川冻土, 2007, 29(3): 387-396.]