基于多源数据融合方法的中国1 km土地覆盖分类制图

doi:10.11867/j.issn.1001-8166.2009.02.0192

精确的全球及区域土地覆盖数据是陆地表层过程研究的重要基础。在集成研究兴起和多种数据并存的背景下，利用多源信息融合技术进行大尺度土地覆盖制图具有重要的现实意义。证据理论清楚地表达了由于不确定和不完全信息所带来的对命题认识的“无知”，能够确定相应的假设在目前的认知与知识状态下的确定、不确定和“无知”程度，是多源数据决策融合的重要方法。基于证据理论，将2000年中国1∶10万土地利用数据、中国植被图集（1∶100万）的植被型分类、中国1∶10万冰川图、中国1∶100万沼泽湿地图和MODIS 2001年土地覆盖产品（MOD12Q1）进行了融合，最终基于最大信任度原则进行决策，产生了新的、IGBP分类系统的2000年中国土地覆盖数据。新的土地覆盖数据在保持了中国土地利用数据的总体精度的同时，补充了中国植被图中对植被类型及植被季相的信息，更新了中国湿地图，增加了中国冰川图最新信息，使分类系统更加通用。

关键词: 土地覆盖, 土地利用, 遥感, 证据理论

Land cover plays a significant role in the earth system science, which reflects the influence of human activities and environmental changes. In China, many land use/cover maps can be used in recent years. How to combine these date effectively to better produce land cover map is a key question. This paper presents a method to map land cover classification using Dempster-Shafer evidential reasoning (DS). DS theory is a non-parametric classifier and can handle data from any number of sources at any scale of measurement and has an explicit mechanism for handling information uncertainty through the use of the concept of ignorance. The 1km land use data of China in 2000 from China landuse database, the 1∶1000000 vegetation map, the 1km glacier map from 1∶100000 glacier map, the 1∶1000000 wetland map and the MODIS land cover classification product (MOD12Q1) as multi-source of evidence to support each IGBP land cover class. These evidences are then combined using Dempster′s Rule of combination. Finally, a new land cover map with higher accuracy is generated by a decision rule based on maximum belief function and could be representative of the Chinese land-cover status in 2000. A simple compare validation is taken and result shows that the accuracy of each land cover class of new land cover map has be strongly promoted relative to IGBP DISCover and MOD12Q1 land cover map especially for the accuracy of the croplands, urban, glacier, wetland and water bodies class. The evidence theory is can be used for fusing multi classification information. The fusion result is sensitive for the basic probability assignment of input data. The results will be validated further and the basic probability for multi-source input data will be assigned more scientific.

Key words: Land cover, Land use, Dempster-Shafer theory, Remote sensing.

中图分类号:

TP75

[1] Turner B L II, Skole D, Sanderson S, et al. Land-use and land-cover change, in Science/Research Plan[R]. HDP Report 7/IGBP Report 35, Stockholm and Geneva, 1995.
[2] Crutzen P J, Andreae M O. Biomass burning in the tropics-impact on atmospheric chemistry and biogeochemical cycles[J]. Science,1990, 250(4 988): 1 669-1 678.
[3] Keller M, Jacob D J, Wofsy S C, et al. Effects of tropical deforestation on global and regional atmospheric chemistry[J]. Climatic Change, 1991, 19: 139-158.
[4] Hederson-Sellers A, Wilson M F. Surface alhedo data for climatic modeling[J].Review of Geophysics and Space Physics, 1983, 21: 1 743-1 778.
[5] Li Xiaobing.International research on environmental consequence of land use/cover change[J].Advances in Earth Science, 1999, 14(4):395-400.[李晓兵. 国际土地利用—土地覆盖变化的环境影响研究[J]. 地球科学进展, 1999, 14(4):395-400.]
[6] Li Xiaobing, Chen Yunhao, Yu Feng. Global and regional cover mapping from remote sensing data: Status, strategies and trends[J].Advances in Earth Science, 2004,19(1):71-80.[李晓兵, 陈云浩,喻锋. 基于遥感数据的全球及区域土地覆盖制图——现状、战略和趋势[J]. 地球科学进展, 2004,19(1):71-80.]
[7] Yongjiu Dai, Xubin Zeng, Robert E, et al. Common Land Model (CLM) (Technical Documentation and User′s Guide)[Z]. 2001.
[8] Sellers P J, Randall D A, Collatz G J, et al. A revised land surface parameterization (SiB2) for atmospheric GCMs Part I: Model formulation[J].Journal of Climate,1996, 9(4): 676-705.
[9] Loveland T R, Reed B C, Brown J F, et al. Development of a global land cover characteristics database and IGBP DISCover from 1 km AVHRR data[J].International Journal of Remote Sensing,2000, 21(6/7): 1 303-1 330.
[10] Hansen M C, Defries R S, Townshend J R G, et al. Global land cover classification at 1 km spatial resolution using a classification tree approach[J].International Journal of Remote Sensing, 2000, 21(6/7): 1 331-1 364.
[11] Bartholome E, Belward A S. GLC2000: A new approach to global land cover mapping sfrom Earth observation data[J]. International Journal of Remote Sensing,2005, 26(9):1 959-1 977.
[12] Friedl M A, McIver D K, Hodges J C F, et al. Global land cover mapping from MODIS: Algorithms and early results[J].Remote Sensing of Environment, 2002, 83(1): 287-302.
[13] Ran Y, Li X, Lu L. Evaluation of four remote sensing based land cover products over China[J].International Journal of Remote Sensing, 2008(in press).
[14] Liu J,Liu M, Deng X, et al. The land use and land cover change database and its relative studies in China[J].Journal of Geographical Sciences,2002, 12(3):275-282.
[15] Liu J, Liu M L, Tian H Q, et al. Spatial and temporal patterns of China's cropland during 1990-2000 An analysis based on Landsat TM data[J].Remote Sensing of Environment, 2005,98(4):442-456.
[16] Liu Jiyuan. MacroScale Survey and Dynamic Study of Natural Resources and Environment of Chinese by Remote Sensing[M]. Beijing: Chinese Science and Technology Press, 1996.[刘纪远. 中国资源环境遥感宏观调查与动态研究[M].北京：中国科学技术出版社, 1996.]
[17] Liu Jiyuan. Study on national resources and environment survey and dynamic monitoring using remote sensing[J].Journal of remote sensing,1997, 1(3): 225-230.[刘纪远. 国家资源环境遥感宏观调查与动态监测研究国家资源环境遥感宏观调查与动态监测研究[J]. 遥感学报，1997, 1(3): 225- 230.]
[18] Liu Jiyuan, Zhang Zengxiang, Zhuang Dafang, et al. A study on the spatial-temporal dynamic changes of land-use and driving forces analyses of China in the 1990s[J].Geographical Research,2003, 22(1):1-12.[刘纪远，张增祥，庄大方，等. 20世纪90年代中国土地利用变化时空特征及其成因分析[J].地理研究, 2003, 22(1): 1-12.]
[19] Hou Xueyu, ed. Vegetation Map (1∶1 000 000) in China[M]. Beijing:Science Press, 2001.[侯学煜主编,1∶1 000 000中国植被图集[M].北京：科学出版社，2001.]
[20] Wu Lizong, Li Xin. China Glacier Information System[M/CD].Beijing: Ocean Press, 2004.[吴立宗, 李新. 中国冰川信息系统（配光盘）[M/CD]. 北京：海洋出版社, 2004.]
[21] Zhang Shuqing. An introduction of wetland science database in China[J].Scientia Geographica Sinica, 2002,22(2): 188-189.[张树清. 中国湿地科学数据库简介[J]. 地理科学, 2002,22(2): 188-189.]
[22] Hansen M C, Reed B. A comparison of the IGBP DISCover and University of Maryland 1 km global land covers products[J]. International Journal of Remote Sensing,2000, 21(6&7): 1 365-1 373.
[23] Hodges J C F, Friedl M A, Strahler A H. The MODIS global land cover product: New data sets for global land surface parameterization[C]//Proceedings of the Global Change Open Science Conference, Amsterdam, 2001.
[24] Dempster A P. Upper and lower probabilities induced by multivalued mappings[J].Annals of Mathematical Statistics,1967, 38: 325-329.
[25] Shafer G. A Mathematical Theory of Evidence[M]. Princeton, NJ: Princeton University Press, 1976.
[26] Peddle D R. MERCURY: An evidential reasoning image classifier[J].Computers and Geosciences,1995, 21(10): 1 163-1 176.[27] Soh L, Tsatsoulis C, Gineris D. ARKTOS: An intelligent system for SAR sea ice image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2004, 42(1): 229-247.
[28] Comber A J, Law A N R, Lishman J R. A comparison of Bayes′, Dempster-Shafer and Endorsement theories for managing knowledge uncertainty in the context of land cover monitoring[J].Computers, Environment and Urban Systems, 2004, 28(4): 311-327.
[29] Sun W, Liang S, Xu G, et al. Mapping plant functional types from MODIS data using multisource evidential reasoning[J]. Remote Sensing of Environment,2008, 112(3): 1 010-1 024.
[30] Liu Chunping. Studies on the Methods and Application of Multi-Sources Information Fusion in Remote Sensing[D]. Nanjing: Nanjing University of Science and Technology, 2002.[刘纯平. 多源遥感信息融合方法及其应用研究[D].南京: 南京理工大学，2002.][31] Zhu Xiaokun. Application of Fusion Model of Dempster-Shafer Evidence Reasoning in Remote Sensing[D]. Wuhan:Wuhan University, 2005.[祝晓坤.Dempster-Shafer证据推理融合模型在遥感分类中的应用[D].武汉:武汉大学，2005.]
[32] Peng Tianqiang, Li Bicheng. Remote sensing image classification method based on evidence theory and neural networks[J].Journal of Data Acquisition & Processing,2003, 18(2): 170-174.[彭天强，李弼程.一种基于证据理论与神经网络的遥感影像分类方法[J].数据采集与处理，2003, 18(2): 170-174.]
[33] Wang Xuhong, Zhou Mingquan, Geng Guohua. Reseach of the application of the theory of dempster_Shafer in intelligent remote sense classification[J].Computer Applications and Software,2004, 21(9): 28-29.[王旭红，周明全，耿国华.“Dempster Shafer”证据理论在智能化遥感分类中应用研究[J].计算机应用与软件，2004,21(9): 28-29.]
[34] Wang Yang, Zheng Qinbo, Zhang Junping. Target classification of the data fusion in multichannel using Dempster-Shafer method[J].Journal of Infrared and Millimeter Waves, 2002, 21(3): 229-232.[汪洋，郑亲波，张钧屏. 用证据理论方法进行多波段数据融合的目标分类[J].红外与毫米波学报，2002, 21(3): 229-232.]
[35] Zadeh L A. Fuzzy sets as a basis for a theory of possibility[J].Fuzzy Sets and Systems,1978, 1(1): 3-28.
[36] Ronald Eastman J. IDRISI Kilimanjaro Guide to GIS and Image Processing[Z]. Clark University, 2003.

[1]	段伟利, 邹珊, 陈亚宁, 李稚, 方功焕. 1879－ 2015年巴尔喀什湖水位变化及其主要影响因素分析[J]. 地球科学进展, 2021, 36(9): 950-961.
[2]	王忠静,石羽佳,张腾. TRMM遥感降水低估还是高估中国大陆地区的降水？[J]. 地球科学进展, 2021, 36(6): 604-615.
[3]	崔林丽, 史军, 杜华强. 植被物候的遥感提取及其影响因素研究进展[J]. 地球科学进展, 2021, 36(1): 9-16.
[4]	吴佳梅,彭秋志,黄义忠,黄亮. 中国植被覆盖变化研究遥感数据源及研究区域时空热度分析[J]. 地球科学进展, 2020, 35(9): 978-989.
[5]	董治宝,吕萍,李超. 火星风沙地貌研究方法[J]. 地球科学进展, 2020, 35(8): 771-788.
[6]	刘元波, 吴桂平, 赵晓松, 范兴旺, 潘鑫, 甘国靖, 刘永伟, 郭瑞芳, 周晗, 王颖, 王若男, 崔逸凡. 流域水文遥感的科学问题与挑战[J]. 地球科学进展, 2020, 35(5): 488-496.
[7]	刘磊,翁陈思,李书磊,胡帅,叶进,窦芳丽,商建. 太赫兹波被动遥感冰云研究现状及进展[J]. 地球科学进展, 2020, 35(12): 1211-1221.
[8]	李浩杰,李弘毅,王建,郝晓华. 河冰遥感监测研究进展[J]. 地球科学进展, 2020, 35(10): 1041-1051.
[9]	陈会,李阳兵,唐家发. 贵州坝子现代农业功能分布特征研究[J]. 地球科学进展, 2019, 34(9): 962-973.
[10]	WangJingfeng,刘元波,张珂. 最大熵增地表蒸散模型：原理及应用综述[J]. 地球科学进展, 2019, 34(6): 596-605.
[11]	陈泽青,刘诚,胡启后,洪茜茜,刘浩然,邢成志,苏文静. 大气成分的遥感监测方法与应用[J]. 地球科学进展, 2019, 34(3): 255-264.
[12]	冉有华,李新. 中国多年冻土制图：进展、挑战与机遇[J]. 地球科学进展, 2019, 34(10): 1015-1027.
[13]	肖雄新, 张廷军. 基于被动微波遥感的积雪深度和雪水当量反演研究进展[J]. 地球科学进展, 2018, 33(6): 590-605.
[14]	龙花楼, 曲艺, 屠爽爽, 李裕瑞, 戈大专, 张英男, 马历, 王文杰, 王婧. 城镇化背景下中国农区土地利用转型及其环境效应研究:进展与展望[J]. 地球科学进展, 2018, 33(5): 455-463.
[15]	栾海军, 田庆久, 章欣欣, 聂芹, 朱晓玲. 定量遥感地表参数尺度转换研究趋势探讨[J]. 地球科学进展, 2018, 33(5): 483-492.

阅读次数

全文

摘要

China Land Cover Classification at 1 km Spatial Resolution Based on a Multi-source Data Fusion Approach