[1]陆广勇,杨勤科,王海江.基于MODIS-NDVI时序数据的黄土丘陵区土地覆盖分类研究[J].水土保持研究,2011,18(02):112-115,120.
　LU Guang-yong,YANG Qin-ke,WANG Hai-jiang.Land Cover Classification in Loess Hilly and Gully Region Using Multi-temporal MODIS-NDVI Data[J].Research of Soil and Water Conservation,2011,18(02):112-115,120.
点击复制

基于MODIS-NDVI时序数据的黄土丘陵区土地覆盖分类研究

《水土保持研究》[ISSN:1005-3409/CN:61-1272/P] 卷: 18 期数: 2011年02期 页码: 112-115,120 栏目: 出版日期: 2011-04-20
Title:
Land Cover Classification in Loess Hilly and Gully Region Using Multi-temporal MODIS-NDVI Data
作者:
陆广勇1, 杨勤科2,1, 王海江1
1. 中国科学院 水利部 水土保持研究所, 陕西 杨凌 712100;
2. 西北大学, 西安 710069
Author(s):
LU Guang-yong1, YANG Qin-ke2,1, WANG Hai-jiang1
1. Institute of Soil and Water Conservation, Chinese Academy of Sciences and Ministry of Water Resources, Yangling, Shaanxi 712100, China;
2. Northwest University, Xi’an 710069, China
关键词:
植被指数; 时间序列; 决策树; ISODATA; 土地覆盖分类
Keywords:
vegetation index; time-series; decision tree; ISODATA; land cover classification
分类号:
P931.1;TP79
摘要:
为了获取年际土地覆盖基础数据以支持区域土壤侵蚀定量评价，探讨了采用基于时间序列谐波分析法（HANTS）对延河流域2006年MODIS-NDVI时间序列进行滤波；参考当地年植被变化特征，根据土地覆盖类型的NDVI时序曲线特征，选择定量化的分类特征，进行决策树分类，并以此为基础建立各个决策树类别掩膜；基于MODIS-NDVI和MOD09GA，在各个掩膜区内进行非监督分类，结合坡度图调整分类结果，形成延河流域土地覆盖类型图。结果表明：与2006年TM分类结果的总体一致性为75%，Kappa系数为0.620 9，影像分类结果可靠，分类方法现实可行。
Abstract:
The temporal features of various land objects were studied based on the MOD13Q1, and built the decision tree model for the land cover classification of Yanhe basin by filtering the MODIS-NDVI time-series data of 2006 in the area via the HNATS (Harmonic Analysis of Time Series) algorithm; analyzing the temporal curve features of NDVI, and selecting the rational quantitative classification features for the decision tree model, building masks for each land cover, and performing the unsupervised classifications in the masks based on the data of MODIS-NDVI or MOD09GA, modifying the results via slope data. The results showed the overall accuracy of the final land cover map was 75.00%, and the kappa coefficient was 0.620 9. It is suggested that applying the temporal features in classification model and integrating decision tree with ISODATA for the land cover classification are feasible and promising.

参考文献/References:

[1] 宫攀, 陈仲新, 唐华俊, 等.基于MODIS温度/植被指数的东北地区土地覆盖分类[J].农业工程学报, 2006, 22 (9):94-99.
[2] 布和敖斯尔, 刘纪远, 吴祖南.基于季相及经度特征的中国土地覆盖变化遥感研究[J].地理学报, 1998, 53 (12):52-60.
[3] 盛永伟, 陈维英, 肖乾广, 等.利用气象卫星植被指数进行我国植被的宏观分类[J].科学通报, 1995, 40 (1):68-71.
[4] Jonsson P, Eklundh L.Seasonality extraction by function fitting to time-series of satellite sensor data[J].Ieee Transactions on Geoscience and Remote Sensing, 2002, 40 (8):1824-1832.
[5] 汪权方, 李家永.基于时序NDVI数据的中国红壤丘陵区土地覆被分类研究[J].农业工程学报, 2005, 21 (2):72-77.
[6] 赵英时.遥感应用分析原理与方法[M].北京:科学出版社, 2003.
[7] 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[J].水土保持研究, 2003, 10 (4):88-91.
[8] 卢玲, 李新, 董庆罕, 等.SPOT4-VEGETATION中国西北地区土地覆盖制图与验证[J].遥感学报, 2003, 7 (3):214-221.
[9] Vegetation Indices 16-Day L3 Global 500m[EB/OL]. https://lpdaac.usgs.gov/lpdaac/products/modis_products_table/vegetation_indices/16_day_13_global_500m/mod13a1.
[10] Vegetation Indices 16-Day L3 Global 250m[EB/OL]. https://lpdaac.usgs.gov/lpdaac/products/modis_products_table/vegetation_indices/16_day_l3_global_250m/myd13q1.
[11] 王正兴, 刘闯, Huetealfredo.植被指数研究进展:从AVHRR-NDVI到MODIS-EVI[J].生态学报, 2003, 23 (5):979-987.
[12] Guerschman J P, Hill M J, Renzullo L J, et al.Estimating fractional cover of photosynthetic vegetation, non-photosynthetic vegetation and bare soil in the Australian tropical savanna region upscaling the EO-1 Hyperion and MODIS sensors[J].Remote Sensing of Environment, 2009, 113 (5):928-945.
[13] 刘勇洪, 牛铮.基于MODIS遥感数据的宏观土地覆盖特征分类方法与精度分析研究[J].遥感技术与应用, 2004, 19 (4):217-224.
[14] 张霞, 孙睿, 张兵, 等.基于MODIS植被指数时间谱的华北平原土地覆盖分类[J].农业工程学报, 2006, 22 (12):128-132.
[15] 左丽君, 张增祥, 董婷婷, 等.MODIS/NDVI和MODIS/EVI在耕地信息提取中的应用及对比分析[J].农业工程学报, 2008, 24 (3):167-172.
[16] 王红说, 黄敬峰.基于MODIS NDVI时间序列的植被覆盖变化特征研究[J].浙江大学学报:农业与生命科学版, 2009, 35 (1):105-110.
[17] 谢红霞.延河流域土壤侵蚀时空变化及水土保持环境效应评价研究[D].西安:陕西师范大学, 2008.
[18] 李正国, 王仰麟, 吴健生.等.不同土地利用方式对黄土高原植被覆盖季节变化的影响:以陕北延河流域为例[J].第四纪研究, 2005 (06):762-769.
[19] Roerink G M, Menent W.Verhoef. Reconstructing cloudfree NDVI composites using Fourier analysis of time series[J].International Journal of Remote Sensing, 2000, 21 (9):1911-1917.
[20] 王丹, 姜小光, 唐伶俐, 等.利用时间序列傅立叶分析重构无云NDVI图像[J].国土资源遥感, 2005 (2):29-32.
[21] 张树誉, 王钊, 李星敏.提高卫星遥感资料利用率的方法[J].测绘学院学报, 2004, 21 (1):30-33.
[22] 刘咏梅, 杨勤科, 温仲明.地形复杂地区遥感图像分类方法应用研究:以黄土丘陵沟壑地区坡耕地遥感调查为例[J].水土保持通报, 2003, 23 (4):30-32.
[23] Kumar U N, Kerle T V.Ramachandra. Constrained Linear Spectral Unmixing Technique for Regional Land Cover Mapping Using MODIS Data[J].Innovations and Advanced Techniques in Systems, Computing Sciences and Software Engineering, 2008:416-423, DOI: 10.1007/978-1-4020-8735-6_78.

相似文献/References:

[1]杨勤科,罗万勤,马宏斌,等.区域水土流失植被因子的遥感提取[J].水土保持研究,2006,13(05):267.
　YANG Qing-ke,LUO Wan-qin,MA Hong-bin,et al.NDVI Extraction of Regional Soil Erosion Based on Remate Sensing[J].Research of Soil and Water Conservation,2006,13(02):267.
[2]张和喜,杨静,方小宇,等.时间序列分析在土壤墒情预测中的应用研究[J].水土保持研究,2008,15(04):82.
　ZHANG He-xi,YANG Jing,FANG Xiao-yu,et al.Application of Time Series Analysis in Soil Moisture Forecast[J].Research of Soil and Water Conservation,2008,15(02):82.
[3]马驰,卢玉东.重庆南部TM图像植被指数与植被覆盖度信息的关系研究[J].水土保持研究,2008,15(06):136.
　MA Chi,LU Yu-dong.The Correlation Between Percentage of Vegetation Cover and Normalized Difference Vegetation Index in the South of Chongqing City[J].Research of Soil and Water Conservation,2008,15(02):136.
[4]张佳,温仲明,杨尚斌.基于自然植被的延河流域生物量空间分布格局评估[J].水土保持研究,2010,17(03):35.
　ZHANG Jia,WEN Zhong-ming,YANG Shang-bin.Spatial Distribution Evaluation of Biomass in Yanhe River Catchment Using Natural Ecosystem as a Reference[J].Research of Soil and Water Conservation,2010,17(02):35.
[5]赵广敏,李晓燕,李宝毅.基于地表温度和植被指数特征空间的农业干旱遥感监测方法研究综述[J].水土保持研究,2010,17(05):245.
　ZHAO Guang-min,LI Xiao-yan,LI Bao-yi.An Overview on Agricultural Drought Montoring Methods Based on Land Surface Temperature and Vegetation Index Feature Space[J].Research of Soil and Water Conservation,2010,17(02):245.
[6]何磊,唐姝娅,苗放,等.岷江上游典型流域叶面积指数的遥感模型及反演[J].水土保持研究,2010,17(01):218.
　HE Lei,TANG Shu-ya,MIAO Fang,et al.Remote Sensing Model and Inversion of Leaf Area Index in the Typical Area of Minjiang Valley Upriver[J].Research of Soil and Water Conservation,2010,17(02):218.
[7]徐学选,陈国良,马国忠.固原30年粮食产量变化及技术进步贡献的数量分析[J].水土保持研究,1996,3(01):196.
　Xu Xuexuan,Chen Guoliang,Ma Guozhong.The Variation Features of Grain Yield in Guyuan County in Recent 30 Years and the Contribution of Associated Factors[J].Research of Soil and Water Conservation,1996,3(02):196.
[8]刘倩楠,欧阳志云,李爱农,等.重庆市森林植被生物量和碳储量的空间分布特征研究[J].水土保持研究,2016,23(06):221.
　LIU Qiannan,OUYANG Zhiyun,LI Ainong,et al.Study on Spatial Differentiation Characteristics of Forest Vegetation Biomass and Carbon Stock in Chongqing City[J].Research of Soil and Water Conservation,2016,23(02):221.
[9]王蕾钦,王飞,李朋飞.相似降水年组下黄土高原植被恢复与土壤水分变化过程与空间特征分析[J].水土保持研究,2017,24(06):179.
　WANG Leiqin,WANG Fei,LI Pengfei.Relationships Between Vegetation Restoration and Soil Moisture on the Loess Plateau[J].Research of Soil and Water Conservation,2017,24(02):179.
[10]张巧凤,刘桂香,于红博,等.锡林郭勒草原蒸散发月季动态及相关因子分析[J].水土保持研究,2017,24(03):164.
　ZHANG Qiaofeng,LIU Guixiang,YU Hongbo,et al.Monthly and Seasonal Dynamics of ET in Xilingol Steppe and Related Factors Analysis[J].Research of Soil and Water Conservation,2017,24(02):164.
[11]马延辉,林辉,孙华.湖南省主要森林类型植被指数动态变化分析[J].水土保持研究,2010,17(03):217.
　MA Yan-hui,LIN Hui,SUN Hua.Variation Analysis of Different Forest Types Vegetation Index in HU’nan Province[J].Research of Soil and Water Conservation,2010,17(02):217.
[12]张盼,马孝义,赵龙,等.基于不同植被指数和分类回归树的关中地区土地利用分类[J].水土保持研究,2018,25(03):310.
　ZHANG Pan,MA Xiaoyi,ZHAO Long,et al.Classification of Land Use in Guanzhong Area Based on Different Vegetation Indexes Time Series and CART[J].Research of Soil and Water Conservation,2018,25(02):310.

备注/Memo

收稿日期:2010-10-2;改回日期:2010-11-17。
基金项目:水土流失经验模型指标体系及孤山川流域年产沙经验模型研究（黄水保200651-08）
作者简介:陆广勇（1985- ），男（壮族），广西贵港市人，在读硕士研究生，主要从事GIS应用和区域土壤侵蚀研究。E-mail：luguangyong16@163.com
通讯作者:杨勤科（1962- ），男，陕西省陇县人，博士，教授，主要从事区域水土流失与GIS应用研究。E-mail：qkyang@nwu.edu.cn

更新日期/Last Update: 1900-01-01