Please wait a minute...
img

官方微信

遥感技术与应用  2020, Vol. 35 Issue (5): 1118-1126    DOI: 10.11873/j.issn.1004-0323.2020.5.1118
遥感应用     
基于Rapid Eye数据的北京生态涵养区土地利用分类及变化研究
郑琪1,2(),邸苏闯1,3(),潘兴瑶1,3,刘洪禄1,3,朱永华1,2,张岑1,3,周星1,3
1.北京市水科学技术研究院,北京 100048
2.河海大学水文水资源学院,江苏 南京 210009
3.北京市非常规水资源开发利用与节水工程技术研究中心,北京 100048
Study of Land Use Classification and Changes in the Ecological Conservation Region of Beijing based on Rapid Eye Images
Qi Zheng1,2(),Suchuang Di1,3(),Xingyao Pan1,3,Honglu Liu1,3,Yonghua Zhu1,2,Cen ZHang1,3,Xing Zhou1,3
1.Beijing Water Science and Technology Institute,Beijing 100048,China
2.College of Hydrology and Water Resources,Hohai University,Nanjing 210098,China
3.Beijing Engineering Technique Research Centre for Non-conventional Water Resource Exploration and Utilization and Water Use Efficient,Beijing 100048,China
 全文: PDF(5459 KB)   HTML
摘要:

针对目前常用的遥感影像分类方法在复杂下垫面识别中出现的分类精度不高、“椒盐”现象明显等问题,以北京生态涵养区为例,基于Rapid Eye数据开展不同土地利用分类方法研究,并提出优化的分类方法。构建的土地利用分类体系涵盖耕地、水体、建筑区、乔木林、灌木林、矿石堆以及砂石坑。采用面向对象分析技术将研究区分割为3.71万个图斑,分别利用决策树分类法和最邻近分类法提取土地利用类型,结果显示:决策树分类法的总体精度为75%,Kappa系数为0.69,其对水体、耕地、建筑区等光谱特性差异明显的区域具有较高解译精度;最邻近分类法对光谱特征差异不明显的灌木、乔木区域具有较好的分类效果,总体精度为71%,Kappa系数为0.71。基于上述两种方法提出耦合分类法,经检验该方法总体精度可达90%,Kappa系数达0.9,在生态涵养区土地利用分类中具有较好的适用性。利用耦合分类法对2010~2018年土地利用变化情况进行分析,发生较大变化的耕地、建筑区、矿石堆及砂石坑区域均逐渐向林地演变。结果表明:自北京生态涵养区建立以来林地资源保护已初显成效,生态破坏带正逐渐被修复。生态涵养区的建立强化了生态保护和绿色发展向导,对促进京津冀协同可持续发展具有重要意义。

关键词: 土地利用Rapid Eye面向对象分析决策树分类法最邻近分类法    
Abstract:

To overcome the low classification accuracy problems in complex land use regions, a case study is carried out to develop a new classification method based on two traditional classification methods and Rapid Eye remote sensing imagines in the eastern part of ecological conservation region in Beijing City. Firstly, the land use classification system is developed and these land such as cultivated land, water body, build-ups, forest, shrub, mine lot and quarry are included. Secondly, the imagines are segmented into 37 100 polygons using object-oriented technology according to different spectral features, structural features and morphological features. Thirdly, the land use types are identified using Decision Tree method and the Nearest Neighbor method. The overall accuracy values are 75% and 71% for the Decision Tree method and the Nearest Neighbor method, respectively. The Kappa coefficient values are 0.69 and 0.71 for the Decision Tree method and the Nearest Neighbor method, respectively. The results show that the Decision Tree method is with higher accuracy in the regions with distinct spectral characteristics such as water body, vegetation and cultivated land, while the Nearest Neighbor method is with higher accuracy in the regions with similar spectral characteristics such as shrubs and forests. Fourthly, a new optimized combination classification method is proposed based on these two methods with the overall accuracy of 90% and the Kappa coefficient of 0.9. Finally, the land use changes are analyzed in ecological conservation area in Beijing from 2010 to 2018 based on the new method. The results show that the ecological damage zone has being repaired and the areas for mine lot and quarry have being declined. These results could provide technical support to explore the evolution process and the disruption characteristics in the ecological conservation region.

Key words: Land use    Rapid Eye    Object-oriented classification    Decision Tree Method    Nearest Neighbor Method
收稿日期: 2019-09-02 出版日期: 2020-11-26
ZTFLH:  TP79  
基金资助: 北京市科委重大研发项目(Z181100005318003);北京市自然科学基金项目(8184075);国家水专项“国家水体污染控制与治理科技重大专项”(2017ZX07103-002)
通讯作者: 邸苏闯     E-mail: hhu_zq0415@163.com;disuchuang@163.com
作者简介: 郑琪(1995-),女,新疆昌吉人,硕士研究生,主要从事GIS和遥感技术在水文水资源中应用研究。E?mail:hhu_zq0415@163.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
郑琪
邸苏闯
潘兴瑶
刘洪禄
朱永华
张岑
周星

引用本文:

郑琪,邸苏闯,潘兴瑶,刘洪禄,朱永华,张岑,周星. 基于Rapid Eye数据的北京生态涵养区土地利用分类及变化研究[J]. 遥感技术与应用, 2020, 35(5): 1118-1126.

Qi Zheng,Suchuang Di,Xingyao Pan,Honglu Liu,Yonghua Zhu,Cen ZHang,Xing Zhou. Study of Land Use Classification and Changes in the Ecological Conservation Region of Beijing based on Rapid Eye Images. Remote Sensing Technology and Application, 2020, 35(5): 1118-1126.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2020.5.1118        http://www.rsta.ac.cn/CN/Y2020/V35/I5/1118

图1  研究区域范围及遥感影像
一级类二级类
编码类型名编码+类型名
100耕地
200林地201 乔木林202 灌木林
300水体
400建筑区
600裸地601 矿石堆602 砂石坑
表1  土地利用分类体系
图2  影像分割前后对比图
图3  不同地表覆被光谱特征图
图4  影像识别分类决策树
类型图斑数解译面积/km2面积比例/%
乔木3 49880.0216.42
灌木16 305314.0364.42
耕地1 90813.932.86
水体4803.460.71
矿石堆3380.100.20
砂石坑940.660.13
建筑区1481974.4115.26
表2  各类型所占地物面积统计表
图5  样本选择示意图
类型图斑数解译面积/km2所占比例/%
乔木4 05197.6620.07
灌木12 695254.3452.27
耕地6 45664.5413.26
水体1 0746.541.34
矿石堆5801.830.38
砂石坑3 06514.432.97
建筑区9 49547.279.71
表3  各类型所占地物面积统计表
图6  各分类法的2018年土地分类成果图
图7  随机检验样本点分布图
精度分类方法乔木灌木耕地水体建筑区矿石堆砂石坑
制图精度/%决策树分类法66.6760.0085.71100.0080.0071.43100.00
最邻近分类76.1969.2338.46100.0069.2350.00100.00
耦合分类法88.0088.4688.8995.2481.82100.00100.00
用户精度/%决策树分类法64.0072.0060.0090.0080.00100.0080.00
最邻近分类64.0072.0050.0080.0090.0080.0060.00
耦合分类法88.0092.0080.00100.0090.0080.0080.00
总体精度/%决策树分类法75.00
最邻近分类71.00
耦合分类法90.00
Kappa系数决策树分类法0.69
最邻近分类0.71
耦合分类法0.90
表4  各分类法精度对比一览表
2018~2010耕地乔木灌木水体建筑物矿石堆砂石坑
耕地5.143.312.330.542.600.000.00
乔木0.0252.6322.450.354.570.000.00
灌木0.0353.39228.071.7030.770.010.06
水体0.010.130.711.190.420.000.00
建筑区0.066.3220.771.7945.360.000.11
矿石堆0.000.020.080.000.170.030.00
砂石坑0.000.010.210.010.530.000.13
表5  2010~2018土地利用变化转移矩阵
1 Cai Yunlong. A Study on Land Use/Cover Change: The Need for a New Integrated Approach[J]. Geographical Research, 2001,20(6):645-652.
1 蔡运龙.土地利用/土地覆被变化研究:寻求新的综合途径[J].地理研究,2001,20(6): 645-652.
2 Liu Jiyuan, Zhang Zengxiang, Zhang Shuwen, et al. Retrospect and Prospect of Remote Sensing Research on Land Use Change in China——Based on the Guidance of Statement of Peng’s Academic Thought [J]. Journal of Earth Sciences, 2020,22(4):680-687.
2 刘纪远,张增祥,张树文,等.中国土地利用变化遥感研究的回顾与展望——基于陈述彭学术思想的引领[J].地球信息科学学报,2020,22(4):680-687.
3 Zhao Hengqian, Jia Liang, Yin Zhengran, et al. Dynamic Monitoring of Land Use and Ecological Environment based on Multiple Remote Sensing Data: A Case Study of Tongzhou District, Beijing[J]. Geography and Geo-Information Science, 2019, 35(1): 38-43,2.
3 赵恒谦, 贾梁, 尹政然, 等. 基于多源遥感数据的北京市通州区土地利用/覆盖与生态环境变化监测研究[J]. 地理与地理信息科学, 2019, 35(1): 38-43.
4 Davidson A, Wang S. The Effects of Sampling Resolution on the Surface Albedos of Dominant Land Cover Types in the North American Boreal Region[J]. Remote Sensing of Environment, 2004, 93(1): 211-224.
5 Song Minghui. Object-oriented Urban Land Classification with GF-2 Remote Sensing Image[J]. Remote Sensing Technology and Application, 2019, 34(3): 547-552,629.
5 宋明辉. 基于高分二号数据的面向对象城市土地利用分类研究[J]. 遥感技术与应用, 2019, 34(3): 547-552,629.
6 Yu Xingxiu, Yang Guishan. The Advances and Problems of Land Use/Land Cover Change Research in China[J]. Progress in Geography, 2002,21(1): 51-57.
6 于兴修, 杨桂山. 中国土地利用/覆被变化研究的现状与问题[J]. 地理科学进展, 2002,21(1): 51-57.
7 Liu Qi. Analysis of the Spatio-temporal Evolution of Land Use/Cover Based on the Monitoring of Geographical Conditions: Taking Yuci District as an Example[J].Mapping and Spatial Geographic Information,2020,43(5):82-85.
7 刘琦.基于地理国情监测的土地利用/覆盖时空演变分析——以榆次区为例[J].测绘与空间地理信息,2020,43(5):82-85.
8 Hu Yingjie, Kong Xiangbin, Zhang Baodong. Spatial and Temporal Variation Characteristics of Land Use in Beijing in the Past 30 Years[J]. Journal of China Agricultural University, 2018, 23(11): 1-14.
8 胡莹洁, 孔祥斌, 张宝东. 30年来北京市土地利用时空变化特征[J]. 中国农业大学学报, 2018, 23(11): 1-14.
9 Sun Li, Chen Huanwei, Pan Jiawen. Analysis of the Land Use Spatiotemporal Variation based on DEM—Beijing Yanqing County as an Example[J]. Mountain Research, 2004,22(6): 762-766.
9 孙丽, 陈焕伟, 潘家文. 运用DEM剖析土地利用类型的分布及时空变化——以北京延庆县为例[J]. 山地学报, 2004,22(6): 762-766.
10 Zhai Hongyu, Li Mangen, Hu Baoqun, et al. Research on the Influence of DEM on the Temporal and Spatial Distribution of Land Use Types——Taking Fuhe River Basin as an Example [J]. Journal of East China University of Technology (Natural Science), 2020,43(2):164-169.
10 翟宏宇, 李满根, 胡宝群, 等. 基于DEM对土地利用类型时空分布的影响研究——以抚河流域为例[J].东华理工大学学报(自然科学版),2020,43(2):164-169.
11 Sungho K, Bongsik C, Jinsu Y, et al. Binarized Neural Network with Silicon Nanosheet Synaptic Transistors for Supervised Pattern Classification[J]. Scientific Reports, 2019,9(1):11705. doi:10.1038/s41598-019-48048-w.
doi: 10.1038/s41598-019-48048-w
12 Liu Jiao,Zhang Chao,Yu Zhexiu, et al. Research on Land Use Change and Prediction in Fuxian Lake Basin based on Landsat Image[J].Journal of Southwest Forestry University,2020,40(3):131-138.
12 刘娇,张超,余哲修,等.基于Landsat影像的抚仙湖流域土地利用变化及预测研究[J].西南林业大学学报,2020,40(3):131-138.
13 Song J, Lin T, Li X, et al. Mapping Urban Functional Zones by Integrating Very High Spatial Resolution Remote Sensing Imagery and Points of Interest: A Case Study of Xiamen, China[J].Remote Sensing,2018,10(11):1737.doi:10.3390/rs10111737.
doi: 10.3390/rs10111737
14 Liu Qinqin, Cui Yaoping, Liu Sujie, et al. Study on Surface Albedo of Spectral Radiation of Different Land Use Types in China[J]. Remote Sensing Technology and Application, 2019, 34(1): 46-56.
14 刘亲亲, 崔耀平, 刘素洁, 等. 中国不同土地利用类型分光辐射地表反照率研究[J]. 遥感技术与应用, 2019, 34(1): 46-56.
15 Defries R S, Townshend J R G. NDVI Derived Land Cover Classification at a Global Scale[J]. International Journal of Remote Sensing, 1994, 15(17): 3567-3586.
16 Yang Cunjian, Zhou Chenghu. Discussion on Classification Method of Remote Sensing Image based on Knowledge[J]. Geography and Territory Research, 2001(1): 72-77.
16 杨存建, 周成虎. 基于知识的遥感图像分类方法的探讨[J]. 地理学与国土研究, 2001(1): 72-77.
17 Duan Xincheng. Remote Sensing of Land Use Classification based on BP Artificial Neural Network[D]. Beijing: China University of Geosciences (Beijing), 2008.
17 段新成. 基于BP人工神经网络的土地利用分类遥感研究[D]. 北京:中国地质大学(北京), 2008.
18 Wang Huiying, Su Wei, Zhou Junqi. A Method of object-Oriented Remote Sensing Image Information Extraction based on Multi-Classifier[J]. Surveying and Mapping Engineering, 2009, 18(5): 22-26.
18 王惠英, 苏伟, 周军其. 基于多分类器组合面向对象遥感影像信息提取方法[J]. 测绘工程, 2009, 18(5): 22-26.
19 Liu Ying. Research on Land Cover Remote Sensing Classification Method based on Semi-supervised Integrated Support Vector Machine[D]. Changchun: Graduate School of Chinese Academy of Sciences (Northeast Institute of Geography and Agricultural Ecology), 2013.
19 刘颖. 基于半监督集成支持向量机的土地覆盖遥感分类方法研究[D]. 长春:中国科学院研究生院(东北地理与农业生态研究所), 2013.
20 Hao Long, Chen Yongfu, Liu Hua, et al. Object-oriented Classification of Forest Vegetation in Nyingchi County based on Texture Information CART Decision Tree[J]. Remote Sensing Technology and Application, 2017, 32(2): 386-394.
20 郝泷, 陈永富, 刘华, 等. 基于纹理信息CART决策树的林芝县森林植被面向对象分类[J]. 遥感技术与应用, 2017, 32(2): 386-394.
21 Kazem R, Mostafa K, Danya K, et al. Supervised Cross-fusion Method: A New Triplet Approach to Fuse Thermal, Radar, and Optical Satellite Data for Land Use Classification[J]. Environmental Monitoring and Assessment, 2019, 191 (8).
22 Wu Guoxi, Yu Zhengzheng, Liu Liangyun. Regional Landscape Pattern Change and Ecological Restoration: A Case Study of Mentougou District in Beijing[J]. Geographical Research, 2011, 30(7): 1227-1236.
22 吴国玺, 喻铮铮, 刘良云. 区域景观格局变化及生态修复——以北京门头沟区为例[J]. 地理研究, 2011, 30(7): 1227-1236.
23 Du Wanguang, Wang Cheng, Wang Qian, et al. Evaluation of Summer Environmental Effects of Main Vegetation Types in Xiangshan Park, Beijing[J].Scientific Science, 2018, 54(4): 155-164.
23 杜万光, 王成, 王茜, 等. 北京香山公园主要植被类型的夏季环境效应评价[J]. 林业科学, 2018, 54(4): 155-164.
24 Zhang Ping, Sun Qiangqiang, Zhang Yaping, et al. Discussion on the Theory and Technical Methods of Land Degradation Monitoring and Evaluation in Arid Areas Based on Hybrid Decomposition of Broadband Remote Sensing Spectra[J]. Remote Sensing Technology and Application, 2020,35(2):497-508.
24 张平,孙强强,张亚萍,等.基于宽波段遥感光谱混合分解的干旱区土地退化监测评价理论和技术方法探讨[J].遥感技术与应用,2020,35(2):497-508.
25 Song Xiaoyang, Jiang Xiaosan, Jiang Dong, et al. Object-oriented Classification of High Resolution Remote Sensing Image[J].Remote Sensing Technology and Application,2015,30(1):99-105.
25 宋晓阳, 姜小三, 江东,等. 基于面向对象的高分影像分类研究[J]. 遥感技术与应用, 2015,30(1):99-105.
26 Liu Li, Yu Qiang. Research on Remote Sensing Classification based on Hierarchical Classification and Supervised Classification[J]. Forest Investigation Planning, 2007(4): 37-39,44.
26 刘礼, 于强. 分层分类与监督分类相结合的遥感分类法研究[J]. 林业调查规划, 2007(4): 37-39,44.
27 Zhang Jinghua, Feng Zhiming, Jiang Luguang. Progress on Studies of Land Use/Land Cover Classification Systems[J]. Resources Science, 2011, 33(6): 1195-1203.
27 张景华, 封志明, 姜鲁光. 土地利用/土地覆被分类系统研究进展[J]. 资源科学, 2011, 33(6): 1195-1203.
28 Di Suchuang, Wu Wenyong, Liu Honglu, et al. The Correlationship between Urban Greenness and Heat Island Effect with RS Technology: A Case Study within 5th Ring Road in Beijing[J]. Journal of Geo-Information Science,2012,14(4):481- 489.
28 邸苏闯, 吴文勇, 刘洪禄, 等. 城市绿量的遥感估算与热岛效应的相关分析——以北京市五环区域为例[J]. 地球信息科学学报, 2012, 14(4): 481-489.
[1] 李智礼,匡文慧,张澍. 近70 a天津主城区城市土地利用/覆盖变化遥感监测与时空分析[J]. 遥感技术与应用, 2020, 35(3): 527-536.
[2] 陈馨,匡文慧. 基于云平台的中哈干旱区典型城市地表覆盖变化遥感监测与比较[J]. 遥感技术与应用, 2020, 35(3): 548-557.
[3] 赵婷,白红英,邓晨晖,孟清,郭少壮,齐贵增. 基于DEM的秦岭陕西段地表面积与垂直投影面积差异性分析[J]. 遥感技术与应用, 2020, 35(2): 399-405.
[4] 刘亲亲, 崔耀平, 刘素洁, 李楠. 中国不同土地利用类型分光辐射地表反照率研究[J]. 遥感技术与应用, 2019, 34(1): 46-56.
[5] 谷晓天, 高小红, 马慧娟, 史飞飞, 刘雪梅, 曹晓敏. 复杂地形区土地利用/土地覆被分类机器学习方法比较研究[J]. 遥感技术与应用, 2019, 34(1): 57-67.
[6] 李洁, 王福红, 宋晓谕, 石培基, 赵锐峰. 干旱区流域土地利用覆被空间转型模拟及热点探测—以黑河流域中游为例[J]. 遥感技术与应用, 2019, 34(1): 187-196.
[7] 胡云锋,商令杰,张千力,王召海. 基于GEE平台的1990年以来北京市土地变化格局及驱动机制分析[J]. 遥感技术与应用, 2018, 33(4): 573-583.
[8] 闫鹏飞,明冬萍. 尺度自适应的高分辨率遥感影像分水岭分割方法[J]. 遥感技术与应用, 2018, 33(2): 321-330.
[9] 赵梦雨,薛亮. 咸阳市生境质量变化遥感监测研究[J]. 遥感技术与应用, 2017, 32(6): 1171-1180.
[10] 陈洋波,张涛,窦鹏,董礼明,陈华. 基于SVM的东莞市土地利用/覆被自动分类误差来源与后处理[J]. 遥感技术与应用, 2017, 32(5): 893-903.
[11] 谢 瀚,李爱农,汤家法,雷光斌,边金虎. 山地地表覆被野外采样系统研究及应用[J]. 遥感技术与应用, 2016, 31(3): 430-437.
[12] 张文博,覃志豪,刘含海. 基于分形理论的土地利用类型变化研究—以广州番禺为例[J]. 遥感技术与应用, 2015, 30(5): 952-958.
[13] 白晓燕,陈晓宏,王兆礼. 基于面向对象分类的土地利用信息提取及其时空变化研究[J]. 遥感技术与应用, 2015, 30(4): 798-809.
[14] 梁治华,刘勇. 近20年来腾格里沙漠南缘土地利用/土地覆盖变化及其成因探讨—以甘肃省古浪县冰草湾地区为例[J]. 遥感技术与应用, 2015, 30(2): 383-390.
[15] 宋晓阳,姜小三,江东,黄耀欢,万华伟,王昌佐. 基于面向对象的高分影像分类研究[J]. 遥感技术与应用, 2015, 30(1): 99-105.