Please wait a minute...
 
国土资源遥感  2020, Vol. 32 Issue (4): 236-243    DOI: 10.6046/gtzyyg.2020.04.29
  技术应用 本期目录 | 过刊浏览 | 高级检索 |
基于Sentinel-2A/B时序数据与随机森林算法的农耕区土地利用分类
王德军1(), 姜琦刚2, 李远华2, 关海涛1, 赵鹏飞1, 习靖2
1.黑龙江省第五测绘地理信息工程院,哈尔滨 150081
2.吉林大学地球探测科学与技术学院,长春 130026
Land use classification of farming areas based on time series Sentinel-2A/B data and random forest algorithm
WANG Dejun1(), JIANG Qigang2, LI Yuanhua2, GUAN Haitao1, ZHAO Pengfei1, XI Jing2
1. The Fifth Surveying Mapping and Geographic Information Engineering Institute of Heilongjiang Province, Harbin 150081, China
2. College of Geo-Exploration Science and Technology, Jilin University, Changchun 130026, China
全文: PDF(6646 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

农耕区土地覆被信息是土地资源管理与规划的基础,在合理开发土地资源,调整土地利用结构以及土地动态监测等方面起着重要作用。由于农耕区土地类型复杂并且具有高异质性的特点,土地覆被信息提取的精度一直面临着挑战。因此,以Sentinel-2A/B多光谱遥感数据作为数据源,首先构建归一化植被指数(normalized difference vegetation index, NDVI)时序数据集和缨帽-湿度分量(tasseled cap wetness, TCW)时序数据集; 其次,利用J-M (Jeffries-Matusita)距离对地物进行可分离性分析和挑选出NDVI和TCW最佳时序数据组合; 最后,结合随机森林(random forest, RF)、支持向量机(support vector machine, SVM)、最大似然分类(maximum likelihood classification, MLC)3种分类算法以及利用单时相遥感数据对农耕区典型地物进行分类研究。研究结果表明: 基于时间序列数据结合随机森林分类算法取得了较高的分类精度,其总体分类精度达到88.87%,Kappa系数达到0.855 7,与利用单时相影像数据分类结果的精度相比分别提高了10.05百分点和0.209 3,这充分说明利用时序数据结合RF分类算法在农耕地区能够有效提高典型地物的分类精度。

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
王德军
姜琦刚
李远华
关海涛
赵鹏飞
习靖
关键词 时间序列随机森林土地利用分类农耕区Sentinel-2A/B    
Abstract

Land cover information in farming areas is the basis of land resource management and planning, which plays an important role in the rational development of land resources, adjustment of land use structure, and dynamic monitoring of land. Due to the complex land types and high heterogeneity in farming areas, the accuracy of land cover information extraction has been facing challenges. Therefore, this study used Sentinel-2A/B remote sensing data as the data source. Firstly, a normalized difference vegetation index (NDVI) time series data set and tasseled cap wetness (TCW) time series data set were constructed; Secondly, the J-M (Jeffries-Matusita) distance was used to analyze the separability of the surface features and select the best time series data combination of NDVI and TCW; Finally, combined with random forest (RF), support vector machine (SVM), maximum likelihood classification (MLC) and single phase remote sensing data, the classification of typical features in farming areas was studied, and the accuracy of classification results was evaluated and compared. The research results show that the classification accuracy of the time series data combined with the random forest classification algorithm is relatively high. The overall classification accuracy reaches 88.87%, and the Kappa coefficient reaches 0.855 7, which improves the classification accuracy by 10.05 percentage points and 0.209 3 respectively compared with that of the single remote sensing data. This fully demonstrates that the combination of time series data and random forest classification algorithm can effectively improve the classification accuracy of typical features in farming areas.

Key wordstime series    random forest    land use classification    farming area    Sentinel-2A/B
收稿日期: 2020-02-07      出版日期: 2020-12-23
:  TP79  
基金资助:中国地质调查局项目“辽吉黑区自然资源更新调查”(3S2170124423);中国地质调查局资金资助项目(GFZX0404130302)
作者简介: 王德军(1995-),男,硕士,助理工程师,研究方向为遥感制图及其技术应用。Email:360539842@qq.com
引用本文:   
王德军, 姜琦刚, 李远华, 关海涛, 赵鹏飞, 习靖. 基于Sentinel-2A/B时序数据与随机森林算法的农耕区土地利用分类[J]. 国土资源遥感, 2020, 32(4): 236-243.
WANG Dejun, JIANG Qigang, LI Yuanhua, GUAN Haitao, ZHAO Pengfei, XI Jing. Land use classification of farming areas based on time series Sentinel-2A/B data and random forest algorithm. Remote Sensing for Land & Resources, 2020, 32(4): 236-243.
链接本文:  
https://www.gtzyyg.com/CN/10.6046/gtzyyg.2020.04.29      或      https://www.gtzyyg.com/CN/Y2020/V32/I4/236
Fig.1  研究区Sentinel-2A B4(R),B3(G),B2(B)波段合成影像
编号 卫星传感器 获取日期 数据级别
1 Sentinel-2B 2018-01-12 Level-1C
2 Sentinel-2B 2018-02-18 Level-1C
3 Sentinel-2A 2017-03-13 Level-1C
4 Sentinel-2A 2017-04-02 Level-1C
5 Sentinel-2A 2017-05-12 Level-1C
6 Sentinel-2A 2017-06-28 Level-1C
7 Sentinel-2B 2017-07-16 Level-1C
8 Sentinel-2B 2017-08-22 Level-1C
9 Sentinel-2A 2017-09-09 Level-1C
10 Sentinel-2A 2017-10-19 Level-1C
11 Sentinel-2B 2017-11-20 Level-1C
12 Sentinel-2B 2017-12-20 Level-1C
Tab.1  Sentinel-2A/B影像数据列表
Fig.2  土地利用分类流程
Fig.3  典型地物NDVI时间序列曲线
Fig.4  典型地物TCW时间序列曲线
Sentinel-2A/B数据组合方式 旱地-林地 旱地-草地 旱地-盐碱地 盐碱地-建设用地 建设用地-裸地
6 7 8 1.997 8 1.882 7 1.999 9 1.552 7 1.861 4
5 6 7 8 1.999 9 1.964 1 1.999 9 1.761 5 1.971 6
4 5 6 7 8 1.999 9 1.989 9 1.999 9 1.883 4 1.992 1
4 5 6 7 8 9 1.999 9 1.998 6 1.999 9 1.966 7 1.997 0
4 5 6 7 8 9 10 2.000 0 1.999 1 1.999 9 1.994 3 1.999 0
3 4 5 6 7 8 9 10 2.000 0 1.999 5 2.000 0 1.999 7 1.999 8
2 3 4 5 6 7 8 9 10 2.000 0 1.999 7 2.000 0 1.999 9 1.999 9
1 2 3 4 5 6 7 8 9 10 11 2.000 0 1.999 9 2.000 0 1.999 9 1.999 9
1 2 3 4 5 6 7 8 9 10 11 12 2.000 0 1.999 9 2.000 0 1.999 9 1.999 9
Tab.2  Sentinel-2A/B不同时间序列数据组合的6种典型地物间的J-M距离
Fig.5  不同时相数据个数的典型地物之间J-M距离变化曲线
Fig.6-1  分类结果对比
Fig.6-2  分类结果对比
类别 时序数据+RF 时序数据+SVM 时序数据+MLC 单时相数据+RF
生产者精度/% 用户精度/% 生产者精度/% 用户精度/% 生产者精度/% 用户精度/% 生产者精度/% 用户精度/%
水体 85.66 89.49 87.52 83.46 82.21 83.60 88.91 78.00
草地 96.89 82.64 93.72 88.91 76.26 72.25 73.91 73.12
林地 90.21 93.79 89.83 91.02 83.53 88.96 62.27 67.06
盐碱地 91.08 90.08 92.41 87.69 90.32 85.98 83.33 99.87
旱地 96.01 91.77 95.87 89.09 82.67 87.89 74.07 79.20
建设用地 86.75 86.86 84.45 87.42 84.38 82.66 81.95 69.26
裸地 89.63 90.48 86.91 85.04 83.56 87.88 82.94 85.10
Kappa系数 0.855 7 0.802 3 0.783 2 0.646 4
总体精度/% 88.87 87.51 84.26 78.82
Tab.3  分类精度指标对比
[1] 张静, 张翔, 田龙, 等. 西北旱区遥感影像分类的支持向量机法[J]. 测绘科学, 2017,42(1):49-52,58.
Zhang J, Zhang X, Tian L, et al. The support vector machine method for RS images’ classification in northwest arid area[J]. Science of Surveying and Mapping, 2017,42(1):49-52,58.
[2] 马玥, 姜琦刚, 孟治国, 等. 基于随机森林算法的农耕区土地利用分类研究[J]. 农业机械学报, 2016,47(1):297-303.
Ma Y, Jiang Q G, Meng Z G, et al. Classification of land use in farming area based on random forest algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2016,47(1):297-303.
[3] 林楠, 姜琦刚, 杨佳佳, 等. 基于资源一号02C高分辨率数据的农业区土地利用分类[J]. 农业机械学报, 2015,46(1):278-284.
Lin N, Jiang Q G, Yang J J, et al. Classifications of agricultural land use based on high-spatial ZY1-02C remote sensing images[J]. Transactions of the Chinese Society for Agricultural Machinery, 2015,46(1):278-284.
[4] 王月如, 韩鹏鹏, 关舒婧, 等. 基于Landsat8 OLI数据的富贵竹种植区域信息提取[J]. 国土资源遥感, 2019,31(1):133-140.doi: 10.6046/gtzyyg.2019.01.08.
Wang Y R, Han P P, Guan S J, et al. Information extraction of Dracaena sanderiana planting area based on Landsat8 OLI data[J]. Remote Sensing for Land and Resources, 2019,31(1):133-140.doi: 10.6046/gtzyyg.2019.01.08.
[5] Wardlow B D, Egbert S L. Large-area crop mapping using time-series MODIS 250 m NDVI data:An assessment for the U.S.Central Great Plains[J]. Remote Sensing of Environment, 2008,112(3):1096-1116.
[6] Vintrou E, Desbrosse A, Bégué A, et al. Crop area mapping in West Africa using landscape stratification of MODIS time series and comparison with existing global land products[J]. International Journal of Applied Earth Observation and Geoinformation, 2012,14(1):83-93.
[7] 朱永森, 曾永年, 张猛. 基于HJ卫星数据与面向对象分类的土地利用/覆盖信息提取[J]. 农业工程学报, 2017,33(14):266-273.
Zhu Y S, Zeng Y N, Zhang M. Extract of land use/cover information based on HJ satellites data and object-oriented classification[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017,33(14):266-273.
[8] 张猛, 曾永年. 基于多时相Landsat数据融合的洞庭湖区水稻面积提取[J]. 农业工程学报, 2015,31(13):178-185.
Zhang M, Zeng Y N. Mapping paddy fields of Dongting Lake area by fusing Landsat and MODIS data[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015,31(13):178-185.
[9] 郝鹏宇, 牛铮, 王力, 等. 基于历史时序植被指数库的多源数据作物面积自动提取方法[J]. 农业工程学报, 2012,28(23):123-131,297.
Hao P Y, Niu Z, Wang L, et al. Multi-source automatic crop pattern mapping based on historical vegetation index profiles[J]. Transactions of the Chinese Society of Agricultural Engineering, 2012,28(23):123-131,297.
[10] 龚燃. 哨兵-2A光学成像卫星发射升空[J]. 国际太空, 2015(8):36-40.
Gong R. Sentinel-2A optical imaging satellite launched[J]. Space International, 2015(8):36-40.
[11] 范唯唯. Sentinel-2B卫星发射成功[J]. 空间科学学报, 2017,37(4):371-372.
Fan W W. Sentinel-2B satellite launched successfully[J]. Chinese Journal of Space Science, 2017,37(4):371-372.
[12] 吴静, 吕玉娜, 李纯斌, 等. 基于多时相Sentinel-2A的县域农作物分类[J]. 农业机械学报, 2019,50(9):194-200.
Wu J, Lyu Y N, Li C B, et al. Fine classification of county crops based on multi-temporal images of Sentinel-2A[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019,50(9):194-200.
[13] Belgiu M, Drguţ L. Random forest in remote sensing:A review of applications and future directions[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016,114:24-31.
[14] 赵理君, 唐娉. 典型遥感数据分类方法的适用性分析——以遥感图像场景分类为例[J]. 遥感学报, 2016,20(2):157-171.
Zhao L J, Tang P. Scalability analysis of typical remote sensing data classification methods:A case of remote sensing image scene[J]. Journal of Remote Sensing, 2016,20(2):157-171.
[15] 喻小倩, 刘娜, 李红, 等. 基于线性光谱混合分解和最大似然分类相结合的土地覆被分类——以红寺堡灌区为例[J]. 国土资源遥感, 2010,22(1):96-100.doi: 10.6046/gtzyyg.2010.01.08.
Yu X Q, Liu N, Li H, et al. Land cover classification based on linear spectral mixture decomposition combined with maximum likelihood classfication:A case study of Hongsipu Irrigation Area[J]. Remote Sensing for Land and Resources, 2010,22(1):96-100.doi: 10.6046/gtzyyg.2010.01.08.
[16] 程红芳, 章文波, 陈锋. 植被覆盖度遥感估算方法研究进展[J]. 国土资源遥感, 2008,20(1):13-18.doi: 10.6046/gtzyyg.2008.01.02.
Cheng H F, Zhang W B, Chen F. Advances in researches on application of remote sensing method to estimating vegetation coverage[J]. Remote Sensing for Land and Resources, 2008,20(1):13-18.doi: 10.6046/gtzyyg.2008.01.02.
[17] 罗开盛, 陶福禄. 融合面向对象与缨帽变换的湿地覆被类别遥感提取方法[J]. 农业工程学报, 2017,33(3):198-203.
Luo K S, Tao F L. Method for wetland type extraction using remote sensing combing obiect-oriented and tasseled cap transformation[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017,33(3):198-203.
[18] Wittke S, Yu X, Karjalainen M, et al. Comparison of two-dimensional multitemporal Sentinel-2 data with three-dimensional remote sensing data sources for forest inventory parameter estimation over a boreal forest[J]. International Journal of Applied Earth Observation and Geoinformation, 2019,76:167-178.
[19] Sun Z P, Shen W M, Wei B, et al. Object-oriented land cover classification using HJ-1 remote sensing imagery[J]. Science China Earth Sciences, 2010,53(1):34-44.
doi: 10.1007/s11430-010-4133-6
[20] 王长耀, 刘正军, 颜春燕. 成像光谱数据特征选择及小麦品种识别实验研究[J]. 遥感学报, 2006,10(2):249-255.
doi: 10.11834/jrs.20060237
Wang C Y, Liu Z J, Yan C Y. A experimental study on imaging spectrometer data feature selection and wheat type identification[J]. Journal of Remote Sensing, 2006,10(2):249-255.
doi: 10.11834/jrs.20060237
[21] Breiman L. Random forests[J]. Machine Learning, 2001,45(1):5-32.
doi: 10.1023/A:1010933404324
[22] Adam E, Mutanga O. Spectral discrimination of papyrus vegetation (Cyperus papyrus L.) in swamp wetlands using field spectrometry[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2009,64(6):612-620.
[23] 刘舒, 姜琦刚, 马玥, 等. 基于多目标遗传随机森林特征选择的面向对象湿地分类[J]. 农业机械学报, 2017,48(1):119-127.
Liu S, Jiang Q G, Ma Y, et al. Object-oriented wetland classification based on hybrid feature selection method combining with Relief F,multi-objective genetic algorithm and random forest[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017,48(1):119-127.
[24] 何云, 黄翀, 李贺, 等. 基于Sentinel-2A影像特征优选的随机森林土地覆盖分类[J]. 资源科学, 2019,41(5):992-1001.
doi: 10.18402/resci.2019.05.15
He Y, Huang C, Li H, et al. Land-cover classification of random forest based on Sentinel-2A image feature optimization[J]. Resources Science, 2019,41(5):992-1001.
doi: 10.18402/resci.2019.05.15
[1] 李伟光, 侯美亭. 植被遥感时间序列数据重建方法简述及示例分析[J]. 自然资源遥感, 2022, 34(1): 1-9.
[2] 吴琳琳, 李晓燕, 毛德华, 王宗明. 基于遥感和多源地理数据的城市土地利用分类[J]. 自然资源遥感, 2022, 34(1): 127-134.
[3] 宋奇, 冯春晖, 马自强, 王楠, 纪文君, 彭杰. 基于1990—2019年Landsat影像的干旱区绿洲土地利用变化与模拟[J]. 自然资源遥感, 2022, 34(1): 198-209.
[4] 柳明星, 刘建红, 马敏飞, 蒋娅, 曾靖超. 基于GF-2 PMS影像和随机森林的甘肃临夏花椒树种植监测[J]. 自然资源遥感, 2022, 34(1): 218-229.
[5] 郭晓征, 姚云军, 贾坤, 张晓通, 赵祥. 基于U-Net深度学习方法火星沙丘提取研究[J]. 自然资源遥感, 2021, 33(4): 130-135.
[6] 钞振华, 车明亮, 侯胜芳. 基于时间序列遥感数据植被物候信息提取软件发展现状[J]. 自然资源遥感, 2021, 33(4): 19-25.
[7] 赖佩玉, 黄静, 韩旭军, 马明国. 基于GEE的三峡蓄水对重庆地表水和植被影响研究[J]. 自然资源遥感, 2021, 33(4): 227-234.
[8] 周超凡, 宫辉力, 陈蓓蓓, 雷坤超, 施轹原, 赵宇. 联合WT-RF的津保高铁沿线地面沉降预测[J]. 自然资源遥感, 2021, 33(4): 34-42.
[9] 刘春亭, 冯权泷, 金鼎坚, 史同广, 刘建涛, 朱明水. 随机森林协同Sentinel-1/2的东营市不透水层信息提取[J]. 自然资源遥感, 2021, 33(3): 253-261.
[10] 许赟, 许艾文. 基于随机森林的遥感影像云雪雾分类检测[J]. 国土资源遥感, 2021, 33(1): 96-101.
[11] 吴倩, 姜琦刚, 史鹏飞, 张莉莉. 基于高光谱的土壤碳酸钙含量估算模型研究[J]. 国土资源遥感, 2021, 33(1): 138-144.
[12] 杨立娟. 基于两层随机森林模型估算中国东部沿海地区的PM2.5浓度[J]. 国土资源遥感, 2020, 32(4): 137-144.
[13] 孙超, 陈振杰, 王贝贝. 基于SAR时间序列的建设用地扩展监测——以常州市新北区为例[J]. 国土资源遥感, 2020, 32(4): 154-162.
[14] 李国庆, 黄菁华, 刘冠, 李洁, 翟博超, 杜盛. 基于Landsat8卫星影像土地利用景观破碎化研究——以陕西省延安麻塔流域为例[J]. 国土资源遥感, 2020, 32(3): 121-128.
[15] 王碧晴, 韩文泉, 许驰. 基于图像分割和NDVI时间序列曲线分类模型的冬小麦种植区域识别与提取[J]. 国土资源遥感, 2020, 32(2): 219-225.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《自然资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 E-mail:zrzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发