EN中文

自然资源学报 >

2016 , Vol. 31 >Issue 3: 503 - 513

DOI: https://doi.org/10.11849/zrzyxb.20150358

资源研究方法

基于MODIS时间序列及物候特征的农作物分类

展开
  • 黑龙江省普通高等学校地理环境遥感监测重点实验室,哈尔滨师范大学,哈尔滨 150025
平跃鹏(1991- ),女,河南平顶山人,硕士研究生,主要从事农业遥感研究.E-mail:pingyuepeng2009@163.com

收稿日期: 2015-04-07

  网络出版日期: 2016-03-15

基金资助

国家自然科学基金重点项目(41030743)

收起

Crop Identification Based on MODIS NDVI Time-series Data and Phenological Characteristics

Expand
  • Key Laboratory of Remote Sensing Monitoring of Geographic Environment, College of Heilongjiang Province, Harbin Normal University, Harbin 150025, China

Received date: 2015-04-07

  Online published: 2016-03-15

Supported by

National Natural Science Foundation of China, No.41030743

Fold

摘要

论文以2012年6月至2014年6月期间的MOD09Q1及2013年四五月的MOD09A1为数据源,合成归一化植被指数(NDVI)和归一化水体指数(NDWI),利用TIMESAT软件对NDVI时间序列数据应用分段高斯函数拟合方法重构NDVI时序曲线,并获取7个物候特征(Phenology,以下简称PH,包括生长季始期,生长季末期,生长季长度,NDVI振幅,NDVI左导数,NDVI右导数,生长季期间的NDVI积分).结合Landsat 8 OLI遥感影像,中国第二次土地调查数据和实地采样样本数据,根据2013年多种地物平滑后的NDVI曲线特征,将年NDVI最大值低于0.5的水体和建设用地掩膜去除.为了获取研究区农作物的最优分类方法,采用分层分类:首先对平滑后的46个NDVI时序数据进行支持向量机(SVM)分类,得到农用地等分类信息;其次利用平滑后的46个NDVI波段,7个物候参数及6期归一化水体指数相互组合,对农用地进行支持向量机分类提取3种农作物的分布信息.经不同波段组合分类对比可知,分类总体精度及Kappa系数的关系为:NDVI+NDWI>NDVI+PH+NDWI>PH+NDWI>NDVI+PH>NDVI>PH.研究结果表明,遥感数据波段的增加不一定带来较高的分类精度;论文中归一化水体指数有效地提高了水稻的分类精度.此外,辅以物候特征对农作物分类也具有一定的可行性.

本文引用格式

平跃鹏, 臧淑英 . 基于MODIS时间序列及物候特征的农作物分类[J]. 自然资源学报, 2016 , 31(3) : 503 -513 . DOI: 10.11849/zrzyxb.20150358

Abstract

Agriculture is the foundation of the national economy. Identification of agricultural information by using remote sensing technique in real-time have been a hot topic. This paper aims to study the distribution of the main crops (soybean, corn, rice) effectively in large scale. Firstly, with the Asymmetric Gaussians method of TIMESAT software, the MOD09Q1 datasets with 250 m resolution were used to filter and reconstruct the time-series NDVI curves. Then seven phenological characteristics (start time of the growth season, end time of the growth season, length of the season, amplitude of NDVI, left derivative of NDVI at the beginning of the growth season, right derivative of NDVI at the end of the growth season and integral of NDVI during the growth season) were extracted. Secondly, to analyze the characteristics of time-series NDVI curve of vegetables, water and construction land were masked off because their maximum NDVI values were less than 0.5. Then in order to get the optimal classification accuracy of the crop land, hierarchical classification method was conducted as below: 1) using SVM classification to extract agricultural area based on the time-series NDVI data; 2) using SVM classification to identify three crop classes (soybean, corn, rice) with different combination of three bands (NDVI: NDVI bands; PH: phonological bands; NDWI: NDWI bands) on the basis of the first step. We compare the Overall Accuracy and Kappa coefficient of different combinations, and the result was as below: NDVI+NDWI>NDVI+PH+NDWI>PH+NDWI>NDVI+PH>NDVI>PH, the combination of NDVI+NDWI being the best. It was found that higher dimensions won't bring higher accuracy necessarily, and the application of NDWI can improve the overall accuracy of rice effectively. In addition, it is workable to identify the crop types with the help of phonological information.

参考文献

[1] 陈思宁, 赵艳霞, 申双和. 基于波谱分析技术的遥感作物分类方法 [J]. 农业工程学报, 2012, 28(5): 154-160. [CHEN S N, ZHAO Y X, SHEN S H. Crop classification by remote sensing based on spectral analysis. Transactions of the CSAE, 2012, 28(5): 154-160. ]
[2] 吴炳方. 中国农情遥感速报系统 [J]. 遥感学报, 2004, 8(6): 481-497. [WU B F. China agriculture with remote sensing systems. Journal of Remote Sensing, 2004, 8(6): 481-497. ]
[3] LIU J, LIU M, TIAN H, 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.
[4] VERBEIREN S, H EERENS, PICCARD I, et al. Sub-pixel classification of spot-vegetation time series for the assessment of regional crop areas in Belgium [J]. International Journal of Applied Earth Observation and Geoinformation, 2008, 10(4): 486-497.
[5] 马丽, 徐新刚, 贾建华, 等. 利用多时相TM影像进行作物分类方法 [J]. 农业工程学报, 2008, 24(S2): 191-195. [MA L, XU X G, JIA J H, et al. Crop classification method using multi-temporal TM images. Transactions of the CSAE, 2008, 24(S2): 191-195. ]
[6] 李存军, 王纪华, 刘良云, 等. 利用多时相Landsat 近红外波段监测冬小麦和苜蓿种植面积 [J]. 农业工程学报, 2005, 21( 2): 96-101. [LI C J, WANG J H, LIU L Y, et al. Land cover mapping of winter wheat and clover using muti-temporal Landsat NIR band in a growing season. Transactions of the CSAE, 2005, 21(2): 96-101. ]
[7] 李鑫川, 徐新刚, 王纪华, 等. 基于时间序列环境卫星影像的作物分类识别 [J]. 农业工程学报, 2013, 29(2):169-176. [LI X C, XU X G, WANG J H, et al. Crop classification recognition based on time-series images from HJ satellite. Tran-sactions of the CSAE, 2013, 29(2): 169-176. ]
[8] 赵英时. 遥感应用分析原理与方法 [M]. 北京: 科学出版社, 2003. [ZHAO Y S. Application of the Principles and Methods of Remote Sensing. Beijing: Science Press, 2003. ]
[9] 邬明权, 王长耀, 牛铮. 利用多源时序遥感数据提取大范围水稻种植面积 [J]. 农业工程学报, 2010, 26(7): 240-244. [WU M Q, WANG C Y, NIU Z. Mapping paddy fields in large areas, based on time series multi-sensors data. Transactions of the CSAE, 2010, 26(7): 240-244. ]
[10] 冯锐, 张玉书, 钱永兰, 等. 基于多时相MODIS 数据的东北地区一季稻面积提取 [J]. 生态学杂志, 2011, 30(11): 2570-2576. [FENG R, ZHANG Y S, QIAN Y L, et al. Extraction of single cropping rice area in Northeast China based on multi-temporal MODIS data. Chinese Journal of Ecology, 2011, 30(11): 2570-2576. ]
[11] GUSSO A, FORMAGGIO A R, RIZZI R, et al. Soybean crop area estimation by MODIS/EVI data [J]. Pesquisa Agropecuaria Brasileira, 2012, 47(3): 425-435.
[12] JIA K, LIANG S L, WEI X Q, et al. Land cover classification of Landsat data with phonological features extracted from time series MODIS NDVI data [J]. Remote Sensing, 2014, 6: 11518-11532.
[13] 竺可桢, 宛敏渭. 物候学 [M]. 长沙: 湖南教育出版社, 1999. [ZHU K Z, WAN M W. Phenology. Changsha: Hunan Education Press, 1999. ]
[14] LIETH H. Phenology and Seasonality Modeling [M]. New York: Springer-Verlag, 1974.
[15] 中华人民共和国农业部种植业管理司. http://202.127.42.157/moazzys/nongshi.aspx [EB/OL]. [The People's Republic of China Ministry of Agriculture Planting Industry Management. http://202.127.42.157/moazzys/nongshi.aspx. ]
[16] 陈健, 刘云慧, 宇振荣. 基于时序MODIS-EVI 数据的冬小麦种植信息提取 [J]. 中国农学通报, 2011, 27(1): 446-450. [CHEN J, LIU Y H, YU Z R. Planting information extraction of winter wheat based on the time-series MODIS-EVI. Chinese Agricultural Science Bulletin, 2011, 27(1): 446-450. ]
[17] 陈颖姝, 张晓春, 王修贵, 等. 基于Landsat 8 OLI与MODIS数据的洪涝季节作物种植结构提取 [J]. 农业工程学报, 2014, 30(21): 165-173. [CHEN Y S, ZHANG X C, WANG X G, et al. Based on Landsat 8 OLI flood season crop planting structure with MODIS data extraction. Transactions of the CSAE, 2014, 30(21): 165-173. ]
[18] 潘耀忠, 李乐, 张锦水, 等. 基于典型物候特征的MODIS-EVI时间序列数据农作物种植面积提取方法 小区域冬小麦实验研究 [J]. 遥感学报, 2011, 15(3): 578-594. [PAN Y Z, LI Y, ZHANG J S, et al. Crop area estimation based on MODIS-EVI time series according to distinct characteristics of key phenology phases: A case study of winter wheat area estimation in small scale area. Journal of Remote Sensing, 2011, 15(3): 578-594. ]
[19] 黄青, 唐华俊, 周清波, 等. 东北地区主要作物种植结构遥感提取及长势监测 [J]. 农业工程学报, 2010, 26(9): 218-223. [HUANG Q, TANG H J, ZHOU Q B, et al. Remote-sensing based monitoring of planting structure and growth condition of major crops in Northeast China. Transactions of the CSAE, 2010, 26(9): 218-223. ]
[20] ESTEL S, KUEMMERLE T, ALCÁNTARA C, et al. Mapping farmland abandonment and recultivation across Europe using MODIS NDVI time series [J]. Remote Sensing of Environment, 2015, 163: 312-325.
[21] MURAKAMI T, OGAWA S, ISHITSUKA N, et al. Crop discrimination with multitemporal SPOT/HRV data in the Saga Plains, Japan [J]. International Journal of Remote Sensing, 2001, 22(7): 1335-1348.
[22] DAMIEN A, MILTON J, SIMOES M, et al. Classification of MODIS EVI time series for crop mapping in the state of Mato Grosso, Brazil [J]. International Journal of Remote Sensing, 2011, 32(22): 7847-7871.
[23] 那晓东, 张树清, 李晓峰, 等. MODIS NDVI时间序列在三江平原湿地植被信息提取中的应用 [J]. 湿地科学, 2007, 5(3): 227-236. [NA X D, ZHANG S Q, LI X F, et al. Application of MODIS NDVI in series to extracting wetland vegetation information in the Sanjiang Plain. Wetland Science, 2007, 5(3): 227-236. ]
[24] 熊勤学, 黄敬峰. 利用NDVI 指数时序特征监测秋收作物种植面积 [J]. 农业工程学报, 2009, 25(1): 144-148. [XIONG Q X, HUANG J F. Estimation of autumn harvest crop planting area based on NDVI sequential characteristics. Transactions of the CSAE, 2009, 25(1): 144-148. ]
[25] XIAO X, BOLES S, LIU J, et al. Mapping paddy rice agriculture in southern China using multi-temporal MODIS images [J]. Remote Sensing of Environment, 2005, 95: 480-492.
[26] 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: 1096-1116.
[27] ALCANTARA C, KUEMMERLE T, PRISHCHEPOV A V, et al. Mapping abandoned agriculture with multitemporal MODIS satellite data [J]. Remote Sensing of Environment, 2012, 124: 334-347.
[28] MCFEETERS S K. The use of normalized difference water index (NDWI) in the delineation of open water features [J]. International Journal of Remote Sensing, 1996, 17(7): 1425-1432.
[29] 孔凡明, 蒋卫国, 李京, 等. 基于MODIS的2011年泰国洪涝受灾信息提取与分析 [J]. 灾害学, 2013, 28(2): 95-99. [KONG F M, JIANG W G, LI J, et al. Extraction and analysis of Thailand flood affected region in 2011 based on MODIS data. Journal of Catastrophology, 2013, 28(2): 95-99. ]
[30] 刘兴土. 松嫩平原退化土地整治与农业发展 [M]. 北京: 科学出版社, 2001. [LIU X T. Management on degraded Land and Agricultural Development in the Songnen Plain. Beijing: Science Press, 2001. ]
[31] 郝卫平, 梅旭荣, 蔡学良, 等. 基于多时相遥感影像的东北三省作物分布信息提取 [J]. 农业工程学报, 2011, 27(1): 201-207. [HAO W P, MEI X R, CAI X L, et al. Crop planting extraction based on multi-temporal remote sensing data in Northeast China. Transactions of the CSAE, 2011, 27(1): 201-207.]
[32] 丁潇. 黑龙江省农作物种植结构布局研究 [D]. 哈尔滨: 东北农业大学资源与环境学院, 2014. [DING X. Study on Distribution of Crop's Structure in Heilongjiang. Harbin: College of Resources and Environment, Northeast Agricultural University, 2014. ]
[33] TANRÉ D, HOLBEN B N, KAUFMAN Y J. Atmospheric correction algorithm for NOAA AVHRR products: Theory and application [J]. IEEE Transactions on Geoscience and Remote Sensing, 1992, 30: 231-248.
[34] SIMPSON J J, STITT J R. A procedure for the detection and removal of cloud shadow from AVHRR data over land [J]. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36: 880-897.
[35] EKLUNDH L, JÖNSSON P. Timesat 3.0 Software Manual [M]. Lund University, Sweden, 2009.
[36] JONSSON P, E KLUNDH L. Timesat A program for analyzing time-series of satellite sensor data [J]. Computers & Geosciences, 2004, 30: 833-845.
[37] 吴文斌, 杨鹏, 唐华俊, 等. 过去20年中国耕地生长季起始期的时空变化 [J]. 生态学报, 2009, 29(4): 1777-1786. [WU W B, YANG P, TANG H J, et al. Spatio-temporal variations in the starting dates of growing season in China's cropland over the past 20 years. Acta Ecologica Sinica, 2009, 29(4): 1777-1786. ]
[38] HIRD J N, MCDERMID G J. Noise reduction of NDVI time series: An empirical comparison of selected techniques [J]. Remote Sensing of Environment, 2009, 113: 248-258.
[39] BO-CAIG. NDWI A normalized difference water index for remote sensing of vegetation liquid water from space [J]. Remote Sensing of Environment, 1996, 58: 257-266.
[40] HUANG C, DAVIS L S, TOWNSHEND J R G. An assessment of support vector machines for land-cover classification [J]. International Journal of Remote Sensing, 2002, 23: 725-749.
Options
文章导航

/

〈 〉