Using Decision Tree Model to Extract Paddy Rice Information from Multi-temporal TM Images

  • 1. Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, China;
    2. State Key Laboratory of Resources and Environment Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China;
    3. School of Remote Sensing and Information Engineering,Wuhan University,Wuhan 7430079, China;
    4. Yantai Institute of Coastal Zone Research,CAS,Yantai 264003,China

Received date: 2012-12-26

  Revised date: 2013-03-11

  Online published: 2013-06-17


Remote sensing images have been widely used in extracting and studying paddy rice information and its spatial distribution, which is highly important in land cover analysis, grain structural adjustment and prices making. But studies using multi-temporal TM images to extract small-scale rice information were few. Based on that rice favors growing on wet land, this paper selected three bands of TM images, the short-wave infrared band (1.55-1.75um) which can reflect plant water content and soil moisture, the red band (0.62-0.69um) and the near infrared band (0.76-0.96um), both of which can reflect vegetation coverage and growing condition, to compute the NDVI and LSWI of rice paddles in the three different periods: transplanting stage, heading stage, and maturing stage. Given the two indices demonstrate different characteristics during rice's different growing stages, the paper developed a corresponding time-series-based decision tree model for rice information extraction. A case study using this model was performed in the southern Luannan County, Tangshan City. Been field validated, the experiment results showed the effectiveness of the decision model in distinguishing rice paddles from water area, corn land, farm land and other similar land features, and the producer accuracy and the user accuracy are 95.18% and 98.84%, which outperform the single-temporal results by 6.78% and 7.54% respectively.

Cite this article

SHU Liang, BENG Bo, SU Fen-Zhen, DU Yun-Yan, SU Wei-Guang . Using Decision Tree Model to Extract Paddy Rice Information from Multi-temporal TM Images[J]. Journal of Geo-information Science, 2013 , 15(3) : 446 -451 . DOI: 10.3724/SP.J.1047.2013.00446


[1] 赵锐,王延颐,戴锦芳.中国水稻遥感动态监测与估产[M].北京:中国科学技术出版社,1996.

[2] 方红亮.两种水稻种植面积遥感提取方案的分析[J].地理学报,1998,53(1):58-64.

[3] 黄晓军,何维,张云柏,等.利用TM卫星资料进行江苏部分地区小麦面积调查[J].江苏农业科学,2003(4):85-87.

[4] 许榕峰,徐涵秋.基于遥感的龙海市水田专题信息提取方法研究[J].国土资源遥感,2003,22(4):46-49.

[5] 郑长春,王秀珍,黄敬峰.基于特征波段的SPOT-5 卫星影像水稻面积信息自动提取的方法研究[J].遥感技术与应用,2008,23(3):294-299.

[6] 张峰,吴炳方,黄慧萍,等.泰国水稻种植区耕地信息提取研究[J].自然资源学报,2003,18(6):766-771.

[7] 汤传勇,卢远.利用面向对象的分类方法提取水稻种植面积[J].遥感应用,2010(1):53-56.

[8] 温兴平,胡光道,杨晓峰.基于C5.0 决策树分类算法的ETM+影像信息提取[J].地理与地理信息科学,2007,23(6):26-29.

[9] 吴健生,潘况一,彭建,等.基于QUEST决策树的遥感影像土地利用分类——以云南省丽江市为例[J].地理研究2012,31(11):1973-1980.

[10] 黄敬峰,王人潮,蒋亨显,等.基于GIS的浙江省水稻遥感估产最佳时相选择[J].应用生态学报,2002,13(3):290-294.

[11] 刘喜珍,李国靖,王立平,等.应用卫星遥感技术对水稻面积变化实施动态监测[J].中国稻米,2003(2):5-7.

[12] 苗翠翠,江南,彭世揆,等.基于NDVI 时序数据的水稻种植面积遥感监测分析——以江苏省为例[J].地球信息科学学报,2011,13(2):273-279.

[13] 王福民,黄敬峰,王秀珍.基于穗帽变换的TM影像水稻面积提取[J].中国水稻科学,2008,22(3):297-301.

[14] 杨学忠.河北省滦南县种植业布局现状调查与对策研究[J].农业网络信息,2011,26(5):41-43.

[15] Freid M A, Brodley C E. Decision tree classification ofland cover from remotely sensed data[J]. Remote Sensingof Environment,1997(61):399-409.

[16] 李爽,张二勋.基于决策树的遥感影像分类方法研究[J].地域研究与开发,2003,2(1):17-21.

[17] Conrad C, Colditz R R, Dech S, et al. Temporal segmentationof MODIS time series for improving crop classificationin Central Asian irrigation systems[J]. InternationalJournal of Remote Sensing, 2011, 32(23): 8763-8778.

[18] 林文鹏,王长耀,储德平,等.基于光谱特征分析的主要秋季作物类型提取研究[J]. 农业工程学报,2006,22(9):128-132.

[19] 于文颖,冯锐,纪瑞鹏,等.基于MODIS数据的水稻种植面积提取研究进展[J].气象与环境学报,2011,27(2):56-61.

[20] 郭亚鸽,于信芳,江东,等.面向对象的森林植被图像识别分类方法[J].地球信息科学学报,2012,14(4):514-522.

[21] Xiao X, Boles S, Frolking S, et al. Landscape-scale characterizationof cropland in China using vegetation andLandsat TM images[J]. International Journal of RemoteSensing, 2002, 23(18):3579-3594.

[22] Xiao X, Boles S, Frolking S, et al. Observation of floodingand rice transplanting of paddy rice fields at the siteto landscape scales in China using vegetation sensor data[J]. International Journal of Remote Sensing, 2002, 23(15):3009-3022.

[23] 吴健平,杨卫星.遥感数据监督分类中训练样本的纯化[J].国土资源遥感,1996(1):36-41.

[24] 朱秀芳,潘耀忠,张锦水,等.训练样本对TM 尺度小麦面积监测精度影响研究(I) [J]. 遥感学报,2007,11(6):827-836.