[1]苏腾飞,刘全明,苏秀川.基于多种植被指数时间序列与机器学习的作物遥感分类研究[J].江苏农业科学,2017,45(16):219-224.
Su Tengfei,et al.Study on crop remote sensing classification based on multiple vegetation index time series and machine learning[J].Jiangsu Agricultural Sciences,2017,45(16):219-224.
点击复制
基于多种植被指数时间序列与机器学习的
作物遥感分类研究(PDF)
Su Tengfei,et al.Study on crop remote sensing classification based on multiple vegetation index time series and machine learning[J].Jiangsu Agricultural Sciences,2017,45(16):219-224.
作物遥感分类研究(PDF)
《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]
- 卷:
- 第45卷
- 期数:
- 2017年16期
- 页码:
- 219-224
- 栏目:
- 农业工程与信息技术
- 出版日期:
- 2017-08-20
文章信息/Info
- Title:
- Study on crop remote sensing classification based on multiple vegetation index time series and machine learning
- Author(s):
- Su Tengfei; et al
- Keywords:
- -
- 分类号:
- S127
- DOI:
- -
- 文献标志码:
- A
- 摘要:
- 开展了基于多种植被指数(vegetation index，VI)时间序列和机器学习(machine learning，ML)算法的作物遥感分类研究。从Landsat-8 OLI与EO-1 ALI影像中提取了内蒙古五原县的时间序列数据。2颗卫星的参数类似，且它们联合提供了更多无云覆盖的数据。7种常用的VI从时间序列遥感数据中提取出来，以用作ML算法的输入。对比分析了SVM、RF、DT 3种ML算法对玉米、向日葵和小麦的区分效果。共选取了2 584个样本，其中1 556个样本用于算法训练。得到了127种VI组合作为输入时3种算法的分类精度。结果表明，SVM的分类效果优于另外2种算法；VI数目并非越多越好，综合考虑算法的精度和稳定性，3种VI可以取得最佳的效果；SVM+NDI5+NDVI+TVI是平均分类精度最高的组合，平均精度为91.97%。
- Abstract:
- -
参考文献/References:
［1］田振坤，傅莺莺，刘素红，等. 基于无人机低空遥感的农作物快速分类方法［J］. 农业工程学报，2013，29(7)：109-116.
［2］游炯，裴志远，徐振宇，等. 水稻遥感识别偏差修正的地统计学方法［J］. 农业工程学报，2013，29(21)：126-136.
［3］刘晓娜，封志明，姜鲁光. 基于决策树分类的橡胶林地遥感识别［J］. 农业工程学报，2013，29(24)：163-172.
［4］Roy D P，Wulder M A，Loveland T R，et al. Landsat-8：science and product vision for terrestrial global change research［J］. Remote Sensing of Environment，2014，145(4)：154-172.
［5］Claverie M，Demarez V，Duchemin B，et al. Maize and sunflower biomass estimation in southwest France using high spatial and temporal resolution remote sensing data［J］. Remote Sensing of Environment，2012，124(9)：844-857.
［6］Duro D C，Franklin S E，Dubé M G. A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery［J］. Remote Sensing of Environment，2012，118(6)：259-272.
［7］Pea-Barragán J M，Ngugi M K，Plant R E，et al. Object-based crop identification using multiple vegetation indices，textural features and crop phenology［J］. Remote Sensing of Environment，2011，115(6)：1301-1316.
［8］Zhong L H，Gong P，Biging G S. Efficient corn and soybean mapping with temporal extendability：a multi-year experiment using Landsat imagery［J］. Remote Sensing of Environment，2014，140(1)：1-13.
［9］Brown J C，Kastens J H，Coutinho A C，et al. Classifying multiyear agricultural land use data from Mato Grosso using time-series MODIS vegetation index data［J］. Remote Sensing of Environment，2013，130(3)：39-50.
［10］Ozdogan M. The spatial distribution of crop types from MODIS data：temporal unmixing using independent component analysis［J］. Remote Sensing of Environment，2010，114(6)：1190-1204.
［11］Sakamoto T，Wardlow B D，Gitelson A A，et al. A Two-step filtering approach for detecting maize and soybean phenology with time-series MODIS data［J］. Remote Sensing of Environment，2010，114(10)：2146-2159.
［12］Yin H，Udelhoven T，Fensholt R，et al. How normalized difference vegetation index (NDVI) trends from advanced very high resolution radiometer (AVHRR) and systeme probatoire dobservation de la terre VEGETATION (SPOT VGT) time series differ in agricultural areas：an inner mongolian case study［J］. Remote Sensing，2012，4(11)：3364-3389.
［13］Conrad C，Fritsch S，Zeidler J A，et al. Per-Field irrigated crop classification in arid central Asia using SPOT and ASTER data［J］. Remote Sensing，2010，2(4)：1035-1056.
［14］Vieira M A，Formaggio A R，Rennó C D，et al. Object based image analysis and data mining applied to a remotely sensed Landsat time-series to map sugarcane over large areas［J］. Remote Sensing of Environment，2012，123(8)：553-562.
［15］Edlinger J，Conrad C，Lamers J P A，et al. Reconstructing the spatio-temporal development of irrigation systems in Uzbekistan using Landsat time series［J］. Remote Sensing，2012，4(12)：3972-3994.
［16］姜晓剑，刘小军，田永超，等. 基于遥感影像的作物生长监测系统的设计与实现［J］. 农业工程学报，2010，26(3)：156-162.
［17］范磊，程永政，王来刚，等. 基于多尺度分割的面向对象分类方法提取冬小麦种植面积［J］. 中国农业资源与区划，2010，31(6)：44-51.
［18］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(增刊2)：191-195.
［19］Gao Y，Masa J F，Maathuis B H P，et al. Comparison of pixel-based and object-oriented image classification approaches—a case study in a coal fire area，Wuda，Inner Mongolia，China［J］. International Journal of Remote Sensing，2006，27(18)：4039-4055.
［20］骆成凤，刘正军，王长耀，等. 基于遗传算法优化的BP神经网络遥感数据土地覆盖分类［J］. 农业工程学报，2006，22(12)：133-137，后插1.
［21］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)：273-280.
［22］Broge N H，Leblanc E. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density［J］. Remote Sensing of Environment，2001，76(2)：156-172.
［23］Mcnairn H，Protz R. Mapping corn residues cover on agricultural fields in Oxford County，Ontario，using thematic mapper［J］. Canadian Journal of Remote Sensing，1993，19(2)：152-159.
［24］Qi J，Marsett R，Heilman P，et al. RANGES improves satellite-based information and land cover assessments in southwest United States［J］. Eos Transactions of the American Geophysical Union，2002，83(51)：601-606.
［25］Hsu C，Chang C，Lin C. A practical guide to support vector classification［EB/OL］. (2010-04-15)［2016-04-02］. http：//www.csie.ntu.edu.tw/-cjlin.
［26］Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection［EB/OL］. (1995-06-15) ［2016-04-02］. http：//robotics.stanford.edu/-ronnyk.
相似文献/References:
[1]王思奇,陆亦农,于瑞德,等.新疆肖塘地区胡杨的种群结构与动态[J].江苏农业科学,2013,41(08):379.
Wang Siqi,et al.Population structure and dynamics of Populus euphratica in Xiaotang area of Xinjiang[J].Jiangsu Agricultural Sciences,2013,41(16):379.
[2]杨琳,高苹,居为民.基于MODIS NDVI数据的江苏省冬小麦物候期提取[J].江苏农业科学,2016,44(01):315.
Yang Lin,et al.Retrieval of winter wheat phenological period based on MODIS NDVI data in Jiangsu Province[J].Jiangsu Agricultural Sciences,2016,44(16):315.
[3]吴嘉惠,吴克宁,李晨曦,等.天津市各区(县)的土地利用经济效益及其发展类型[J].江苏农业科学,2017,45(16):327.
Wu Jiahui,et al.Regional economic benefits of land use and county development types in Tianjian City[J].Jiangsu Agricultural Sciences,2017,45(16):327.
[4]刁智华,魏玉泉,吴贝贝,等.基于图像的农业信息演变规律提取现状分析[J].江苏农业科学,2017,45(16):8.
Diao Zhihua,et al.Analysis on current situation of agricultural information evolution law based on image[J].Jiangsu Agricultural Sciences,2017,45(16):8.
[5]吴亚茜,肖向明,陈帮乾,等.近30年来盐城潮间带湿地盐沼植被物候遥感监测[J].江苏农业科学,2018,46(16):264.
Wu Yaqian,et al.Phenological remote sensing monitoring of salt marsh vegetation in Yancheng intertidal wetland in recent thirty years[J].Jiangsu Agricultural Sciences,2018,46(16):264.
[6]徐永金,黄纪心,苗珊珊.主产区、产销平衡区和主销区粮食产量影响因素的实证分析[J].江苏农业科学,2018,46(20):362.
Xu Yongjin,et al.Empirical analysis of factors influencing grain yield in main producing areas， producing and sale balance areas，and sale areas[J].Jiangsu Agricultural Sciences,2018,46(16):362.
[7]罗振军.农村金融发展与农村经济增长的关系——基于1978—2016年浙江省数据[J].江苏农业科学,2020,48(21):328.
Luo Zhenjun.Relationship between rural financial development and rural economic growth—Based on data from 1978 to 2016 in Zhejiang Province[J].Jiangsu Agricultural Sciences,2020,48(16):328.
[8]李环,孙素芬,罗长寿.基于NARX神经网络的粮食产量预测模型[J].江苏农业科学,2020,48(22):228.
Li huan,et al.Grain yield prediction model based on NARX neural network[J].Jiangsu Agricultural Sciences,2020,48(16):228.
[9]刘剑锋,方鹏,陈琳,等.基于MODIS NDVI的冬小麦收获指数遥感提取[J].江苏农业科学,2022,50(13):219.
Liu Jianfeng,et al.Remote sensing extraction of winter wheat harvest index based on MODIS NDVI[J].Jiangsu Agricultural Sciences,2022,50(16):219.
[10]王小飞,张方敏,任祖光,等.基于机器学习算法的河南省冬小麦面积提取研究[J].江苏农业科学,2024,52(6):215.
Wang Xiaofei,et al.Study on area extraction of winter wheat in Henan Province based on machine learning algorithm[J].Jiangsu Agricultural Sciences,2024,52(16):215.
备注/Memo
- 备注/Memo:
-
收稿日期：2016-04-03
基金项目：国家自然科学基金(编号：51569018)。
作者简介：苏腾飞(1987—)，男，内蒙古呼和浩特人，硕士，实验师，主要从事遥感影像分析算法的研究。E-mail：stf1987@126.com。
通信作者：刘全明，博士，副教授，主要从事遥感测绘方法与应用的研究。E-mail：nndlqm@sina.com。
常用功能
统计/Statistics
- 摘要浏览/Viewed1414
- 全文下载/Downloads817
- 评论/Comments
