基于GF-1/WFV 时间序列的葡萄识别模型——以宁夏红寺堡区为例

doi:10.13866/j.azr.2019.03.13

摘要/Abstract

摘要： 以宁夏红寺堡区为研究区,基于高分一号(GF-1/WFV)卫星构建葡萄生长季时间序列光谱数据,运用(Jeffreys-Matusita)(J-M)距离分析葡萄地块归一化植被指数(NDVI)时序曲线特征确定了最佳识别时相,将最佳时相的NDVI、相邻时相差值速率和曲线积分训练样本集导入Clementine数据挖掘软件中,利用C5.0决策树分类算法,并结合专家经验法构建葡萄林决策树提取模型。结果表明:构建的识别模型能够满足葡萄的识别需求,但在不同覆盖度的葡萄地块上精度有所差异;基于决策树分类的总体精度为 93.71%,Kappa 系数为 0.91。其中,中低覆盖度葡萄林生产精度为90.82%,用户精度为88.56%;高覆盖度葡萄林生产精度为92.44%,用户精度为91.18%。

关键词: 葡萄林, 遥感提取, GF-1/WFV时序数据, 识别模型, 曲线积分, 决策树, 宁夏

Abstract: Grape is one of the most widely distributed fruit tree species,and its accurate spatial distribution is of great significance for the management and development of grape planting and wine industry.In this study,the Hongsibao in Ningxia was taken as the study area to obtain the time series of spectrum data in grape growing season based on the Gaofen-1 satellite (GF-1/WFV),the J-M distance analysis was used to analyze the normalized difference vegetation index (NDVI) of the grape plots,and the best recognition phase was determined.The NDVI values of the best phase,adjacent to the value difference rate and curvilinear integral training samples were put into the Clementine data mining software.The extract grape model of decision tree was developed by using C5.0 decision tree classification algorithm and combining with the expert experience method.The results suggested that the established recognition model could meet the needs of grape recognition,but the accuracy was different from different grape plots due to their different coverage.The overall accuracy based on the decision tree classification was 93.71%,and the Kappa coefficient was 0.91.In which the production precision and users' precision of the grape plots with moderate or low coverage were 90.82% and 88.56%,and those with high coverage were 92.44% and 91.18%,respectively.

Key words: grape forest, remote sensing extraction, GF-1/WFV timing data, recognition model, curve integral, decision tree, Ningxia

赵希妮, 王磊, 刘雅清, 璩向宁, 许兴, 王锐. 基于GF-1/WFV 时间序列的葡萄识别模型——以宁夏红寺堡区为例[J]. 干旱区研究, 2019, 36(3): 630-638.

ZHAO Xi-ni, WANG Lei, LIU Ya-qing, QU Xiang-ning, XU Xing, WANG Rui. Grape Recognition Model Based on GF-1/WFV Time Series: A Case Study in Hongsibu District of Ningxia[J]. Arid Zone Research, 2019, 36(3): 630-638.

参考文献

[1] 覃泽林,谢国雪,李宇翔,等.多时相高分一号影像在丘陵地区大宗农作物提取中的应用[J].南方农业学报,2017,48(1):181-188.
[Qin Zelin,Xie Guoxue,Li Yuxiang,et al.Application of multi-temporal GF-1 image in extraction of staple crops in hilly region[J].Guangxi Agricultural Sciences,2017,48(1):181-188.]
[2] 温胜强.贺兰山东麓葡萄酒产业发展研究——以红寺堡区为例[J].现代农业科技,2017(17):281-283,285.
[Wen Shengqiang.Wine industry development research in Eastern Helan Mountain area:A case study of Hongsibu District[J].Modern Agricultural Sciences and Technology,2017(17):281-283,285.]
[3] 黄健熙,贾世灵,武洪峰,等.基于GF-1 WFV影像的作物面积提取方法研究[J].农业机械学报,2015,46(增刊1):253-259.
[Huang Jianxi,Jia Shiling,Wu Hongfeng,et al.Extraction method of crop planted area based on GF-1 WFV image[J].Transactions of the Chinese Society for Agricultural Machinery,2015,46(Suppl.1):253-259.]
[4] 张赫林,彭代亮,邓睿,等.基于Landsat时间序列数据的祁连山区域土地利用变化[J].北京工业大学学报,2017,43(5):665-676.
[Zhang Helin,Peng Dailiang,Deng Rui,et al.Dynamic change of land use in Qilian Mountains based on time-series Landsat image[J].Journal of Beijing University of Technology,2017,43(5):665-676.]
[5] 梁守真,陈劲松,吴炳方,等.应用面向对象的决策树模型提取橡胶林信息[J].遥感学报,2015,19(3):485-494.
[Liang Shouzhen,Chen Jinsong,Wu Bingfang,et al.Extracting rubber plantation with decision tree model based on object-oriented method[J].Journal of Remote Sensing,2015,19(3):485-494.]
[6] 常布辉,王军涛,罗玉丽,等.河套灌区沈乌灌域GF-1/WFV遥感耕地提取[J].农业工程学报,2017,33(23):188-195.
[Chang Buhui,Wang Juntao,Luo Yuli,et al.Cultivated land extraction based on GF-1/WFV remote sensing in Shenwu irrigation area of Hetao Irrigation District[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(23):188-195.]
[7] 潘琛,杜培军,罗艳,等.一种基于植被指数的遥感影像决策树分类方法[J].计算机应用,2009,29(3):777-780.
[Pan Chen,Du Peijun,Luo Yan,et al.Decision tree classification of remote sensing images based on vegetation indices[J].Jouranl of Computer Application,2009,29(3):777-780.]
[8] 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.
[9] 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):169-176,298.
[Li Xinchuan,Xu Xingang,Wang Jihua,et al.Crop classification recognition based on time-series images from HJ satellite[J].Transactions of the Chinese Society of Agricultural Engineering,2013,29(2):169-176,298.]
[10] 杨闫君,占玉林,田庆久,等.利用时序数据构建冬小麦识别矢量分析模型[J].遥感信息,2016,31(5):53-59.
[Yang Yanjun,Zhan Yulin,Tian Qingjiu,et al.Vector analysis model of winter wheat identification using NDVI time series[J].Remote Sensing Information,2016,31(5):53-59.]
[11] 刘吉凯,钟仕全,陈玉兰,等.基于卫星遥感数据的库尔勒香梨识别提取方法研究[J].科学技术与工程,2014,14(26):190-196.
[Liu Jikai,Zhong Shiquan,Chen Yulan,et al.Study on extracting method of Korla pear information based on satellite remote sensing data[J].Science Technology and Engineering,2014,14(26):190-196.]
[12] 王玉,付梅臣,王力,等.基于多源高分卫星影像的果棉套种信息提取[J].国土资源遥感,2017,29(2):152-159.
[Wang Yu,Fu Meichen,Wang Li,et al.Tree-cotton intercropping land extraction based on multi-source high resolution satellite imagery[J].Remote Sensing for Land ＆ Resources,2017,29(2):152-159.]
[13] 田野,张清,李希灿,等.基于多时相影像的棉花种植信息提取方法研究[J].干旱区研究,2017,34(2):423-430.
[Tian Ye,Zhang Qing,Li Xican,et al.Extraction method of cotton plantation information based on multi-temporal images[J].Arid Zone Research,2017,34(2):423-430.]
[14] 王中挺,辛金元,贾松林,等.利用暗目标法从高分一号卫星16 m相机数据反演气溶胶光学厚度[J].遥感学报,2015,19(3):530-538.
[Wang Zhongting,Xin Jinyuan,Jia Songlin,et al.Retrieval of AOD from GF-1 16 m camera via DDV algorithm[J].Journal of Remote Sensing,2015,19(3):530-538.]
[15] 郭燕,武喜红,程永政,等.用高分一号数据提取玉米面积及精度分析[J].遥感信息,2015,30(6):31-36.
[Guo Yan,Wu Xihong,Cheng Yongzheng,et al.Maize recognition and accuracy evaluation based on high resolution remote sensing (GF-1)Data[J].Remote Sensing Information,2015,30(6):31-36.]
[16] 白照广.高分一号卫星的技术特点[J].中国航天,2013(8):5-9.
[Bai Zhaoguang.Technical features of GF-1 satellite[J].Aerospace China,2013(8):5-9.]
[17] 杨新国,宋乃平.宁夏红寺堡扬黄灌区土壤沙化和盐渍化及其相互关系[J].应用生态学报,2011,22(9):2265-2271.
[Yang Xinguo,Song Naiping.Soil sandy desertification and salinization and their interrelationships in Yanghuang irrigated area of Hongsipu,Ningxia of Northwest China[J].Chinese Journal of Applied Ecology,2011,22(9):2265-2271.]
[18] 李昀霏,李陇堂.红寺堡地区葡萄酒旅游发展研究[J].北方园艺,2016(10):170-174.
[Li Yunfei,Li Longtang.Study on the development of wine tourism in Hongsibu[J].Northern Horticulture,2016(10):170-174.]
[19] 王志强,张敬国,郝志强,等.葡萄埋藤防寒机的研制与试验[J].中国农机化学报,2015,36(5):20-23.
[Wang Zhiqiang ,Zhang Jingguo,Hao Zhiqiang,et al.Development and experiment of grape vine burying machine[J].Chinese Agricul Tural Mechanization,2015,36(5):20-23.]
[20] 马丽,徐新刚,刘良云,等.基于多时相NDVI及特征波段的作物分类研究[J].遥感技术与应用,2008,23(5):520-524.
[Ma Li,Xu Xingang,Liu Liangyun,et al.Study on crops classification based on multi-temporal NDVI and characteristic bands[J].Remote Sensing Technology and Application,2008,23(5):520-524.]
[21] 李梦莹,胡勇,王征禹.基于C5.0决策树和时序HJ-1A/B CCD数据的神农架林区植被分类[J].长江流域资源与环境,2016,25(7):1070-1077.
[Li Mengying,Hu Yong,Wang Zhengyu.Study on vegetation classfication in Shennongjia forest district based on C5.0 decision tree and HJ-1A/B data[J].Resources and Environment in the Yangtze Basin,2016,25(7):1070-1077.]
[22] 姜洋,李艳.浙江省森林信息提取及其变化的空间分布[J].生态学报,2014,34(24):7261-7270.
[Jiang Yang,Li Yan.The extraction of forest information and the spatial distribution of its change in Zhejiang Province[J].Acta Ecologica Sinica,2014,34(24):7261-7270.]
[23] 刘娇,黄显峰,方国华,等.基于GIS缓冲区功能的塔里木河中游植被指数时空变化分析[J].干旱区研究,2018,35(1):171-180.
[Liu Jiao,Huang Xianfeng,Fang Guohua,et al.Spatiotemporal variation of NDVI in the middle reaches of the Tarim River based on GIS buffer function[J].Arid Zone Research,2018,35(1):171-180.]
[24] 柳文杰,曾永年,张猛.融合时间序列环境卫星数据与物候特征的水稻种植区提取[J].遥感学报,2018,22(3):381-391.
[Liu Wenjie,Zeng Yongnian,Zhang Meng.Mapping rice paddy distribution by using time series HJ blend data and phonological parameters [J].Journal of Remote Sensing,2018,22(3):381-391.]
[25] 马娜,胡云锋,庄大方,等.基于最佳波段指数和J-M距离可分性的高光谱数据最佳波段组合选取研究——以环境小卫星高光谱数据在东莞市的应用为例[J].遥感技术与应用,2010,25(3):358-365.
[Ma Na,Hu Yunfeng,Zhuang Dafang,et al.Determination on the optimum band combination of HJ-1A hyperspectral data in the case region of Dongguan based on optimum index factor and J-M distance[J].Remote Sensing Technology and Application,2010,25(3):358-365.]
[26] 王龑,田庆久,黄彦,等.基于HJ星CCD遥感数据的落叶阔叶林NDVI差值速率识别模型[J].光谱学与光谱分析,2013,33(4):1018-1022.
[Wang Yan,Tian Qingjiu,Huang Yan,et al.NDVI difference rate recognition model of deciduous broad-leaved forest based on HJ-CCD remote sensing data[J].Spectroscopy and Spectral Analysis,2013,33(4):1018-1022.]
[27] 中国科学院遥感与数字地球研究所.一种基于NDVI时间序列曲线积分的冬小麦提取方法:中国,CN201510401405.0[P].2015-09-30.
[Institute of remote sensing and digital earth,Chinese academy of sciences.Extraction method of winter wheat based on NDVI time series curve integral:China,CN201510401405.0[P].2015-09-30.]
[28] 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.
[Wen Xingping,Hu Guangdao,Yang Xiaofeng.Extracting information from ETM＋ image using C5.0 decision tree algorithm[J].Geography and Geo-Information Science,2007,23(6):26-29.]
[29] 齐红超,祁元,徐瑱.基于C5.0决策树算法的西北干旱区土地覆盖分类研究——以甘肃省武威市为例[J].遥感技术与应用,2009,24(5):648-653,553.
[Qi Hongchao,Qi Yuan,Xu Zhen.The study of the Northwest arid zone land-cover classification based on C5.0 decision tree algorithm at Wuwei City,Gansu Province[J].Remote Sensing Technology and Application,2009,24(5):648-653,553.]
[30] 红寺堡区——葡萄产业[EB/OL].http://www.nxdofcom.gov.cn/zbzz/1938.jhtml,2015-06-03.
[Hongsipu District of Ningxia——Grape Industry[EB/OL].http://www.nxdofcom.gov.cn/zbzz/1938.jhtml,2015-06-03.]