[1]于天祥,樊红.基于Sentinel-2多时相遥感影像的冬小麦种植面积监测[J].江苏农业学报,2024,(09):1653-1661.[doi:doi:10.3969/j.issn.1000-4440.2024.09.009]
　YU Tianxiang,FAN Hong.Remote sensing monitoring of winter wheat planting area based on multi-temporal Sentinel-2 imagery[J].,2024,(09):1653-1661.[doi:doi:10.3969/j.issn.1000-4440.2024.09.009]
点击复制

基于Sentinel-2多时相遥感影像的冬小麦种植面积监测()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2024年09期
页码:
1653-1661
栏目:
农业信息工程
出版日期:
2024-09-30

文章信息/Info

Title:
Remote sensing monitoring of winter wheat planting area based on multi-temporal Sentinel-2 imagery
作者:
于天祥; 樊红
武汉大学测绘遥感信息工程国家重点实验室,湖北武汉430079)
Author(s):
YU Tianxiang; FAN Hong
(State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China)
关键词:
冬小麦分布图提取; 红边植被指数; Sentinel-2; 随机森林; 支持向量机
Keywords:
extraction of winter wheat distribution image; red-edged vegetation index; Sentinel-2; random forest; support vector machine
分类号:
TP79
DOI:
doi:10.3969/j.issn.1000-4440.2024.09.009
文献标志码:
A
摘要:
针对农业保险精准理赔对农作物真实种植面积的数据需求,提出1种快速有效提取冬小麦分布与种植面积的方法。以湖北省荆州市荆州区作为研究区,选取2019-2020年的Sentinel-2影像,计算多时相红边植被指数与黄度值,并将其作为特征用于优化分类模型,利用随机森林法、支持向量机算法提取冬小麦的分布图,对比分析不同方法的分类结果。结果表明,包括红边指数在内的多时相植被指数的加入可以有效提高小麦地块分类的完整度；相比于支持向量机,用随机森林法提取的小麦地块边界更清晰、完整且准确性更高；基于多时相特征的随机森林法分类结果的总精度、Kappa系数分别为 97.49%、0.968 6；不同分类方法提取的分类小麦面积与统计年鉴记录的小麦面积的比值为91.28%。由研究结果可以看出,归一化植被指数(NDVI)、归一化红边指数(NDre1)、新型倒红边叶绿素指数(IRECI)和黄度值是随机森林模型中重要性较高的分类特征。
Abstract:
Aiming at the data demand of the real planting area of crops in the accurate claims of agricultural insurance, a fast and efficient method for crop classification was proposed in this study. Taking Jingzhou District of Jingzhou City, Hubei province as the research area, Sentinel-2 images from 2019 to 2020 were selected to calculate multi-temporal red-edge vegetation index and yellowness value for feature optimization. Random forest and support vector machine algorithms were used to extract the distribution images of winter wheat. The results showed that adding multi-temporal vegetation index as a classification feature could effectively improve the integrity of wheat plot classification. Compared with support vetcor machine (SVM), the wheat boundary extracted by random forest was clearer, more complete and more accurate. The total accuracy and Kappa coefficient of the classification results of the random forest method based on multi-temporal features were 97.49% and 0.968 6, respectively. The ratio of the wheat area extracted by different classification methods to the wheat area recorded in the statistical yearbook was 91.28%. Normalized difference vegetation index (NDVI), normalized difference red-edge 1(NDre1), novel inverted red-edge chlorophyll index (IRECI) and yellowness value were the most important classification features in random forest models.

参考文献/References:

[1]潘力,夏浩铭,王瑞萌,等. 基于Google Earth Engine的淮河流域越冬作物种植面积制图[J]. 农业工程学报,2021,37(18):211-218.
[2]陈岳,寇卫利,李莹,等. 农作物遥感灾损评估研究进展[J]. 江苏农业科学,2022,50(16):12-20.
[3]吴炳方,范锦龙,田亦陈,等. 全国作物种植结构快速调查技术与应用[J]. 遥感学报,2004,8(6):618-627.
[4]DHUMAL R K, VIBHUTE A D, NAGNE A D, et al. Advances in classification of crops using remote sensing data[J]. International Journal of Advanced Remote Sensing and GIS,2015,4(1):1410-1418.
[5]史舟,梁宗正,杨媛媛,等. 农业遥感研究现状与展望[J]. 农业机械学报,2015,46(2):247-260.
[6]许青云,杨贵军,龙慧灵,等. 基于MODISNDVI多年时序数据的农作物种植识别[J]. 农业工程学报,2014,30(11):134-144.
[7]ZHANG M W, FAN J L, ZHU X X, et al. Monitoring winter-wheat phenology in North China using time-series MODIS EVI[C]//SPIE. SPIE Remote Sensing 2009. Zhangjiajie:SPIE,2009:232-242.
[8]CAI Y P, GUAN K Y, PENG J, et al. A high-performance and in-season classification system of field-level crop types using time-series Landsat data and a machine learning approach[J]. Remote Sensing of Environment,2018,210:35-47.
[9]谢登峰,张锦水,潘耀忠,等. Landsat 8和MODIS融合构建高时空分辨率数据识别秋粮作物[J]. 遥感学报,2015,19(5):791-805.
[10]王利军,郭燕,贺佳,等. 基于决策树和SVM的Sentinel-2A影像作物提取方法[J]. 农业机械学报,2018,49(9):146-153.
[11]JOHANN D, DINO I, ANTOINE B. Out-of-year corn yield prediction at field-scale using Sentinel-2 satellite imagery and machine learning methods[J]. Computers and Electronics in Agriculture,2023,209:107807.
[12]王志辉,易善桢. 不同指数模型法在水体遥感提取中的比较研究[J]. 科学技术与工程,2007,7(4):534-537.
[13]林建平,邓爱珍,朱青,等. 基于BP神经网络模型的南方离子型稀土矿区开采遥感监测研究[J]. 中国稀土学报,2022,40(2):339-350.
[14]李亚妮,曹建君,杨树文,等. 基于决策树的大尺度复杂地区夏收作物遥感提取与分析[J]. 江苏农业学报,2022,38(5):1257-1264.
[15]方灿莹,王琳,徐涵秋. 不同植被红边指数在城市草地健康判别中的对比研究[J]. 地球信息科学学报,2017,19(10):1382-1392.
[16]GITELSON A, MERZLYAK M N. Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. spectral features and relation to chlorophyll estimation[J]. Journal of Plant Physiology,1994,143(3):286-292.
[17]FRAMPTON W J, DASH J, WATMOUGH G, et al. Evaluating the capabilities of Sentinel-2 for quantitative estimation of biophysical variables in vegetation[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2013,82:83-92.
[18]龙亦凡,乔雯钰,孙静. 基于SVM的大屯矿区遥感影像变化检测[J]. 测绘与空间地理信息,2020,43(12):107-110,115.
[19]江远东,李新国,杨涵. 基于连续小波变换的表层土壤有机碳含量的高光谱估算[J]. 江苏农业学报,2023,39(1):118-125.
[20]路阳,杨化龙,陈宇,等. 基于TSDPSO-SVM的水稻稻瘟病图像识别[J]. 江苏农业科学,2022,50(23):164-170.
[21]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.
[22]黄靖舒,高心丹,景维鹏. 基于BOVW和SVM的城市土地类型遥感变化监测研究[J]. 南京林业大学学报(自然科学版),2023,47(3):37-44.

备注/Memo

备注/Memo:
收稿日期：2023-11-15作者简介：于天祥(2000-),男,内蒙古巴彦淖尔人,硕士研究生,主要从事农业遥感方面的研究。(E-mail)1224745953@qq.com通讯作者：樊红,(E-mail)hfan3@whu.edu.cn
更新日期/Last Update: 2024-11-17