多源遥感数据特征优选的大兴安岭沿麓不同农作物提取

doi:10.12190/j.issn.2096-1197.2020.06.20

北方农业学报 ›› 2020, Vol. 48 ›› Issue (6): 119-128.doi: 10.12190/j.issn.2096-1197.2020.06.20

• 农业气象·农业信息技术 • 上一篇下一篇

多源遥感数据特征优选的大兴安岭沿麓不同农作物提取

于利峰^1,2, 乌兰吐雅^1,2, 李继辉³, 于伟卓¹, 敦惠霞¹

1.内蒙古自治区农牧业科学院农牧业经济与信息研究所,内蒙古呼和浩特 010031;
2.内蒙古自治区农业遥感工程技术研究中心,内蒙古呼和浩特 010031;
3.奈曼旗林业工作站,内蒙古大沁他拉镇 028300

收稿日期:2020-10-22 出版日期:2020-12-20 发布日期:2021-02-04
通讯作者: 乌兰吐雅(1976—),女,研究员,硕士,主要从事遥感与GIS应用的研究工作。敦惠霞(1962—),女,编审,学士,主要从事农业信息管理与期刊出版工作。
作者简介:于利峰(1994—),男,研究实习员,学士,主要从事农业遥感应用的研究工作。
基金资助:
内蒙古农牧业科学院青年创新基金项目(2020QNJJN04);内蒙古自治区科技重大专项(2020ZD0005)

Multi-source remote sensing data feature optimization for different crop extraction in Daxing′Anling along the foothills

YU Lifeng^1,2, Wulantuya^1,2, LI Jihui³, YU Weizhuo¹, DUN Huixia¹

1. Institute of Agricultural and Animal Husbandry Economy and Information,Inner Mongolia Academy of Agricultural and Animal Husbandry Sciences,Hohhot 010031,China;
2. Inner Mongolia Engineering and Technology Research Center for Agricultural Remote Sensing,Hohhot 010031,China;
3. Forestry Workstation of Naiman Banner,Daqintala Town 028300,China

Received:2020-10-22 Online:2020-12-20 Published:2021-02-04

摘要/Abstract

摘要： 【目的】以内蒙古呼伦贝尔市为研究区,采用多源遥感数据进行农作物提取,旨在为多云多雨条件下、跨气候带区域和高寒旱作农业区大尺度农作物提取应用提供解决方案。【方法】基于Google Earth Engine平台,采用以Sentinel-1和 Sentinel-2为主的多源遥感数据进行农作物提取。利用Boxcar滤波后Sentinel-1多极化数据构建时序数据集;获取Sentinel-2 TOA生长季数据,合成为最小云量影像并计算多种遥感指数特征;将地形因素和地表覆盖作为分类辅助数据,结合地面样本数据应用到随机森林分类器中,获取10 m精度的作物分布图,通过评估分类精度和分类贡献水平,将特征优选后的数据集用以提取研究区农作物分布,并分析农作物的分布特征。【结果】通过将雷达数据和光学数据进行组合(VV_B+VH_B+M+I+T+L)得到87.41%的农作物分类精度,比单独的组合(VV_B+VH_B、M+I+T+L)提取结果分别提高了7.58%和7.88%;使用500树的分类精度最高,当决策树的数量超过或不足500时,分类精度都有所下降,过多的决策树并没有提高分类器的性能;利用多源遥感数据特征波段重要性排名前24位组成的数据集提取的农作物总体精度为87.76%,Kappa系数为0.86。【结论】该研究结果获得了比较理想的农作物分布图,可实现常规业务化监测,能够为农作物遥感调查提供有效手段。

关键词: 多源遥感数据, 旱作农业区, 农作物制图, 机器学习

Abstract: 【Objective】Using multi-source remote sensing data for crop extraction in Hulun Buir of Inner Mongolia,it aimed to provide solutions for large-scale crop extraction applications under cloudy and rainy conditions,across climatic regions and alpine dry farming areas.【Methods】Based on the Google Earth Engine platform,and used Sentinel-1 and Sentinel-2 as the main source of multi-source remote sensing data. Using Boxcar filtered Sentinel-1 multi-polarization data to construct a time series data set,and acquire Sentinel-2 TOA growth season data and synthesized it into a minimum cloud cover image and calculate multiple remote sensing index features;using topographic factors and land cover as auxiliary data for classification,combined ground sample data and apply it to a random forest classifier to obtain a 10 m precision crop distribution map. By evaluating the classification accuracy and classification contribution level,the data set after feature optimization was used to extract the crop distribution in the study area,and analyze the distribution characteristics of crops.【Results】By combining radar data and optical data(VV_B+VH_B+M+I+T+L),87.41% of crop classification accuracy was obtained,which was higher than the extraction results of a separate combination(VV_B+VH_B,M+I+T+L)7.58% and 7.88%;500 trees classification had the highest accuracy,once the number of decision trees exceeds or less than 500,the classification accuracy decreased,and excessive decision trees did not improve the performance of the classifier;the overall accuracy of crops extracted from the data set composed of the top 24 important bands of multi-source remote sensing data was 87.76%,and the Kappa coefficient was 0.86.【Conclusion】The results of this study had obtained a relatively ideal crop distribution map,which could realize routine operational monitoring and provide effective means for crop remote sensing surveys.

Key words: Multi-source remote sensing data, Dry farming area, Crop mapping, Machine Learning

中图分类号:

TP79

于利峰, 乌兰吐雅, 李继辉, 于伟卓, 敦惠霞. 多源遥感数据特征优选的大兴安岭沿麓不同农作物提取[J]. 北方农业学报, 2020, 48(6): 119-128.

YU Lifeng, Wulantuya, LI Jihui, YU Weizhuo, DUN Huixia. Multi-source remote sensing data feature optimization for different crop extraction in Daxing′Anling along the foothills[J]. Journal of Northern Agriculture, 2020, 48(6): 119-128.

参考文献

[1] 李正国,杨鹏,周清波,等.基于时序植被指数的华北地区作物物候期/种植制度的时空格局特征[J].生态学报,2009,29(11):6216-6226.
[2] 朱再春,陈联裙,张锦水,等.MODIS EVI时间序列数据和光谱角聚类的冬小麦遥感估产分区方法研究[J].光谱学与光谱分析,2012,32(7):1899-1904.
[3] 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.
[4] 乌云德吉,于利峰,承昊,等.基于GF-1/WFV时间序列数据的河套灌区主要农作物识别[J].北方农业学报,2019,47(5):112-118.
[5] 何馨.基于多源数据融合的玉米种植面积遥感提取研究[D].南京:南京信息工程大学,2010.
[6] 史飞飞,雷春苗,肖建设,等.基于多源遥感数据的复杂地形区农作物分类[J].地理与地理信息科学,2018,34(5):49-55.
[7] 解毅,张永清,荀兰,等.基于多源遥感数据融合和LSTM算法的作物分类研究[J].农业工程学报,2019,35(15):129-137.
[8] 宋茜,周清波,吴文斌,等.农作物遥感识别中的多源数据融合研究进展[J].中国农业科学,2015,48(6):1122-1135.
[9] 董芳.基于多源数据的丘陵区苹果园地信息遥感提取技术研究[D].泰安:山东农业大学,2012.
[10] 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.
[11] 曾志康,覃泽林,黄启厅,等.基于国产高时空分辨率卫星影像的作物种植信息提取研究[J].福建农业学报,2017,32(5):560-567.
[12] 梁若飞.面向对象的遥感图像分割与玉米田面积统计方法研究[D].太原:中北大学,2016.
[13] 王利民,刘佳,杨福刚,等.基于GF-1卫星遥感的冬小麦面积早期识别[J].农业工程学报,2015,31(11):194-201.
[14] JIN Z,AZZARI G,YOU C,et al.Smallholder maize area and yield mapping at national scales with Google Earth Engine[J].Remote Sensing of Environment,2019,228:115-128.
[15] DONG J,XIAO X,MENARGUEZ M A,et al.Mapping paddy rice planting area in northeastern Asia with Landsat 8 images,phenology-based algorithm and Google Earth Engine[J].Remote Sensing of Environment,2016,185:142-154.
[16] 李宇宸,张军,薛宇飞,等.基于Google Earth Engine的中老缅交界区橡胶林分布遥感提取[J].农业工程学报,2020,36(8):174-181.
[17] SINGHA M,DONG J,ZHANG G,et al.High resolution paddy rice maps in cloud-prone Bangladesh and Northeast India using Sentinel-1 data[J].Scientific Data,2019,6(1):1-10.
[18] 潘志峰.内蒙古统计年鉴[M].北京:中国统计出版社,2019.
[19] LIN C,WU C C,TSOGT K,et al.Effects of atmospheric correction and pansharpening on LULC classification accuracy using WorldView-2 imagery[J].Information Processing in Agriculture,2015,2(1):25-36.
[20] 于利峰,乌兰吐雅,乌云德吉,等.基于纹理特征与MODIS-NDVI时间序列的耕地面积提取研究[J].中国农业资源与区划,2018,39(11):169-177.
[21] 朱闯,刘沁萍,田洪阵.2001-2017年中国土地利用时空变化[J].中国资源综合利用,2019,37(9):70-71.
[22] 于利峰,乌兰吐雅,乌兰,等.基于SAR-C的大兴安岭西麓地区主要农作物识别方法研究[J].北方农业学报,2017,45(3):108-113.
[23] 宋海平,卢战伟,赵松.Boxcar滤波器和极化Refined Lee滤波器对极化SAR分类精度影响的评估[J].影像技术,2011,23(5):39-44.
[24] 张华伟,王明文,甘丽新.基于随机森林的文本分类模型研究[J].山东大学学报(理学版),2006(3):139-143.
[25] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.

多源遥感数据特征优选的大兴安岭沿麓不同农作物提取

Multi-source remote sensing data feature optimization for different crop extraction in Daxing′Anling along the foothills

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

Metrics

本文评价

推荐阅读 0

[1]	崔志强. 赤峰市特色农业发展现状及措施[J]. 北方农业学报, 2014, (3): 129-129.
[2]	朱品松. 阜新市花生产业现状及发展对策[J]. 北方农业学报, 2010, (3): 78-78.
[3]	贾海波韩明玉. 乌兰察布市旱作农业区发展荞麦种植业的政策研究[J]. 北方农业学报, 2010, (2): 12-12.
[4]	王小宁田振荣蒲志斌张红. 宁南山区实施地膜覆盖栽培技术的优势及效益[J]. 北方农业学报, 2009, (4): 98-98.
[5]	邢杰. 内蒙古旱作农业区应加强对免耕和少耕技术的推广应用[J]. 北方农业学报, 2002, (2): 33-33.
[6]	臧健蔡桂芝王艳菊. 兴安盟旱作农业建设思路及技术途径[J]. 北方农业学报, 2001, (S3): 28-28.