扫 描 看 全 文
引用
李俐，谢小曼，朱德海，蒋朝为，许佳薇.XXXX.去除土壤后向散射影响的SAR数据玉米留茬方式识别.遥感学报，XX（XX）： 1-14
LI Li，XIE Xiaoman，ZHU Dehai，JIANG Chaowei，XU Jiawei. XXXX. Recognition of corn stubble modes from SAR data without the influence of soil backscatter. National Remote Sensing Bulletin， XX（XX）：1-14
作物留茬覆盖作为保护性耕作的重要方式之一，快速、准确地获取其不同方式的分布情况对保护性耕作的实施现状监测及效果评估具有重要意义。现有的留茬监测方法主要集中于留茬覆盖度估算，而对不同留茬方式识别的研究较少。本文以Sentinel-1 SAR数据为主数据源，尝试探究其对玉米留茬方式的识别能力。利用留茬后向散射模型分离土壤散射贡献和留茬散射贡献，以消除土壤散射贡献干扰。提出融合留茬指数（Fusion residue index，FRI），结合雷达指数与SAR纹理，分析不同特征组合对留茬方式的识别能力。采用最优特征集进行玉米留茬方式的识别，完成实验区的不同玉米留茬方式制图。结果表明：采用消除土壤影响后的VH极化后向散射系数、FRI和SAR纹理等8个特征的识别表现最好，OA和Kappa系数分别为89.28%、0.84。相比采用消除土壤散射影响前，识别精度和Kappa系数提高了5.44%和0.09。研究结果为Sentinel-1 SAR 影像在留茬研究的广泛应用提供一种新的思路。
Crop stubble cover is one of the important ways of conservation tillage. Obtaining the distribution of different corn stubble cover modes quickly and accurately is of great significance to the implementation status monitoring and effect evaluation of conservation tillage. Due to its characteristics of all-weather, all-weather, and strong penetration, microwave remote sensing can not only ensure the acquisition of data in a short period for stubble monitoring, but also be sensitive to the information of surface roughness and crop residue structure, which provides rich information for the identification of stubble modes. Though there are some research considering the stubble monitoring with microwave data, they mainly focus on the estimation of stubble coverage, and there are few studies on the identification of different stubble modes. In addition, the microwave backscattering coefficient is affected by many factors, such as soil moisture, soil roughness and so on. So, the accuracy using microwave data simply to monitor stubble is limited.In this paper, using Sentinel-1 SAR data as the main data source，an identification method for corn stubble modes by removing soil backscatter is proposed. Based on the autumn field sample data in 2019 in Lishu County, Jilin Province, the backscattering model of the corn stubble is designed to separate the corn stubble scattering contribution from the soil scattering contribution and to reduce the interference of soil scattering contribution on the identification of the corn stubble modes. A new fusion radar index (FRI) which is produced with Sentinel-1 SAR data and Sentinel-2 optical image, combining with traditional common-used SAR features such as radar index and SAR textures, is used to analyze the backscattering coefficient characteristic of field surface with different stubble modes. With the analysis of identification ability, the best feature combination for stubble recognition is selected. Using the optimal feature set selected, a convolution neural network model based on 1D CNN is constructed to identify the corn stubble modes. And the corn stubble modes are mapped for the study area. The results showed that: (1) The overall accuracy of stubble identification is above 83% based on VH polarized data, FRI, GLCM1~GLCM6 with backscattering values, which proves that the feature set gotten from Sentinel-1 radar scattering characteristics is feasible and effective for identification of the corn stubble modes. (2) The identification performance of the corn stubble modes based on data removing the soil backscatter contribution improves significantly. The OA and Kappa coefficients are 89.28% and 0.84, respectively. Compared with that before removing the influence of soil scattering, the recognition accuracy and Kappa coefficient are improved by 5.44% and 0.09. Therefore, separating the soil scattering contribution from the total scattering contribution based on the stubble radar backscattering model can effectively reduce the influence of soil factors on the monitoring of corn stubble and improve the accuracy of the corn stubble modes recognition.The study demonstrates the great potential of Sentinel-1 SAR data and backscattering models to access the distribution map of corn stubble modes and provides a new idea for the wide application of Sentinel-1 SAR image in the research of corn stubble.
Sentinel-1 SAR数据玉米留茬留茬方式识别后向散射模型最优特征集
Sentinel-1 SAR datacorn stubblerecognition of stubble modesbackscatter modeloptimal feature set
Adams J R, Berg A A, McNairn H and Merzouki A. 2013. Sensitivity of C-band SAR polarimetric variables to unvegetated agricultural fields. Canadian Journal of Remote Sensing, 39(1): 1-16[DOI: 10.5589/m13-003http://dx.doi.org/10.5589/m13-003]
Bouvet A, Mermoz S, Toan T L, Villard L , Mathieu R ， Naidoo L and Asner GP. 2018. An above-ground biomass map of african savannahs and woodlands at 25m resolution derived from alos palsar. Remote Sensing of Environment, (206): 156-173[DOI:10.1016/j.rse.2017.12.030http://dx.doi.org/10.1016/j.rse.2017.12.030]
Cai W, Zhao S, Wang Y, Peng F, Heo J and Duan Z. 2019. Estimation of winter wheat residue coverage using optical and SAR remote sensing images. Remote Sensing, 11(10): 1163[DOI: 10.3390/rs11101163http://dx.doi.org/10.3390/rs11101163]
Daughtry C S T, Hunt E R Jr and McMurtrey J E III. 2004. Assessing crop residue cover using shortwave infrared reflectance. Remote Sensing of Environment, 90(1): 126–134 [DOI: 10.1016/j.rse.2003.10.023http://dx.doi.org/10.1016/j.rse.2003.10.023]
Ding Y L, Zhang H Y, Wang Z Q, Xie Q Y, Wang Y Q, Liu L and Hall C C. 2020. A Comparison of Estimating Crop Residue Cover from Sentinel-2 Data Using Empirical Regressions and Machine Learning Methods. Remote Sensing, 12(9), 1470–[DOI:10.3390/rs12091470http://dx.doi.org/10.3390/rs12091470]
Gelder B K, Kaleita A L and Cruse R M. 2009. Estimating Mean Field Residue Cover on Midwestern Soils Using Satellite Imagery. Agronomy Journal, 101(3): 635–643[DOI:http://dx.doi.org/10.2134/agronj2007.0249http://dx.doi.org/http://dx.doi.org/10.2134/agronj2007.0249]
Huang J Y, Liu Z, Wan W, Liu Z Y, Wang J Y and Wang S. 2020. Remote sensing retrieval of maize residue cover on soil heterogeneous background. Chinese Journal of Applied Ecology, 31(02): 474-482
黄晋宇, 刘忠, 万炜, 刘之榆, 王佳莹, 王思. 2020. 基于土壤异质背景的玉米秸秆覆盖度遥感反演. 应用生态学报, 31(02): 474-482[DOI: 10.13287/j.1001-9332.202002.012http://dx.doi.org/10.13287/j.1001-9332.202002.012]
Jin X, Ma J, Wen Z and Song K. 2015. Estimation of maize residue cover using Landsat-8 OLI image spectral information and textural features. Remote Sensing, 7(11): 14559-14575[DOI: 10.3390/rs71114559http://dx.doi.org/10.3390/rs71114559]
Kim Y H, Oh J H, Kim Y II. 2015. Development of a Fusion Vegetation Index Using Full-PolSAR and Multispectral Data. Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 33(6): 547-555[DOI: 10.7848/ksgpc.2015.33.6.547http://dx.doi.org/10.7848/ksgpc.2015.33.6.547]
Kong Q L, Li L, Xu K H and Zhu D H. 2017. Monitoring crop residue area in northeast of China based on Sentinel-1A data. Transactions of the Chinese Society for Agricultural Machinery, 48 (S1):284-289
孔庆玲, 李俐, 徐凯华, 朱德海. 2017. 基于Sentinel-1A的东北地区作物留茬区监测研究. 农业机械学报, 48(S1):284-289[DOI: 10.6041/j.issn.1000-1298.2017.S0.043http://dx.doi.org/10.6041/j.issn.1000-1298.2017.S0.043]
Li L, Wang D, Wang P X, Huang J X and Zhu D H. 2015. Soil surface roughness measurement based on color operation and chaotic particle swarm filtering. Transactions of the Chinese Society for Agricultural Machinery, 46(3): 158-165.
李俐,王荻,王鹏新,黄健熙,朱德海. 2015. 基于色彩运算和混沌粒子群滤波的土壤粗糙度测算. 农业机械学报, 46(03): 158-165[DOI: 10.6041/j.issn.1000-1298.2015.03.022http://dx.doi.org/10.6041/j.issn.1000-1298.2015.03.022]
Li S L, Li H P, Lin Y, Xiao B and Wang G P. 2019. Effects of tillage methods on wind erosion in farmland of northeastern china. Journal of Soil and Water Conservation, 33(4): 110-118,220
李胜龙, 李和平, 林艺, 肖波, 王国鹏. 2019. 东北地区不同耕作方式农田土壤风蚀特征. 水土保持学报, 33(4): 110-118,220[DOI: 10.13870/j.cnki.stbcxb.2019.04.016http://dx.doi.org/10.13870/j.cnki.stbcxb.2019.04.016]
Liu Z Y, Liu Z, Wan W, Huang J Y, Wang J Y, Zheng M D. 2020. Estimation of maize residue cover based on SAR and optical remote sensing image. Journal of Remote Sensing(Chinese): 1993-2002
刘之榆, 刘忠, 万炜, 黄晋宇, 王佳莹, 郑曼迪. 2020. 基于SAR与光学遥感影像的玉米秸秆覆盖度估算研究. 遥感学报: 1993-2002[DOI: 10.11834/jrs.20210053http://dx.doi.org/10.11834/jrs.20210053]
McNairn H, Duguay C, Brisco B and Pultz T. 2002. The effect of soil and crop residue characteristics on polarimetric radar response. Remote sensing of environment, 80(2): 308-320[DOI: 10.1016/S0034-4257(01)00312-1http://dx.doi.org/10.1016/S0034-4257(01)00312-1]
McNairn H, Wood D, Gwyn Q H J, Brown R J and Charbonneau F. 1998. Mapping tillage and crop residue management practices with RADARSAT. Canadian Journal of Remote Sensing, 24(1): 28-35[DOI: 10.1080/07038992.1998.10874688http://dx.doi.org/10.1080/07038992.1998.10874688]
Miguel Q and Craig D. 2016. Spectral indices to improve crop residue cover estimation under varying moisture conditions. Remote Sensing, 8(8): 660[DOI: 10.3390/rs8080660http://dx.doi.org/10.3390/rs8080660]
Niel T G, McVicar T R and Datt B. 2005. On the relationship between training sample size and data dimensionality: Monte Carlo analysis of broadband multi-temporal classification. Remote Sensing of Environment, 98(4): 468-480[DOI: 10.1016/j.rse.2005.08.011http://dx.doi.org/10.1016/j.rse.2005.08.011]
Quemada M, Hively W D, Daughtry C S T, Lamb B T and Shermeyer J. 2018. Improved crop residue cover estimates obtained by coupling spectral indices for residue and moisture. Remote Sensing of Environment, 206(), 33–44[DOI: 10.1016/j.rse.2017.12.012http://dx.doi.org/10.1016/j.rse.2017.12.012]
Saatchi S S and Moghaddam M. 2000. Estimation of crown and stem water content and biomass of boreal forest using polarimetric SAR imagery. IEEE Transactions on Geoscience and Remote Sensing, 38(2): 697–709[DOI: 10.1109/36.841999http://dx.doi.org/10.1109/36.841999]
Serbin G, Hunt E R, Daughtry C S T, McCarty G W and Doraiswamy P C. 2009. An improved ASTER index for remote sensing of crop residue. 510 Remote Sensing, 1(4): 971-991 [DOI:10.3390/rs1040971http://dx.doi.org/10.3390/rs1040971]
Smith A M and Major D J. 1996. Radar backscatter and crop residues. Canadian journal of remote sensing, 22(3): 243-247[DOI: 10.1080/07038992.1996.10855179http://dx.doi.org/10.1080/07038992.1996.10855179]
Tao L, Wang G, Chen W, Chen X, Li J and Cai Q. 2019. Soil moisture retrieval from SAR and optical data using a combined model. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(2): 637-647[DOI: 10.1109/JSTARS.2019.2891583http://dx.doi.org/10.1109/JSTARS.2019.2891583]
Van Deventer A P, Ward A D, Gowda P H and Lyon J G. 1997. Using Thematic Mapper data to identify contrasting soil plains and tillage practices. Photogrammetric Engineering and Remote Sensing, 1997, 63: 87–93.
Wang C J, Zhao Q Z, Ma Y J and Ren Y Y. 2019. Crop identification of drone remote sensing based on convolutional neural network. Transactions of the Chinese Society for Agricultural Machinery, 50(11): 161-168
汪传建, 赵庆展, 马永建, 任媛媛. 2019. 基于卷积神经网络的无人机遥感农作物分类. 农业机械学报, 50(11): 161-168[DOI: 10.6041/j.issn.1000-1298.2019.11.018http://dx.doi.org/10.6041/j.issn.1000-1298.2019.11.018]
Wang L H, JIN H H, WANG C C, SUN R X. 2019. Backscattering characteristics and texture information analysis of typical crops based on synthetic aperture radar: A case study of Nong'an County, Jilin Province. Chinese Journal of Eco-Agriculture, 27(9):1385-1393
王利花, 金辉虎, 王晨丞, 孙瑞悉. 2019. 基于合成孔径雷达的农作物后向散射 特性及纹理信息分析 ——以吉林省农安县为例. 中国生态农业学报（中英文）, 27(9):1385-1393 [DOI: 10.13930/j.cnki.cjea.190274http://dx.doi.org/10.13930/j.cnki.cjea.190274]
Wu T D, Chen K S, Shi J C and Fung A K. 1998. A transition model for the reflection coefficient in surface scattering. IEEE Transactions on Geoscience and Remote Sensing, 39(9): 2040-2050[DOI: 10.1109/36.951094http://dx.doi.org/10.1109/36.951094]
Yue J B and Tian Q J. 2020. Estimating fractional cover of crop, crop residue, and soil in cropland using broadband remote sensing data and machine learning. International Journal of Applied Earth Observation and Geoinformation, 89(), 102089[DOI: 10.1016/j.jag.2020.102089http://dx.doi.org/10.1016/j.jag.2020.102089]
Zhang M, Li Q Z, Meng J H and Wu B F. 2011. Review of crop residue fractional cover monitoring with remote sensing. Spectroscopy and Spectral Analysis, 31(12): 3200-3205
张淼, 李强子, 蒙继华, 吴炳方. 2011. 作物残茬覆盖度遥感监测研究进展. 31(12):3200-3205)[DOI: 10.3964/j.issn.1000-0593(201112-3200-06]
Zhang M, Meng J H, Dong T F, Wu B F and Sun H J. 2012. Spectral responses analysis of soybean residues. Journal of Remote Sensing(Chinese), 16(6):1115-1129
张淼, 蒙继华, 董泰锋, 吴炳方, 孙洪江. 2012. 大豆残茬光谱响应特征研究.遥感学报, 16(6):1115-1129[DOI: 10.11834/jrs.20121305http://dx.doi.org/10.11834/jrs.20121305]
Zhang W C, Liu H B, Wu W, Zhan L Q and Wei J. 2020. Mapping rice paddy based on machine learning with Sentinel-2 multi-temporal data: Model comparison and transferability. Remote Sensing, 12(10): 1620[DOI: 10.3390/rs12101620http://dx.doi.org/10.3390/rs12101620]
Zheng B J, Campbell J B, Serbin G and Galbraith J M. 2014. Remote sensing of crop residue and tillage practices: Present capabilities and future prospects. Soil and Tillage Research, 138: 26-34[DOI: 10.1016/j.still.2013.12.009http://dx.doi.org/10.1016/j.still.2013.12.009]
京公网安备11010802024621
