基于改进植被指数的黄河口区盐渍土盐分遥感反演

陈红艳; 赵庚星; 陈敬春; 王瑞燕; 高明秀

doi:10.3969/j.issn.1002-6819.2015.05.016

基于改进植被指数的黄河口区盐渍土盐分遥感反演

1.
山东农业大学资源与环境学院/土肥资源高效利用国家工程实验室，泰安 271018
2.
山东省巨野县水务局，巨野 274900

基金项目: 国家自然科学基金（41401239，41271235）；山东省优秀中青年科学家科研奖励基金（BS2013NY004）；中国博士后科学基金（2014M561953）；"十二五"国家科技支撑计划项目课题（2013BAD05B06）。

计量
- 文章访问数: 2900
- HTML全文浏览量: 12
- PDF下载量: 2077
出版历程
- 收稿日期: 2014-12-24
- 修回日期: 2015-02-04
- 发布日期: 2015-02-28

Remote sensing inversion of saline soil salinity based on modified vegetation index in estuary area of Yellow River

1.
National Engineering Laboratory for Efficient Utilization of Soil and Fertilizer Resources, College of Resources and Environment, Shandong Agricultural University, Taian 271018, China
2.
Hydrological Bureau of Juye County, Juye 274900, China

摘要

摘要: 快速获取土壤盐分的含量、特征及空间分布信息是盐渍土治理、利用的客观需求。该文针对黄河三角洲盐渍土，以垦利县为例，基于Landsat 8 OLI 多光谱影像，在传统植被指数的基础上引入短波红外波段进行扩展，提出了改进植被指数；然后基于改进前后对应的植被指数，分别采用多元逐步回归（multivariable linear regression，MLR）、反向传播神经网络（back propagation neural networks，BPNN）和支持向量机（support vector machine，SVM）方法构建土壤盐分含量的遥感反演模型，并进行模型验证、对比和优选；最后基于最佳模型进行研究区土壤盐分含量的空间分布反演和分析。结果显示：相对传统植被指数，扩展后植被指数可增强与土壤盐分的相关性，大幅降低指数间的多重共线性；采用上述3种方法建模，改进后模型的精度比改进前都有提高，验证集决定系数R2提高0.04～0.10，均方根误差RMSE降低0.13～0.73，相对分析误差RPD提高0.25～0.34，改进后模型RPD均大于2.0，普遍达到性能良好；对比3种建模方法，SVM建模精度最高，BPNN模型次之，MLR分析精度最低，最佳模型为基于改进植被指数的土壤盐分含量支持向量机反演模型，建模集R2和RMSE为0.75、3.48，验证集R2、RMSE和RPD为0.78、3.02和2.56，模型较为准确、可靠；基于该模型反演的研究区土壤盐分含量整体较高，盐渍化程度空间分布表现为自西南部农业生产区至东北沿海区域逐渐加重，与实地调查一致。研究表明基于Landsat 8 OLI多光谱影像，引入第7波段对植被指数进行改进，从而构建土壤盐分含量的支持向量机模型，可获得较好的土壤盐分空间分布反演结果。
- 土壤 /
- 盐分 /
- 遥感 /
- 支持向量机 /
- 植被指数 /
- 反演 /
- 黄河口
Abstract: Abstract: Fast acquisition of the soil salt content, characteristics, and spatial distributing are the objective needs of saline soil management and utilization. This paper focused on the saline soil on the Yellow River Delta, and took Kenli County as an example. Based on the multi-spectral remote sensing image of Landsat 8 OLI, the traditional vegetation index (VI) was extended by adding the short-wave infrared band, and the modified vegetation index (MVI) was put forward. Then, based on the corresponding VI and MVI, using multivariate stepwise regression (MLR), a back propagation neural network (BPNN), and the support vector machine (SVM) method respectively, the remote sensing inversion models of soil salinity were built, validated, and compared. Finally, the spatial distribution of soil salinity was analyzed using the best model in the study area. The results indicated that the correlation between the vegetation indices and soil salinity was heightened and the multicollinearity between vegetation indices was greatly reduced by extending the traditional vegetation index. Extended normalized difference vegetation index(ENDVI) and extended ratio vegetation index (ERVI) which were added band 7 were selected as the modified vegetation index(MVI). Using MLR, a BPNN and the SVM method, the precision of the models based on the MVI was improved compared to the VI with the calibration coefficient of determination (R2) raised between 0.05 and 0.11, and the calibration root mean squares error (RMSE) reduced between 0.09 and 0.55, the validation R2 raised between 0.04 and 0.10, the validation RMSE reduced between 0.13 and 0.73, and the validation relative prediction deviation (RPD) raised between 0.25 and 0.34. The models based on MVI obtained generally good performance with the validation RPD greater than 2.00. The main reasons improved the model precision were that the band 7 on Landsat 8 OLI had more information and the MVI including band 7 could more protrude the difference in vegetation coverage and production status. Comparing the three modeling methods, the SVM achieved the highest accuracy, the second was the BPNN, and the MLR analysis resulted in the lowest accuracy. With the calibration R2 and RMSE of 0.75 and 3.48, the validation R2, RMSE and RPD of 0.78, 3.02 and 2.56, the SVM model of soil salinity based on MVI was the best and obtained very high accuracy and reliability for remote sensing inversion of soil salinity content. The spatial distribution of soil salinity content in the study area was analyzed based on the best model. The statistical information of the inversed soil salinity was very close to the measured value of soil samples, the soil salinity content in the study area was very high generally, the area that belonged to severe saline soil and solonchak accounted for 77.91%, and the spatial distribution of soil salinization showed that the soil salinity content was gradually increased from the southwest agriculture region to the northeast coastal region, which was consistent with the field survey and geostatistical analysis. Therefore, the experiment indicated that the vegetation index was modified by introducing the band 7 based on Landsat 8 OLI, and the SVM model of soil salinity was built, which could obtain better inversion result of soil salinity spatial distribution.
- soils /
- salts /
- remote sensing /
- support vector machine /
- vegetation index /
- inversion /
- Yellow River estuary

HTML全文

参考文献(34)

[1]	Metternicht G, Zinck J A. Remote Sensing of Soil Salinization Impaction Land Management[M]. Boca Raton: CRC Press, 2009: 63.
[2]	Rengasamy P. Soil processes affecting crop production in salt-affected soils[J]. Functional Plant Biology, 2010, 37(7): 613－620.
[3]	丁建丽，伍漫春，刘海霞，等. 基于综合高光谱指数的区域土壤盐渍化监测研究[J]. 光谱学与光谱分析，2012，32(7)：1918－1922.Ding Jianli, Wu Manchun, Liu Haixia, et al. Study on the soil salinization monitoring based on synthetical hyperspectral index[J]. Spectroscopy and Spectral Analysis, 2012, 32(7): 1918－1922. (in Chinese with English abstract)
[4]	王静，刘湘南，黄方，等. 基于ANN技术和高光谱遥感的盐渍土盐分预测[J]. 农业工程学报，2009，25(12)：161－166.Wang Jing, Liu Xiangnan, Huang Fang, et al. Salinity forecasting of saline soil based on ANN and hyperspectral remote sensing[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2009, 25(12): 161－166. (in Chinese with English abstract)
[5]	Melendez-Pastor I, Hernández E I, Navarro-Pedre?o J, et al. Mapping soil salinization of agricultural coastal areas in Southeast Spain[J]. Remote Sensing Applications, 2012, 6(5): 117－140.
[6]	马驰. 松辽平原土地盐碱化监测机理及方法研究[D]. 长春：吉林大学，2011：6.Ma Chi. Study on Monitoring Mechanism and Method of Soil Salinization in Songliao Plain[D]. Changchun: Jilin University, 2011: 6. (in Chinese with English abstract)
[7]	Melendez-Pastor I, Navarro-Pedre?o J, Koch M, et al. Applying imaging spectroscopy techniques to map saline soils with ASTER images[J]. Geoderma, 2010, 158(1/2): 55－65.
[8]	Abbas A, Khan S, Hussain N, et al. Characterizing soil salinity in irrigated agriculture using a remote sensing approach[J]. Physics and Chemistry of the Earth, 2013, 55/56/57: 43－52.
[9]	Dehaan R L, Taylor G R. Image-derived spectral endmembers as indicators of salinisation[J]. International Journal of Remote Sensing, 2003, 24(4): 775－794.
[10]	王飞，丁建丽，伍漫春. 基于NDVI-SI特征空间的土壤盐渍化遥感模型[J]. 农业工程学报，2010，26(8)：168－174.Wang Fei, Ding Jianli, Wu Manchun. Remote sensing monitoring models of soil salinization based on NDVI-SI feature space[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2010, 26(8): 168－174. (in Chinese with English abstract)
[11]	范晓梅，刘高焕，唐志鹏，等. 黄河三角洲土壤盐渍化影响因素分析[J]. 水土保持学报，2010，24(1)：139－144.Fan Xiaomei, Liu Gaohuan, Tang Zhipeng, et al. Analysis on main contributors influencing soil salinzation of Yellow River Delta[J]. Journal of Soil and Water Conservation, 2010, 24(1): 139－144. (in Chinese with English abstract)
[12]	翁永玲，宫鹏. 土壤盐渍化遥感应用研究进展[J]. 地理科学，2006，26(3)：369－375.Weng Yongling, Gong Peng. A review on remote sensing technique for salt-affected soils[J]. Scientia GeoGraphica Snica, 2006, 26(3): 369－375. (in Chinese with English abstract)
[13]	扶卿华，倪绍祥，王世新，等. 土壤盐分含量的遥感反演研究[J]. 农业工程学报，2007，23(1)：48－54.Fu Qinghua, Ni Shaoxiang, Wang Shixin, et al. Retrieval of salt content based on remote sensing[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2007, 23(1): 48－54. (in Chinese with English abstract)
[14]	Dehni A, Lounis M. Remote sensing techniques for salt affected soils mapping: Application to the oran region of Algeria[J]. Procedia Engineering, 2012, 33(1): 188－198.
[15]	Farifeth J, Farshad A, George R J. Assessing salt-affected soils using remote sensing, solute modeling and geophysics[J]. Geoderma, 2006, 130(3/4): 191－206.
[16]	Bouaziz M, Matschullat J, Gloaguen R. Improved remote sensing detection of soil salinity from a semi-arid climate in Northeast Brazil[J]. C R Geoscience, 2011, 343(11): 795－803.
[17]	姚远，丁建丽，雷磊，等. 干湿季节下基于遥感和电磁感应技术的塔里木盆地北缘绿洲土壤盐分的空间变异性[J]. 生态学报，2013，33(17)：5308－5319．Yao Yuan, Ding Jianli, Lei Lei, et al. Monitoring spatial variability of soil salinity in drv and wet seasons in the North "farim Basin using remote sensing and electromagnetic induction instruments[J]. Acta Ecologica, 2013, 33(17): 5308－5319. (in Chinese with English abstract)
[18]	Jiang H N, Ding J L, Tashpolat·Titip, et al. Extraction of salinized soil information in arid area based on ETM+ data[J]. Acta Pedologica Sinica, 2008, 45(2): 222－228．
[19]	Mulder V L, Bruin S D, Schaepman M E, et al. The use of remote sensing in soil and terrain mapping: A review[J]. Geoderma, 2011, 162(1/2): 1－19.
[20]	陶金梅，范兴旺，翁永玲. 基于GRNN的ALI多光谱遥感数据土壤盐分反演研究[J]. 现代测绘，2012，35(6)：10－12.Tao Jinmei, Fan Xingwang, Weng Yongling. Soil salt content retrieval from ALI multispectral image based on GRNN[J]. Modern Surveying and Mapping, 2012, 35(6): 10－12. (in Chinese with English abstract)
[21]	杨佳佳，姜琦刚，赵静，等. 基于环境减灾卫星高光谱数据的盐碱地等级划分[J]. 农业工程学报，2011，27(10)：118－124.Yang Jiajia, Jiang Qigang, Zhao Jing, et al. Quantitative retrieval and classification of saline soil using HJ-lA hyperspectral data[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2011, 27(10): 118－124. (in Chinese with English abstract)
[22]	李百红，赵庚星，董超，等. 基于遥感和GIS的黄河三角洲盐化土地动态及其驱动力分析[J]. 自然资源学报，2011，26(2)：310－318.Li Baihong, Zhao Gengxing, DongChao, et al. Dynamic and drivng force analysis of salnized land in the Yellow River delta based on RS and GIS[J]. Journal of Natural Resources, 2011, 26(2): 310－318. (in Chinese with English abstract)
[23]	李新举，方玉东，田素锋，等. 黄河三角洲垦利县可持续土地利用障碍因素分析[J]. 农业工程学报，2007，23(7)：71－75.Li Xinju, Fang Yudong, Tian Sufeng, et al. Analysis of obstacle factors to sustainable land use of Kenli County in Yellow River Deltas[J]. Transactions of the Chinese Society of Agricultural Engineering, 2007, 23(7): 71－75. (in Chinese with English abstract)
[24]	刘娅，潘贤章，王昌昆，等. 基于可见-近红外光谱的滨海盐土土壤盐分预测方法[J]. 土壤学报，2012，49(4)：824－829.Liu Ya, Pan Xianzhang, Wang Changkun, et al. Prediction of coastal soil salinity based on VIS-NIR reflectance spectroscopy[J]. Acta Pedologica Sinica, 2012, 49(4), 824－829. (in Chinese with English abstract)
[25]	鲍士旦. 土壤农业化学分析[M]. 北京：中国农业出版社，2000：163-165，178－199.
[26]	陈斌，邹贤勇，朱文静. PCA结合马氏距离法剔除近红外异常样本[J]. 江苏大学学报：自然科学版，2008，29(4)：277－279.Chen Bin, Zou Xianyong, Zhu Wenjing. Eliminating outlier samples in near-infrared model by method of PCA-Mahalanobis distance[J]. Journal of Jiangsu University: Natural Science Edition, 2008, 29(4): 277－279. (in Chinese with English abstract)
[27]	Mouazen A M, Kuang B, Baerdemaeker J D, et al. Comparison among principal component, partial least squares and back propagation neural network analyses for accuracy of measurement of selected soil properties with visible and near infrared spectroscopy[J]. Geoderma, 2010, 158(1/2): 23－31.
[28]	张海云，彭彦昆，王伟，等. 基于光谱技术和支持向量机的生鲜猪肉水分含量快速无损检测[J]. 光谱学与光谱分析，2012，32(10)：2794－2798.Zhang Haiyun, Peng Yankun, Wang Wei, et al. Rapid nondestructive detection of water content in fresh pork based on spectroscopy technique combined with support vector machine[J]. Spectroscopy and Spectral Analysis, 2012, 32(10): 2794－2798.(in Chinese with English abstract)
[29]	Terhoeven-Urselmans T, Schmidt H, Joergensen R G, et al. Usefulness of near-infrared spectroscopy to determine biological and chemical soil properties: Importance of sample pre-treatment[J]. Soil Biology & Biochemistry, 2008, 40(5): 1178－1188.
[30]	USGS. Landsat Data Continuity Mission （LDCM）- Landsat 8 [J/OL]. [2013-04-18] http: // landsat. usgs. gov/ LDCM_Landsat 8. php.
[31]	徐涵秋，唐菲. 新一代Landsat系列卫星：Landsat8遥感影像新增特征及其生态环境意义[J]. 生态学报，2013，33(11)：3249－3257.Xu Hanqiu, Tang Fei. Analysis of new characteristics of the first Landsat 8 image and their eco-environmental significance[J]. Acta Ecologic Sinica, 2013, 33(11)：3249－3257. (in Chinese with English abstract)
[32]	Darvishzadeh R, Atzberger C, Skidmore A K. Leaf Area Index derivation from hyperspectral vegetation indices and the red edge position[J]. International Journal of Remote Sensing, 2009, 30(23): 6199－6218.
[33]	赖宁，李新国，梁东. 开都河流域下游绿洲盐渍化土壤高光谱特征[J]. 干旱区资源与环境，2015，29(2)：151－156.Lai Ning, Li Xinguo, Liang Dong. Spectral characteristics of salinized soil in the lower reaches of Kaidu river basin[J]. Journal of Arid Land Resources and Environment, 2015, 29(2): 151－156. (in Chinese with English abstract)
[34]	Weng Y L, Gong P, Zhu Z L. A spectra index for estimating soil salinity in the Yellow River Delta Region of China using EO-1 hyperion data[J]. Pedosphere, 2010, 20(3): 378－388.

施引文献

资源附件(0)

计量

文章访问数: 2900
HTML全文浏览量: 12
PDF下载量: 2077
被引次数: 0

基于改进植被指数的黄河口区盐渍土盐分遥感反演

计量

出版历程

Remote sensing inversion of saline soil salinity based on modified vegetation index in estuary area of Yellow River

计量

出版历程

目录