小开河引黄灌区土壤盐渍化定量遥感反演

刘恩 王军涛 常布辉 王东琦

PDF(611 KB)
中国农村水利水电 ›› 2019 ›› (12) : 20-24.
农田水利

小开河引黄灌区土壤盐渍化定量遥感反演

  • 刘 恩1,2 ,王军涛1 ,常步辉1 ,王东琦1
作者信息 +

Quantitative Remote Sensing Inversion of Soil Salinization in Xiaokaihe Yellow River Irrigation District

  • LIU En1,2 ,WANG Jun-tao1 ,CHANG Bu-hui 1 ,WANG Dong-qi 1
Author information +
稿件信息 +

摘要

近年来黄河下游土地次生盐渍化呈现反复和逐渐加剧的态势,对农业生产和生态安全造成危害。本文以黄河三角洲小开河引黄灌区为研究区,基于野外实地调查的土壤盐分含量以及Landsat8 OLI多光谱影像,分析土壤样品的光谱曲线特征,利用诊断指数法选取诊断指数较大的波段反射率数据作为自变量,土样盐分数据为因变量,分别采用多元线性回归模型和BP神经网络模型构建土壤含盐量反演模型。结果表明:土壤盐渍化程度越高,影像光谱反射率越低,且在近红外波段反射率最高;BP神经网络模型的反演精度优于传统的多元线性回归模型,其R2为0.9808,RMSE为1.0595,平均相对误差为15.4%,拟合精度较高,能够为灌区盐渍化治理提供基础依据。

Abstract

In recent years,secondary salinization of the lower reaches of the Yellow River has been repeated and gradually intensified, causing damage to agricultural production and ecological security. This paper takes the Xiaokaihe Irrigation District of the Yellow River Delta as the study area. Based on the soil salt content and Landsat8 OLI multi-spectral imagery,the spectral curve characteristics of soil samples are analyzed. According to the diagnostic index method,the band reflectance data with larger diagnostic index is an independent variable and the salt salinity is the dependent variable,and the soil salt inversion model is constructed by multiple linear regression model and BP neural network model. The results show that the higher the degree of soil salinization,the lower the spectral reflectance of the image and the highest reflectance is in the near-infrared. The inversion accuracy of BP neural network model is better than that of the traditional multiple linear regression model. It's R2 is 0.980 8 and RMSE is 1.059 5,the average relative error is 15.4%,and the fitting accuracy is high,which can provide a basis for the salinization treatment in the irrigation district.

关键词

小开河引黄灌区 / landsat8 / 定量遥感反演 / BP 神经网络

Key words

Yellow River Delta / landsat8 / quantitative remote sensing inversion / the BP neural network model

基金

黄河水利科学研究院基本科研业务费专项( HKY-JBYW -2017-22) 。 

引用本文

导出引用
刘恩 王军涛 常布辉 王东琦. 小开河引黄灌区土壤盐渍化定量遥感反演[J].中国农村水利水电, 2019(12): 20-24
LIU En, WANG Jun-tao, CHANG Bu-hui, WANG Dong-qi. Quantitative Remote Sensing Inversion of Soil Salinization in Xiaokaihe Yellow River Irrigation District[J].China Rural Water and Hydropower, 2019(12): 20-24

参考文献

[1] 关元秀,王劲峰,刘高焕.黄河三角洲土地盐碱化遥感监测、预测 和治理研究[D]. 北 京: 中国科学院地理科学与资源研究所, 2001: 178-181. 
[2] Bao B R M,Sankar T R,Dwivedi R S et. Spectral Behavior of salt-affected soils[J]. International Journal of Remote Sensing,1995,16 ( 12) : 2 125-2 136. 
[3] Dwivedi R S. Monitoring and the Study of the Effects of Image Scale on Delineation of Salt-affected Soils in the Indo-Gangetic Piains[J]. International Jounral of Remote Sensing,1992,13( 8) : 1 527-1 536. 
[4] Mougenot B,Pouget M,Epema G. Remote Sensing of Salt-affected Soils[J]. Remote Sensing Reviews,1993( 7) : 241-259. 
[5] 曹建荣,刘文全.基于 landsat TM/ETM 影像的黄河三角洲盐渍土 动态变化分析[J].水土保持通报,2014,34( 6) : 180-183. 
[6] 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. 
[7] 樊彦国,李潭潭,李祥昌.基于 Landsat8 的黄河三角洲盐渍化反演 [J〗.山东农业科学,2015,47( 2) : 119-124. 
[8] 张成雯,唐家奎,于新菊,等.黄河三角洲土壤含盐量定量遥感反 演[J].中国科学院研究生院学报,2013,30( 2) : 220-227. 
[9] 王多多,贾文晓,王志保,等.基于 Landsat 影像的崇明岛东滩土壤 盐分遥感反演技术[J].中国农业科技导报,2018,20( 3) : 55-63. 
[10] 高大启.有教师的线性基本函数前向三层神经网络结构研究 [J].计算机学报,1998,21( 1) : 80-86. 
[11] 廖宁放,高稚允. BP 神经网络用于函数逼近的最佳隐层结构 [J].北京理工大学学报,1998,18( 4) : 476-480.
PDF(611 KB)

410

访问

0

引用

详细情况

段落导航
相关文章

/