节点文献

基于ANN技术和高光谱遥感的盐渍土盐分预测

Salinity forecasting of saline soil based on ANN and hyperspectral remote sensing

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 王静刘湘南黄方唐吉龙赵冷冰

【Author】 Wang Jing 1,2 ,Liu Xiangnan 3 ,Huang Fang 1,2 ,Tang Jilong 4 ,Zhao Lengbing 5 (1.Key Laboratory of Vegetation Ecology of Education Ministry,Institute of Grassland Science,Northeast Normal University, Jilin 130024,China;2.Key Laboratory for Wetland Ecology and Vegetation Restoration of National Environmental Protection, Northeast Normal University,Jilin 130024,China;3.Information Engineering College,China University of Geosciences(Beijing), Beijing 100083,China;4.College of Opto-electronic Engineering,Changchun University of Science and Technology, Jilin 130022,China;5.Academy of Forestry Inventory and Planning of Jilin,Jilin 130022,China)

【机构】 东北师范大学草地研究所植被生态教育部重点实验室东北师范大学国家环境保护湿地生态与植被恢复重点实验室中国地质大学(北京)信息工程学院长春理工大学光电工程学院吉林省林业调查规划院

【摘要】 土壤盐渍化是干旱、半干旱农业区主要的土地退化问题,及时、精准、动态地监测盐渍土盐分,对于治理、防治盐渍土和进行农业可持续发展至关重要。以松嫩平原西部长岭县为例,利用盐渍土高光谱数据构建盐渍土盐分遥感预测模型。电导法测得土壤盐量,用ASD高光谱仪野外采集高光谱数据,利用光谱导数变换选择能够表征盐渍土盐分信息的最佳波段,即550、720、760、820和940nm。通过比较3层和4层72种不同神经网络结构,最终选择5-6-1结构的3层神经网络预测盐渍土盐分(R2=0.895,RMSE=0.089)。与传统回归相比(R2=0.81,RMSE=0.25),运用高光谱数据与人工神经网络方法相结合,能够提高盐渍土的预测精度,说明人工神经网络在构建光谱反射率与土壤参数关系研究中具有突出优势。

【Abstract】 Soil salinization is a major problem of land degradation in arid and semi-arid agricultural area.It is crucial to detect the salinity of saline soils accurately and dynamicly in time in order to prevent soil salinization and achieve sustainable development in agriculture.Taking Changling County western Songnen Plain,as the example,this paper constructed remote sensing predictive model of saline soils using hyperspectral data.The salinity was measured by electric conduction method,and hyperspectral data was collected using ASD spectrometer.Derivative transformation of spectral reflectance was used to select best spectral bands which can represent the salinity of saline soils,e.g.550,720, 760,820 and 940 nm.The best performance was achieved in the 5-6-1 architecture(R 2 =0.895,RMSE=0.089)in 72 different architectures in the three-and four-layer networks.Compared with traditional regression model(R 2 =0.81, RMSE=0.25),the method combining hyperspectral data with artificial neural network can improve the predictive accuracy of saline soil,showing that artificial neural network is prominently advanced in establishing the relationships between spectral reflectance and soil parameters.

【关键词】 神经网络遥感预测盐渍化高光谱
【Key words】 neural networkremote sensingforecastingsalinationhyperspectral
【基金】 国家“973”计划(2009CB426305)
  • 【文献出处】 农业工程学报 ,Transactions of the Chinese Society of Agricultural Engineering , 编辑部邮箱 ,2009年12期
  • 【分类号】S156.4
  • 【被引频次】96
  • 【下载频次】903
节点文献中: 

本文链接的文献网络图示:

本文的引文网络