首页|基于高分遥感影像的总磷浓度反演研究

基于高分遥感影像的总磷浓度反演研究

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
以定量遥感反演水质参数为目的,以天津市海河下游段为研究区,利用总磷实测水质数据和同期GF-2 PMS 2 遥感影像数据,建立两者的偏最小二乘回归模型、单隐含层神经网络模型、双隐含层神经网络模型及粒子群算法优化的双隐含层神经网络模型(DP-BPNN模型).通过决定系数、平均绝对误差、均方根误差进行精度检验,选出研究区水体适用的总磷浓度的反演模型.结果表明:与偏最小二乘模型精度对比,所建总磷反演模型精度提高了48%.
Total Phosphorus Concentration Inversion Research Based on High-resolution Remote Sensing Images
In this paper,the inversion model for total phosphorus concentration was established based on the measured water quality data and GF-2 satellite data in the Haihe River Basin,Tianjin.The optimal inversion model for total phosphorus concentration was determined by comparing the partial least squares regression model,the single hidden layer neural network model,the double hidden layer neural network model and the dual neural network model optimized by the particle swarm algorithm.Through the determination coefficient,mean absolute error,and root mean square error,the accuracy was verified,and the inversion model of total phosphorus concentration applicable to the water body in the study area was selected.The results show that the accuracy of DP-BPNN of total phosphorus concentrations is improved by 48%as compared with that of the partial least squares model.

neural network modelparticle swarm optimizationwater quality parameter inversiontotal phosphorus concentrationGF-2 remote sensing imagesHaihe River

吴欢欢、春兰、王春晓、国巧真、刘晓娟、熊小青

展开 >

自然资源部海南基础地理信息中心,海南 海口 570100

天津城建大学 地质与测绘学院,天津 300384

神经网络模型 粒子群优化算法 总磷 GF-2遥感影像 海河

自然资源部海洋测绘重点实验室开放研究基金自然资源部科技创新人才培养工程青年人才资助项目

2021A0212110600000018003932

2024

测绘与空间地理信息
黑龙江省测绘学会

测绘与空间地理信息

影响因子：0.788
ISSN：1672-5867
年,卷(期)：2024.47(8)