测绘通报 ›› 2020, Vol. 0 ›› Issue (3): 21-24.doi: 10.13474/j.cnki.11-2246.2020.0071

• 学术研究 • 上一篇    下一篇

结合PRO-4SAIL和BP神经网络的叶绿素含量高光谱反演

郭云开1,2, 许敏1,2, 张晓炯1,2, 刘雨玲1,2   

  1. 1. 长沙理工大学交通运输工程学院, 湖南 长沙 410076;
    2. 长沙理工大学测绘遥感应用技术研究所, 湖南 长沙 410076
  • 收稿日期:2019-06-05 修回日期:2019-09-14 出版日期:2020-03-25 发布日期:2020-04-09
  • 通讯作者: 许敏。E-mail:2877076921@qq.com E-mail:2877076921@qq.com
  • 作者简介:郭云开(1958-),男,博士,教授,主要从事路域植被生态环境遥感研究。E-mail:guoyunkai226@163.com
  • 基金资助:
    国家自然科学基金面上项目(41671498)

Chlorophyll hyperspectral inversion with PRO-4SAIL and BP neural networks

GUO Yunkai1,2, XU Min1,2, ZHANG Xiaojiong1,2, LIU Yuling1,2   

  1. 1. School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410076, China;
    2. Institute of Surveying and Mapping Remote Sensing Applied Technology, Changsha University of Science and Technology, Changsha 410076, China
  • Received:2019-06-05 Revised:2019-09-14 Online:2020-03-25 Published:2020-04-09

摘要: 针对PRO-4SAIL辐射传输模型耦合BP神经网络反演叶绿素时存在过拟合、预测精度低的问题,本文以研究区内实测的高光谱数据和模拟光谱数据为数据源,在模拟样本数据构成的训练集中添加部分实测样本数据,构建BP神经网络叶绿素反演模型,然后利用剩余的实测数据进行模型验证与精度评定。结果表明:向训练集中加入少量实测数据,可以解决叶绿素反演模型过拟合的问题,叶绿素含量的预测精度得到提升,实现准确的反演路域植被信息,为路域环境植被环境遥感监测评价提供一定的技术支持。

关键词: PRO-4SAIL, BP神经网络, 过拟合, 叶绿素, 路域植被

Abstract: In view of the problems of over-fitting and low prediction accuracy of chlorophyll inversion by the PRO-4SAIL radiation transfer model coupled with BP neural network, there are some problems.In this paper, measured hyperspectral data and simulated spectral data in the research area are used as data sources, and some measured sample data are added to the training set composed of simulated sample data to build the BP neural network chlorophyll inversion model, and the model verification and accuracy evaluation are carried out with additional measured data.The results show that the training concentration can solve the over-fitting problem of chlorophyll inversion model by adding a small amount of measured data, improve the accuracy of chlorophyll content prediction, and accurately invert the vegetation information of roadways, which can be applied to the remote sensing monitoring and evaluation of roadways environment.

Key words: PRO-4SAIL, back propagation neural networks, overfitting, chlorophyll, expressway vegetation

中图分类号: