基于地理信息的OED-RF草海水深反演  

Water-depth inversion for Caohai Lake based on GEO+OED-RF

作　　者：周彬 陈冬云 黄筱 刘开奋 王沿儒 ZHOU Bin;CHEN Dongyun;HUANG Xiao;LIU Kaifen;WANG Yanru(School of Electronic and Communication Engineering,Guiyang University,Guiyang 550005,China;School of Mines,Guizhou University,Guiyang 550025,China;PowerChina Guiyang Engineering Corporation Limited,Guiyang 550081,China)

机构地区：[1]贵阳学院电子与通信工程学院,贵州贵阳550005 [2]贵州大学矿业学院,贵州贵阳550025 [3]中国电建集团贵阳勘测设计研究院有限公司,贵州贵阳550081

出　　处：《人民长江》2023年第4期62-67,共6页Yangtze River

基　　金：国家自然科学基金项目(12165003)。

摘　　要：为充分利用已有数据提高浅水区水深反演的精度,并快速选择机器学习模型中的参数,选取贵州省草海为研究区,在BP神经网络模型和随机森林模型(RF)中加入地理信息(GEO),采用正交试验设计法(OED)选取GEO+RF模型较优参数,并与多波段对数线性模型、GEO+BP神经网络模型和GEO+RF模型进行对比。结果表明:相较于文中所对比的模型,提出的GEO和OED-RF模型反演精度最高,实测水深-反演水深散点图点位最为集中,反演水深图与实测水深图基本一致。说明GEO和OED-RF模型能有效提升试验效率、选出较优参数并提高浅水区水深反演精度,可为相似区域水资源遥感监测与分析提供参考。In order to make full use of the existing data to improve the accuracy of remote sensing water-depth inversion of shallow water,and quickly select parameters in the machine learning model,taking Caohai Lake as the research area,geographic information(GEO)was added to the BP neural network model and random forest model(RF),and the optimal parameters of the GEO+RF model were selected by orthogonal experimental design(OED).The inverted results were compared with the multi-band log-linear model,GEO+BP neural network model and GEO+RF model.The results showed that the GEO+OED-RF model had the highest accuracy,the measured water depth-inverted water depth scatter plot had the most concentrated points,and the inversion water depth map was basically consistent with the measured water depth.It showed that the GEO+OED-RF model can effectively improve the experimental efficiency,select optimal parameters,and improve the inversion accuracy of remote sensing water-depth in shallow water areas,which can provide a method reference for remote sensing monitoring and analysis of water resources in similar areas.

关 键 词：水深反演 正交试验设计 随机森林 地理信息 草海 

分 类 号：P237[天文地球—摄影测量与遥感]