摘要
以Sentinel-2A遥感影像为数据源,在数据预处理基础上,使用极限学习机建立水深反演非线性回归模型,并与双波段回归模型、神经网络BP模型进行了比较。结果表明,总体上,支持极限学习机反演精度比较高,在水深5~20m处,极限学习机模型具有较高的反演精度和良好的效果,适用于研究区的水深反演。
Taking Sentinel-2A image as data sources,on the basis of data preprocessing,the depth inversion nonlinear regression model is established using Extreme Learning Machine(ELM),and a comparison is made between dual-band regression model and BP neural network model respectively.The results show that,in general,the inversion accuracy of support vector machine(SVM)is higher,and in depth of 5-10-15-20,ELM has a higher inversion accuracy and better effect,which suits depth inversion in research ares.
作者
吴忠强
毛志华
王正
邱耀炜
沈蔚
WU Zhongqiang;MAO Zhihua;WANG Zheng;QIU Yaowei;SHEN Wei(School of Geographic and Oceanographic Sciences,Nanjing University,Nanjing 210023,China;Collaborative Innovation Center for the South China Sea Studies,Nanjing University,Nanjing 210023,China;States Key Laboratory of Satellite Ocean Environment Dynamics,Second Institute of Oceanography,Ministry of Natural Resources,Hangzhou 310012,China;College of Marine Sciences,Shanghai Ocean University,Shanghai 201306,China;Estuarine and Oceanographic Mapping Engineering Research Center of Shanghai Municipal Ocean Bureau,Shanghai 201306,China)
出处
《海洋测绘》
CSCD
2019年第3期11-15,共5页
Hydrographic Surveying and Charting
基金
国家重点研发计划项目(2016YFC140091)
国家海洋公益项目(201005030)
国家自然科学基金(41476156
41621064)
高分辨率对地观测系统重大专项(41-Y20A31-9003-15/17)
