摘要
岛礁周边海底地形精密测量是海洋测绘的难点问题之一,利用多光谱卫星能精确测定岛礁周边水深地形,是传统岛礁水深测量有效的补充方式。本文以螟支洲岛周围水域为研究区域,提出了基于BP神经网络水深分段选取反演因子的方法,利用WorldView-2数据和多波束实测数据建立多模型,整合预测的各段水深获得海底地形。实验表明,本文方法能充分利用水体的光谱特性,与单一BP神经网络模型结果相比,平均相对误差(MRE)降低了6.4%,均方根误差(RMSE)降低了1.2 m,是一种可行的多光谱水深反演方法。
The precise measurement of seafloor topography around islands and reefs is one of the difficult problems in marine mapping,The use of multispectral satellites can accurately determine the bathymetric topography around islands and reefs,thus is one effective complementary to traditional island bathymetry detection.Taking the waters around Wuzhizhou Island as the study area,this paper proposes a method based on BP-net as well as water depth segmentation to select the inversion factors,and establishes a multi-model using WorldView-2 data and in-situ measurement to integrate the predicted water depths of each segment to obtain the seafloor topography.The experiment shows that this method can make full use of the spectral properties of the water body,and the MRE is reduced by 6.4% and the RMSE is reduced by 1.2 m compared with the results of a single BP net model.It is a feasible method for multispectral water depth inversion.
作者
李宁宁
陈义兰
王燕红
张靖宇
唐秋华
LI Ningning;CHEN Yilan;WANG Yanhong;ZHANG Jingyu;TANG Qiuhua(First Institute of Oceanography,Ministry of Natural Resources,Qingdao 266061,China;Key Laboratory of Oceanic Surveying and Mapping,Ministry of Natural Resources,Qingdao 266590,China)
出处
《海洋通报》
CAS
CSCD
北大核心
2022年第4期371-378,共8页
Marine Science Bulletin
基金
国家自然科学基金(41876111,51839002,41906158)。
关键词
多光谱遥感
水深反演
BP神经网络
水深分段
反演因子分析
multi-spectral remote sensing
water depth inversion
BP net
water depth segmentation
inversion factors analysis
作者简介
李宁宁(2001-),硕士研究生,主要从事多光谱遥感反演水深研究。电子邮箱:529142251@qq.com;通讯作者:陈义兰,硕士,高级工程师。电子邮箱:chenyilan@fio.org.cn。
