基于红(R)绿(G)蓝(B)三波段的典型港湾透明度反演研究  

ESTIMATING TRANSPARENCY IN TYPICAL BAY USING RGB SPECTRAL BANDS

作　　者：朱元励 毛铭 郭然 杜萍 陶邦一 江志兵 曾江宁 ZHU Yuan-Li;MAO Ming;GUO Ran;DU Ping;TAO Bang-Yi;JIANG Zhi-Bing;ZENG Jiang-Ning(Key Laboratory of Marine Ecosystem Dynamics,Second Institute of Oceanography,Ministry of Natural Resources,Hangzhou 310012,China;Key Laboratory of Nearshore Engineering Environment and Ecological Security of Zhejiang Province,Hangzhou 310012,China;School of Environmental Science and Engineering,Zhejiang Gongshang University,Hangzhou 310012,China;Key Laboratory of Ocean Space Resource Management Technology,Ministry of Natural Resources,Hangzhou 310012,China;Observation and Research Station of Marine Ecosystem in the Yangtze River Delta,Ministry of Natural Resources,Zhoushan 316021,China;State Key Laboratory of Satellite Ocean Environment Dynamics,Second Institute of Oceanography,Ministry of Natural Resources,Hangzhou 310012,China)

机构地区：[1]自然资源部第二海洋研究所自然资源部海洋生态系统动力学重力实验室,浙江杭州310012 [2]浙江省近海海洋工程环境与生态安全重点实验室,浙江杭州310012 [3]浙江工商大学环境科学与工程学院,浙江杭州310012 [4]浙江省海洋科学院海洋空间资源管理技术重点实验室,浙江杭州310012 [5]自然资源部长三角海洋生态环境科学野外观测研究站,浙江舟山316021 [6]自然资源部第二海洋研究所卫星海洋环境动力学国家重点实验室,浙江杭州310012

出　　处：《海洋与湖沼》2024年第3期651-659,共9页Oceanologia Et Limnologia Sinica

基　　金：浙江省基础公益研究计划,LGF21D060001号;浙江省科技计划项目,2024C03235号;国家重点研发计划,2021YFC3101702号;浙江省自然科学基金,LY22D060006号。

摘　　要：基于卫星遥感的透明度(Secchi depth,SD)反演方法已经在大洋、近海、湖泊等不同水体开展了广泛应用。富营养化河口港湾等水体具有水域面积小且受陆地影响大等特点,并且在此类水体开展环境监测具有时效性要求。受时间空间分辨率以及云层覆盖、大气校正等影响,基于卫星遥感方法在河口港湾等小水域进行透明度反演会受到一定的应用限制,因此在此类特征水体建立一种高效便捷的透明度反演方法作为卫星遥感方法的有益补充就十分迫切。本研究尝试通过无人机和智能手机应用程序HydroColor APP搭载的普通光学相机构建基于红(red,R)绿(green,G)蓝(blue,B)三波段的象山港透明度反演方法。结果表明,无人机和HydroColor的红蓝波段比值(R/B)和红绿波段比值(R/G)与透明度具有显著负相关,相关系数R为–0.88~–0.93(n=16,P<0.001)。根据相关性分析结果构建透明度反演模型并基于独立数据库对模型进行精度评估。结果显示,(1)指数反演模型要优于线性经验模型,(2)基于R/G反演模型要优于R/B模型,(3)HydroColor反演模型要优于无人机反演模型。通过以上结果分别构建基于无人机DJI-R/G和HydroColor-R/G最优透明度指数反演模型。DJI-R/G模型平均相对误差和均方根误差为29%和0.3 m,HydroColor-R/G模型为21.9%和0.27 m。以上结果表明,通过无人机和手机获取RGB信息均可用于对象山港透明度进行反演。该方法的建立为快速便捷开展河流港湾等水体的水质监测和赤潮防控提供了新的技术支持。Satellite remote sensing-based transparency(as in the Secchi depth(SD))inversion methods have been widely applied for oceans,offshore areas,and lakes.However,eutrophic estuaries,harbors,and other water bodies are relatively small in water area with significant land impact,and environmental monitoring in these waters requires timeliness.Due to the restrictions from temporal and spatial resolution,cloud shadowing,atmospheric correction,and other factors,the application in such small water bodies are limited.Therefore,it is urgent to establish an efficient and convenient transparency inversion method for these areas to complement satellite remote sensing methods,which calls for a robust SD inversion specific to these areas.This study attempts to construct a transparency inversion method for Xiangshan Bay,Zhejiang,East China,based on the red(R),green(G),blue(B)three bands using a conventional optical camera co-worked with smartphone HydroColor app and a drone,focusing on the red(R),green(G),and blue(B)bands.We observed that the drone and the app’s red-to-blue(R/B)and red-to-green(R/G)ratios had a strong negative correlation with SD,and the correlation coefficients R was between-0.88 and-0.93(n=16,P<0.001).A transparency inversion model was established based on the results of correlation analysis and the accuracy of the model was evaluated based on an independent database.After the SD inversion model was calibrated,its accuracy was assessed using an independent dataset.Results show that the exponential inversion model is superior to the linear empirical model;the R/G inversion model is superior to the R/B model;and the HydroColor-based inversion model is superior to the drone-based inversion model.Based on these results,optimal SD inversion models were constructed for drone R/G and HydroColor-R/G determination.The average relative error and root mean square error of the drone model were 29%and 0.3 m,while those of the HydroColor model were 21.9%and 0.27 m,respectively.The above results indicate that both drones and

关 键 词：透明度 红绿蓝(red green blue RGB) 遥感反演 无人机 手机APP 象山港 

分 类 号：X87[环境科学与工程—环境工程]