基于GOCI-Ι影像的黄河口周边海域悬浮物浓度反演模型构建  

Construction of a Suspended Sediment Concentration Inversion Model in The Yellow River Estuary Surrounding Waters Based on GOCI-I Images

作　　者：毛露 江娜[2] 王娟 刘善伟[1] 崔建勇[1] 许明明 MAO Lu;JIANG Na;WANG Juan;LIU Shanwei;CUI Jianyong;XU Mingming(Dept.Surveying and Mapping,China University of Petroleum(East China),Qingdao 266580,China;Land Surveying and Mapping Institute of Shandong Province,Jinan 250102,China;North China Sea Environmental Monitoring Center,State Oceanic Administration,Qingdao 266033,China)

机构地区：[1]中国石油大学(华东)测绘系,青岛266580 [2]山东省国土测绘院,济南250102 [3]自然资源部北海生态中心,青岛266033

出　　处：《遥测遥控》2024年第6期121-130,共10页Journal of Telemetry,Tracking and Command

基　　金：国家自然科学基金(U1906217,62071491);中央高校基本科研专项资金(22CX01004A-4,22CX01004A-5)。

摘　　要：为实现黄河口周边海域悬浮物浓度的高精度遥感反演,本文利用GOCI-I影像数据构建了基于WOA-BP算法的春、夏、秋三个季节模型和一个跨季节模型,并与Catboost、RF、KNN、BP等多种模型进行比较。结果表明,在各个季节模型中,WOA-BP算法在训练集和测试集上均表现最佳,相应季节测试集的平均相对误差依次为24.18%、25.97%、29.42%,而利用跨季节测试集对三个模型进行测试,其精度非常差,说明季节模型不能跨季节应用;在跨季节模型中,WOA-BP算法的精度也是最高的,总体平均相对误差为26.96%,利用三个季节测试集进行测试的平均相对误差依次为25.80%、21.90%、37.17%,除夏季的精度有所提升外,另外两个季节的精度都低于相应的季节模型,其中秋季的精度降低最大。因此,对于春夏两季可以使用跨季节模型,而对于秋季则建议使用相应的季节模型。In order to achieve high-precision remote sensing inversion of suspended particulate matter concentration in the seas surrounding the Yellow River Estuary,this paper constructs seasonal models for spring,summer,and autumn,as well as a crossseasonal model,utilizing GOCI-I image data and based on the WOA-BP algorithm.These models are compared with multiple algorithms such as Catboost,RF,KNN,BP and so on.The results reveal that within each seasonal model,the WOA-BP algorithm exhibits superior performance on both the training and testing sets,with the average relative errors for the respective seasonal testing sets being 24.18%,25.97%,and 29.42%.When the cross-seasonal testing set is employed to evaluate the three models,and their accuracy is found to be significantly lacking,which indicates that seasonal models are not applicable across different seasons.In the crossseasonal model,the WOA-BP algorithm again demonstrates the highest accuracy,with an overall average relative error of 26.96%.The average relative errors when testing with the three seasonal testing sets are 25.80%,21.90%,and 37.17%,respectively.While the accuracy for summer is improved,the accuracy for the other two seasons falls below that of the corresponding seasonal models,with autumn experiencing the greatest decline in precision.Therefore,it is suggested that the cross-seasonal model be employed for spring and summer,whereas the appropriate seasonal models are recommended for autumn.

关 键 词：悬浮物浓度反演 GOCI-I卫星数据 季节性分析 WOA-BP模型 

分 类 号：X834[环境科学与工程—环境工程] P714[天文地球—海洋科学]