基于M-SD-GWO-SVRWL叶绿素a浓度反演研究  

Research on Wuliangsu Lake Chlorophyll-a Concentration Inversion Based on M-SD-GWO-SVR

作　　者：吴陈昊 付学良[1] 李宏慧[1] 扈华[1] WU Chen-hao;FU Xue-liang;LI Hong-hui;HU Hua(College of Computer and Information Engineering,Inner Mongolia Agricultural University,Hohhot Inner Mongolia 010010,China)

机构地区：[1]内蒙古农业大学计算机与信息工程学院,内蒙古呼和浩特010010

出　　处：《计算机仿真》2024年第10期272-278,共7页Computer Simulation

基　　金：国家自然科学基金项目(62041211,61962047);国家重点研发计划(2019YFC049205);内蒙古自然科学基金(2020MS06011,2019MS0601);内蒙古高校科技重点项目(NJZZ23044)。

摘　　要：为了解乌梁素海水质状况,提出一种基于月份特征(M)融合灰狼算法(GWO)优化支持向量回归(SVR)的叶绿素a浓度反演模型。以Sentinel-2遥感影像为数据源,首先考虑研究区域存在的时空特征,提出将月份作为叶绿素a浓度的特征数据输入,通过归一化(N)和二阶导数(SD)方法对数据进行预处理,建立起M-SD-GWO-SVR的叶绿素a浓度反演模型,该模型决定系数(R^(2))为0.932,均方根误差(RMSE)为0.046。仿真结果表明,所提模型反演效果优于GA-SVR、PSO-SVR,并且引入月份特征数据时,有效降低了模型复杂度,提高了模型反演精度,验证了所提模型对乌梁素海叶绿素a浓度反演的可行性。In order to understand the water quality of Wuliangsu Lake,a chlorophyll-a concentration inversion model based on month feature(M)was proposed.It combines Grey Wolf Algorithm(GWO)to optimize Support Vector Regression(SVR).Sentinel-2 remote sensing satllite image is used as the data source.Firstly,considering the spatial and temporal characteristics of the study area,the month is proposed as the characteristic data input of chlorophyll a concentration.The data are preprocessed by normalization(N)and second derivative(SD)methods,and the chlorophyll a concentration inversion model of M-SD-GWO-SVR is established.The coefficient of determination(R²)of the model is 0.932,and the root mean square error(RMSE)is 0.046.The simulation results show that the inversion effect of the proposed model is better than that of GA-SVR and PSO-SVR.The coefficient of determination(R2)of the model is 0.932,and the root mean square error(RMSE)is 0.046.The simulation results show that the inversion effect of the proposed model is better than that of GA-SVR and PSO-SVR.When the monthly characteristic data is introduced,the complexity of the model is effectively reduced,the accuracy of the model inversion is improved,and the feasibility of the proposed model for the inversion of chlorophyll-a concentration in Wuliangsu lake is verified.

关 键 词：乌梁素海 叶绿素 月份特征 支持向量回归 灰狼算法 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置] TP391.9[自动化与计算机技术—控制科学与工程]