摘要
及时准确地开展城市湖泊水质监测,对于保护城市生态环境、保障居民健康和促进可持续发展具有重要意义。结合无人机高光谱影像与机器学习算法,开展武汉市汤逊湖的水质参数反演研究,分别使用误差反向传播神经网络(Backpropagation Neural Network,BP)、随机森林(Random Forest,RF)、极限梯度提升(eXtreme Gradient Boosting,XGBoost)和支持向量机(Support Vector Machine,SVM)构建叶绿素a(Chla)、总磷(TP)、总氮(TN)和悬浮物(SS)的反演模型。结果表明:(1)Chla、TP、TN和SS反演的最优机器学习算法分别为BP(R^(2)=0.949,RMSE=9.337μg/L)、RF(R^(2)=0.948,RMSE=0.013mg/L)、XGBoost(R^(2)=0.928,RMSE=0.095mg/L)、XGBoost(R^(2)=0.875,RMSE=4.052mg/L);(2)Chla最佳反演模型为BP神经网络结合高光谱全波段,TP最优反演模型为RF结合高光谱敏感波段,TN和SS的最优反演模型为XGBoost结合高光谱敏感波段。研究结果可为城市湖泊水质动态监测和管理提供技术支撑,有助于推动城市水环境的精细化管理和保护。
Timely and accurately monitoring of urban lake water quality is crucial for protecting urban ecosystems,safeguarding public health,and promoting sustainable development.This article takes the water quality parameter inversion of a typical lake area in Tangxun Lake,Wuhan as the research object,and conducts research on water quality parameter inversion based on unmanned aerial vehicle(UAV)hyperspectral images and machine learning algorithms.Error backpropagation(BP)neural network,Random Forest(RF),eXtreme Gradient Boosting(XGBoost)and Support Vector Machine(SVM)are used to construct the inversion models for Chlorophyll-a(Chla),Total Phosphorus(TP),Total Nitrogen(TN),and Suspended Sediment(SS),respectively.The main conclusions are as follows:(1)The optimal models for Chla,TP,TN,and SS are BP(R^(2)=0.949,RMSE=9.337μg/L),RF(R^(2)=0.948,RMSE=0.013 mg/L),XGBoost(R^(2)=0.928,RMSE=0.095 mg/L),and XGBoost(R^(2)=0.875,RMSE=4.052 mg/L),respectively;(2)Comparative analysis reveals that BP and RF performed best for Chla and TP inversion,while XGBoost demonstrated superior performance for TN and SS inversion.The research results of this article provide technical support for the dynamic monitoring and management of urban lake water quality,which help to promote the refined management and protection of urban water environment.
作者
郭亚会
周伟
李松泽
马瑞晨
高敬丹
张璇
郝芳华
GUO Yahui;ZHOU Wei;LI Songze;MA Ruichen;GAO Jingdan;ZHANG Xuan;HAO Fanghua(Hubei Province Key Laboratory for Geographical Process Analysis and Simulation,Central China Normal University,Wuhan 430079,China;College of Urban and Environmental Sciences,Central China Normal University,Wuhan 430079,China;College of Water Sciences,Beijing Normal University,Beijing 100875,China)
出处
《宁波大学学报(理工版)》
2025年第5期20-30,共11页
Journal of Ningbo University(Natural Science and Engineering Edition)
基金
国家社科基金重大项目(23&ZD105)。
关键词
无人机遥感
高光谱影像
水质参数反演
机器学习算法
unmanned aerial vehicle remote sensing
hyperspectral imagery
water quality parameter inversion
machine learning algorithms
