摘要
利用哨兵-2数据及多种方法反演喀斯特高原深水湖库的高锰酸盐指数(COD_(Mn)),对于区域水环境管理和丰富水质反演理论具有重要意义。以贵阳市红枫湖与百花湖为研究区,基于Sentinel-2 MSI影像和COD_(Mn)浓度数据,使用随机森林回归(RFR)、支持向量回归方法(SVR)、高斯过程回归(GPR),构建COD_(Mn)反演模型,获得2018~2020年不同时期的COD_(Mn)空间分布。结果表明:(1)RFR模型估算精度最高,验证集RMSE为0.222 mg·L^(-1),MAPE为5.84%,R2为0.841;(2)红枫湖COD_(Mn)浓度变化呈现上游高于下游、春季高于夏季的时空分布特征。百花湖除了上游,整体湖区COD_(Mn)浓度较低且随时间变化不大。研究揭示了RFR模型与Sentinel-2数据在喀斯特高原深水湖库COD_(Mn)浓度反演具有良好的适用性。
Using Sentinel-2 data and multiple methods to invert the permanganate index(COD_(Mn))of deep-wa-ter lakes and reservoirs in the Karst Plateau is of great significance for the regional water environment manage-ment and enrichment of water quality inversion theories.Taking Hongfeng Lake and Baihua Lake as the re-search area,based on the Sentinel-2 MSI image and COD_(Mn) concentration data,use Random Forest Regres-sion(RFR),Support Vector Regression Method(SVR),Gaussian Process Regression(GPR),Obtaining COD_(Mn) spatial distribution in different periods of 2018~2020.The results show that:①The RFR model has the highest accuracy,the verification set is 0.222 mg·L^(-1),MAPE is 5.84%,and R^(2) is 0.841;In addition to the upstream of Baihua Lake,the COD_(Mn) concentration of the overall lake is low and there is not much change over time.Studies have shown that the RFR model and Sentinel-2 data are well applicable to monitoring the COD_(Mn) concentration monitoring of deep-water lakes in the Karst Plateau.
作者
王姣
李威
赵卫权
赵祖伦
黄亮
杨家芳
WANG Jiao;LI Wei;ZHAO Weiquan;ZHAO Zulun;HUANG Liang;YANG Jiafang(Institute of Mountain Resources,Guiyang 550001,China)
出处
《遥感技术与应用》
CSCD
北大核心
2024年第1期98-109,共12页
Remote Sensing Technology and Application
基金
贵州省基础研究计划(黔科合基础[2020]1Y410、黔科合基础[2018]1418)
贵州省科技支撑计划(黔科合支撑[2020]4Y132、黔科合支撑[2023]199)
贵州科学院青年基金(黔科院J字[2018]11号、黔科院J字【2020】15号)。
