测绘通报 ›› 2024, Vol. 0 ›› Issue (10): 1-6.doi: 10.13474/j.cnki.11-2246.2024.1001.

• 水环境监测 •    下一篇

利用Sentinel-2卫星影像反演骆马湖叶绿素a浓度

梁文广1, 陈伟2, 王金东3, 吴勇锋1, 祁诣恒3   

  1. 1. 江苏省水利科学研究院, 江苏 南京 210017;
    2. 河海大学地球科学与工程学院, 江苏 南京 210098;
    3. 江苏省骆运水利工程管理处, 江苏 宿迁 223800
  • 收稿日期:2024-07-08 发布日期:2024-11-02
  • 作者简介:梁文广(1981—),男,博士,正高级工程师,主要从事水利遥感研究工作。E-mail:82335673@qq.com
  • 基金资助:
    水利青年拔尖人才资助项目(2022026)

Inversion of Chlorophyll-a concentration in Luoma Lake using Sentinel-2 satellite imagery

LIANG Wenguang1, CHEN Wei2, WANG Jindong3, WU Yongfeng1, QI Yiheng3   

  1. 1. Jiangsu Hydraulic Research Institute, Nanjing 210017, China;
    2. School of Earth Sciences and Engineering, Hohai University, Nanjing 210098, China;
    3. Luoyun Management Division, Suqian 223800, China
  • Received:2024-07-08 Published:2024-11-02

摘要: 本文利用2023年6月15日采集的骆马湖水质参数、光谱数据和同期Sentinel-2影像数据,构建了基于数学统计和机器学习方法的水质反演模型,并对骆马湖叶绿素a(Chl-a)浓度进行了定量反演。通过对比分析,选定了性能最优的模型分析骆马湖Chl-a浓度状况。研究发现,Chl-a浓度与Sentinel-2影像B5和B9波段表现出较高的相关性,且经波段组合处理后,相关性进一步提升。在Chl-a反演模型中,FA-SVR模型相较于传统数学统计回归模型及其他机器学习模型(FA-RF、FA-XGBoost)表现出最高的精度(R2=0.86, RMSE=2.77, MAE=2.10)。反演结果揭示,骆马湖东北部近岸区域的Chl-a浓度较高,这可能与北部水域存在鱼塘养殖、水体富营养高有关。本文突显了机器学习技术在提升水质遥感反演精度方面的重要应用价值,为湖泊水质监控和管理提供了重要的技术支撑。

关键词: 骆马湖, Chl-a浓度, 遥感反演, 机器学习, 萤火虫算法

Abstract: This study constructs a water quality inversion model based on mathematical statistics and machine learning methods by combining water quality parameters, spectral data collected on June 15, 2023, and synchronous Sentinel-2 imagery data to quantitatively invert the Chl-a concentration in Luoma Lake. Through comparative analysis, the model with the best performance is selected to analyze the Chl-a status in Luoma Lake. The study found that Chl-a shows a high correlation with the B5 and B9 bands of the Sentinel-2 imagery, and this correlation is further enhanced after band combination processing. In the Chl-a inversion model, the FA-SVR model demonstrates the highest accuracy (R2=0.86, RMSE=2.77, MAE=2.10) compared to traditional mathematical statistical regression models and other machine learning models (FA-RF, FA-XGBoost). The inversion results reveale that the nearshore area in the northeastern part of Luoma Lake has higher Chl-a concentrations, which may be related to the presence of fishpond farming and high eutrophication in the northern waters. This study highlights the significant application value of machine learning technology in improving the accuracy of water quality remote sensing inversion, provides important technical support for water quality monitoring and management in Luoma Lake.

Key words: Luoma Lake, Chlorophyll-a concentration, remote sensing inversion, machine learning, firefly algorithm

中图分类号: