长江流域资源与环境 >> 2024, Vol. 33 >> Issue (1): 102-113.doi: 10.11870/cjlyzyyhj202401009

• 自然资源 • 上一篇    下一篇

小样本下大冶湖非光学活性水质参数反演与时空变化分析

黄振辉1,杨小红1*,王力哲1,厉芳婷2,3,刘君3,4,刘新龙5,王玲玲6   

  1. (1.中国地质大学(武汉)计算机学院,湖北 武汉 430074; 2.武汉大学测绘遥感信息工程国家重点实验室,湖北 武汉 430079;3.湖北省测绘工程院,湖北 武汉 430074; 4.湖北省自然资源厅,湖北 武汉 430071; 5.武汉中地数字孪生技术有限公司,湖北 武汉 430074;6.湖北省生态环境科学研究院,湖北 武汉 430072)
  • 出版日期:2024-01-20 发布日期:2024-02-01

Inversion and Spatiotemporal Variation of Non-optically Active Water Quality Parameters in Daye Lake With Small Samples

HUANG Zhen-hui1,YANG Xiao-hong1,WANG Li-zhe1,LI Fang-ting2,3,LIU Jun3,4, LIU Xin-long5,WANG Ling-ling6   

  1. (1. College of Computer Science, China University of Geosciences, Wuhan 430074,China;2.State Key Laboratory of Information Engineering in Surverying,Mapping and Remote Sensing, Wuhan University, Wuhan 430079,China;3. Hubei Institute of Surveying and Mapping Engineering, Wuhan 430074,China;4. Department of Natural Resource of Hubei Province, Wuhan 430071,China;5. Wuhan Zhongdi Digital Twin Technology Co., LTD, Wuhan 430074,China;6. Hubei Provincial Academy of Eco-Environmental Sciences, Wuhan 430072,China)

  • Online:2024-01-20 Published:2024-02-01

摘要: 遥感技术为内陆湖泊水质监测提供了极大的便利,但是由于非光学活性水质参数在复杂的内陆水体生物光学环境中,很难直接找到其光学特性,导致这类参数的实测水质数据与遥感反射率之间难以用简单的回归模型拟合,尤其是在实测水质样本量较小时,传统机器学习容易出现欠拟合的现象,反演精度难以保证。针对非光学活性水质参数在反演中数据量较小、拟合困难等问题,提出了一种基于点积注意力模型的水质反演方法,通过58个水质实测数据和Sentinel-2遥感数据构建了点积注意力模型,实现大冶湖遥感水质反演。在同样的样本和影像数据下,对比了基于统计回归模型和多层感知机模型的遥感水质反演。实验表明,点积注意力模型的非光学活性水质参数浓度反演的准确性较高,总磷、总氮、高锰酸盐指数的决定系数R2分别能达到0.83,0.89,0.80。最后,将提出的模型运用到大冶湖非光学活性水质参数反演中,对该湖泊2018~2021年总磷、总氮、高锰酸盐指数3种非光学活性水质参数进行反演,统计并分析了近4年大冶湖水质参数浓度的时空变化特征,对大冶湖的营养状态进行了综合评价,为大冶湖水环境治理提供重要数据支撑。

Abstract: Remote sensing technology provides great convenience for monitoring water quality of inland lakes. However, it is difficult to directly find the optical characteristics of certain optically inactive water quality parameters, such as Total Phosphorus (TP), Total Nitrogen (TN) and permanganate index (CODMn). In the complex biological optical environment of inland waters, it is usually hard to fit the measured water quality data with the remote sensing reflectance of such parameters using a simple regression model. Moreover, when the size of measured water quality data sample is small, traditional machine learning methods are prone to under fitting, resulting a low accuracy of water quality inversion results. To address these problems, this paper proposed a dot product attention model for estimating water quality parameters. The model was constructed using 58 measured water quality data and the corresponding Sentinel-2 remote sensing data, in Daye Lake. To verify the accuracy and priority of the proposed model, this paper compared the results with the water quality inversion results of statistical regression model and multi-layer perceptron model under the same measured water quality data sample and image data. Results showed that the accuracy of the inversion results based on the dot product attention model were the best, with the determination coefficients R2 of TP, TN and CODMn of 0.83, 0.89 and 0.80, respectively. The proposed model was also employed to estimate TP, TN and CODMn in Daye Lake from 2018-2021. These results help to explore the spatial and temporal variation characteristics of the water quality parameter concentrations in Daye Lake in the past four years and assess  the water pollution situation in Daye Lake. This research is expected to provide important data support for the water environment management of Daye Lake.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 姚琳, 沈竞, 温新龙, 高超. WRF模式参数化方案对江西山地风电场的风模拟研究[J]. 长江流域资源与环境, 2018, 27(07): 1380 .
[2] 孙惠惠, 章新平, 罗紫东, 尚程鹏, 贺新光, 饶志国.  近53 a来长江流域极端降水指数特征[J]. 长江流域资源与环境, 2018, 27(08): 1879 .
[3] 方琳, 吴凤平, 王新华, 余燕团.  

基于共同前沿SBM模型的农业用水效率测度及改善潜力 [J]. 长江流域资源与环境, 2018, 27(10): 2293 -2304 .

[4] 刘冀, 孙周亮, 张特, 程雄, 董晓华, 谈新. 基于不同卫星降雨产品的澴水花园流域径流模拟比较研究[J]. 长江流域资源与环境, 2018, 27(11): 2558 -2567 .
[5] 谢五三, 吴 蓉, 丁小俊. 基于FloodArea模型的城市内涝灾害风险评估与预警[J]. 长江流域资源与环境, 2018, 27(12): 2848 -2855 .
[6] 刘晓阳 黄晓东 丁志伟. 长江经济带县域信息化水平的空间差异研究[J]. 长江流域资源与环境, , (): 0 .
[7] 吕乐婷, 王晓蕊, 孙才志, 张 杰. 基于SWAT模型的细河流域蓝水绿水资源量时空分布研究[J]. 长江流域资源与环境, 2019, 28(01): 39 -47 .
[8] 李艳, 马百胜, 杨宣. 两类ENSO事件对中国东部地区极端降水的影响[J]. 长江流域资源与环境, 2019, 28(02): 469 -482 .
[9] 秦欢欢 孙占学 高柏. 农业节水和南水北调对华北平原可持续水管理的影响[J]. 长江流域资源与环境, , (): 0 .
[10] 柯杭, 王小军, 尹义星, 罗志文, . 衡水市1961~2015年极端降水和干旱的时空变化特征[J]. 长江流域资源与环境, 2019, 28(04): 971 -980 .