基于SSA-BP-SVM模型的云龙湖水质反演研究
作者:
作者单位:

江苏省水文水资源勘测局徐州分局

中图分类号:

X87


Water Quality Retrieval of Yunlong Lake Based on SSA-BP-SVM Model
Author:
Affiliation:

Xu zhou Hydrology and Water Resources Survey Bureau of Jiangsu Province

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    目前利用遥感技术及时准确的进行水质监测全面的了解水质分布情况对水环境保护具有重要意义。然而水质参数与地表反射率并非简单的线性关系,BP神经网络和SVM因其非线性模拟的特点,被广泛用于水质反演。但是传统BP神经网络存在收敛缓慢、容易陷入局部最优的问题;SVM虽然具有很好的拟合能力,但受惩罚系数及核函数参数影响较大。因此以云龙湖为研究区域,利用Sentinel-2影像和实测数据,针对重要水质参数电导率和浊度,提出了一种基于麻雀搜索算法(SSA)优化BP神经网络及SVM的水质反演耦合模型,利用SSA对BP神经网络及SVM进行参数寻优,基于验证集MAE计算模型权重,对SSA-BP、SSA-SVM模型测试组输出层加权计算后获得最终反演结果。并与BPNN、SVM、SSA-BP、SSA-SVM模型进行了对比实验。结果表明:(1)Sentinel-2影像对电导率及浊度的敏感波段均为可见光及短波红外波段。(2)SSA-BP-SVM水质反演耦合模型精度更高,电导率及浊度反演模型R2分别为0.92、0.89。(3)云龙湖具有典型的城市水体特征,电导率受上游南望净水厂排水影响较大,浊度受社会生产活动带来的颗粒污染物影响较大。基于Sentinel-2影像利用SSA-BP-SVM模型进行水质反演具有较好的应用潜力,能够为云龙湖水质监测以及制定保护措施提供一定的技术支撑。

    Abstract:

    At present, the use of remote sensing technology in a timely and accurate monitoring of water quality, a comprehensive understanding of the distribution of water quality is of great significance to the protection of water environment.However, the relationship between water quality parameters and surface reflectance is not simple linear. BP neural network and SVM are widely used in water quality inversion because of their nonlinear simulation characteristics.However, the traditional BP neural network has the problems of slow convergence and easy to fall into local optimum. Although SVM has good fitting ability, it is greatly affected by penalty coefficient and kernel function parameter.Therefore, taking Yunlong Lake as the study area, using Sentinel-2 image and measured data, aiming at the important water quality parameters of conductivity and turbidity, a water quality inversion coupling model based on sparrow search algorithm (SSA) to optimize BP neural network and SVM was proposed. SSA was used to optimize the parameters of BP neural network and SVM, the model weight was calculated based on verification set MAE, and the final inversion result was obtained after the weighted calculation of output layer of SSA-BP and SSA-SVM model test group.And compared with BPNN, SVM, SSA-BP, SSA-SVM model.The results show that: (1) The sensitive bands of Sentinel-2 image to conductivity and turbidity are visible light and short wavelength infrared.(2) that precision of the couple model of SSA-BP-SVM is higher, and the R2 of the inversion model of conductivity and turbidity are 0.92 and 0.89 respectively.(3) the yunlong lake has the typical characteristics of urban water body, conductivity is greatly affected by the upstream of the south at water treatment plant drainage, turbidity is greatly affected by the social production activities of particulate pollutants.The SSA-BP-SVM model based on Sentinel-2 image has a good application potential in water quality inversion, which can provide a certain technical support for water quality monitoring and protection measures of Yunlong Lake.

    参考文献
    [1] 周婷,刘小妮,戚王月,等.基于GF_1 卫星影像的巢湖蓝藻时空演变特征分析[J].华北水利水电大学学报(自然科学版),2020,41( 3):62-66.Zhou Ting, Liu Xiaoni, Qi Wangyue, et al. Temporal and spatial evolution characteristics of cyanobacteria in Chaohu Lake based on GF_1 satellite images [J]. Journal of North China University of Water Resources and Electric Power (Natural Science Edition), 2020, 41 ( 3):62-66.
    [2] 王歆晖,田华,季铁梅,等.哨兵2卫星综合水质指标的河流水质遥感监测方法[J].上海航天(中英文),2020,37(5):92-97+104.ang XH, Tian H, Ji TM, et al. Remote sensing monitoring method of river water quality based on Sentinel-2 satellite integrated water quality index [J]. Shanghai Aerospace, 2020, 37 (5):92-97+104.
    [3] 梁文广,蒋志昊,王金东,等.长荡湖叶绿素浓度卫星遥感反演研究[J].江苏水利,2021,8:19-22.iang WG, Jiang ZH, Wang JD, et al. Retrieval of chlorophyll concentration in Changdang Lake by satellite remote sensing [J]. Jiangsu Water Conservancy, 2021, 8:19-22.
    [4] 马方凯,高兆波,叶帮玲.基于高分遥感卫星影像的汤逊湖水质遥感反演[J].水利信息化,2021,5:69-75.a Fangkai, Gao Zhaobo, Ye Bangling. Remote sensing retrieval of water quality in Tangxun Lake based on high-resolution remote sensing satellite images [J]. Water Resources Informatization, 2021, 5:69-75.
    [5] 谭小琴,罗勇,赵铮,等.基于高分遥感的河流水质反演研究—以金马河温江段为例[J].环境生态学,2020,2(7):29-36.an XQ, Luo Y, Zhao Z, et al. River water quality retrieval based on high-resolution remote sensing-a case study of Wenjiang section of Jinma River [J]. Environmental Ecology, 2020, 2 (7):29-36.
    [6] 张怡,冯萱,王硕,等.基于BP人工神经网络的红旗泡水库富营养化评价[J].环境生态学,2022.4(9):103-107.hang Yi, Feng Xuan, Wang Shuo, et al. Eutrophication assessment of Hongqipao reservoir based on BP artificial neural network [J]. Environmental Ecology, 2022. 4 (9):103-107.
    [7] GOGU R, CARABIN G, HALLET V, et al. GIS-based hydrogeological databases and groundwater modelling[J]. Hydrogeology Journal, 2001, 9(6): 555-569.
    [8] 王喆,连炎清,李晓娜,等.基于机器学习的浐灞河水质参数遥感反演研究[J]人民长江, 2022,53(9):13-18.ang Z, Lian YQ, Li XN, et al. Remote sensing retrieval of water quality parameters of Chanba River based on machine learning [J] People''s Yangtze River, 2022,53(9):13-18.
    [9] 李慧,周轶成.未确知测度BP神经网络模型在黑河流域水质预测中的应用[J].水文,2014,34(3):66-69.i Hui, Zhou Yicheng. Application of unascertained measure BP neural network model in water quality prediction of Heihe River basin [J]. Hydrology, 2014, 34 (3):66-69.
    [10] 马振,周密.聚类分析在秦淮河水质指标相关性研究中的应用[J]水文,2018.38(1):77-80.a Zhen, careful. Application of cluster analysis in correlation study of water quality indexes of Qinhuai River [J] Hydrology, 2018.38 (1):77-80.
    [11] 玉芹,汪西莉,蒋赛.渭河水质遥感反演的人工神经网络模型研究[J].遥感技术与应用,2009,24(1):63-67.u Qin, Wang Xili, Jiang Sai. Study on artificial neural network model for remote sensing inversion of Weihe River water quality [J]. Remote Sensing Technology and Application, 2009, 24 (1):63-67.
    [12] VAPNIK V. The nature of statistical learning theory[M]. NewYork:Springer-Verlag New York,1995.
    [13] 王海峰,行鸿彦,陈梦,等.基于SSA-SVM 的海杂波背景下小信号检测方法[J]电子测量与仪器学报 2022,36(4):24-31.ang Haifeng, Xing Hongyan, Chen Meng, et al. Small signal detection in sea clutter based on SSA-SVM [J] Chinese Journal of Electronic Measurement and Instrumentation, 2022, 36 (4):24-31.
    [14] 崔东文,郭荣.HTS算法与GRNN、SVM耦合模型在径流预测中的应用[J].华北水利水电大学学报(自然科学版),2018,39(5):73-81.ui Dongwen, Guo Rong. Application of HTS algorithm and GRNN/SVM coupling model in runoff prediction [J]. Journal of North China University of Water Resources and Electric Power (Natural Science Edition), 2018, 39 (5):73-81.
    [15] 孟彩霞,吴迪,雷雨,等.基于麻雀搜索算法优化的BP神经网络卫星钟差预报[J].大地测量与地球动力学,2022,42(2):125-131.eng Caixia, Wu Di, Lei Yu, et al. Satellite clock bias prediction based on BP neural network optimized by sparrow search algorithm [J]. Geodesy and Geodynamics, 2022, 42 (2):125-131.
    [16] XUE J K,SHEN B A, novel swarm intelligence optimization approach:sparrow search algorithm[J].Systems Science Control Engineering,2020,8(1):22-34.
    [17] 吴欢欢,国巧真,臧金龙,等.基于Landsat8与实测数据的水质参数反演研究[J]遥感技术与应用,2021,36(4):898-907.u Huanhuan, Guo Qiaozhen, Zang Jinlong, et al. Retrieval of water quality parameters based on Landsat8 and observed data [J] Remote Sensing Technology and Application, 2021, 36 (4):898-907.
    [18] 吕富强,唐诗华,张炎,等.SSA-BP神经网络在无人机点云孔洞修补的应用[J].测绘通报,2023(5):130-134.ü Fuqiang, Tang Shihua, Zhang Yan, et al. Application of SSA-BP neural network in UAV point cloud hole repair [J]. Bulletin of Surveying and Mapping, 2023 (5):130-134.
    [19] 郝婧,刘强.基于SSA-SVM模型的台风风暴潮灾害损失评估[J]海洋地质前沿,2022,38(11):65-72.ao Jing, Liu Qiang. Loss assessment of typhoon storm surge disaster based on SSA-SVM model [J] Frontiers of Marine Geology, 2022, 38 (11):65-72.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

任中杰.基于SSA-BP-SVM模型的云龙湖水质反演研究[J].南京信息工程大学学报,,():

复制
分享
文章指标
  • 点击次数:86
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2023-06-07
  • 最后修改日期:2023-08-08
  • 录用日期:2023-08-10

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司