|
|
|
|
|
|
| Retrieval Model for Water Quality Parameters of Miyun Reservoir Based on UAV Hyperspectral Remote Sensing Data and Deep Neural Network
Algorithm |
| QIAO Zhi1, JIANG Qun-ou1, 2*, LÜ Ke-xin1, GAO Feng1 |
1. School of Soil and Water Conservation, Beijing Forestry University, Beijing 100038, China
2. Key Laboratory of Soil and Water Conservation and Desertification Prevention, Beijing Forestry University, Beijing 100083, China
|
|
|
|
|
Abstract With the rapid development of industrialization and social economy, water pollution and deterioration of water sources are increasingly aggravated, and effective water quality monitoring is an important prerequisite for water source protection. Miyun Reservoir is an important surface water source in Beijing, which plays an important role in protecting water safety in the capital. In order to monitor the water quality parameters and pollution degree of Miyun Reservoir more accurately, this study used four phases of UAV hyperspectral remote sensing data to construct a water quality parameter retrieval model based on a deep neural network algorithm. Total nitrogen (TN) and total phosphorus (TP) water quality parameters in Miyun Reservoir were retrieved. Firstly, the hyperspectral image dimensionality reduction processing based on the recursive feature elimination method was used, and the spectral data and groundwater quality monitoring data were superimposed. The network structure parameters, such as the number of hidden layers and the number of ganglion points, were determined by minimizing the error in the training process. Then, the migration method gradually expanded the network from knowledge source domain to network, and the water quality parameters of TN and TP concentration in Miyun reservoir were trained and verified. Finally, the water quality parameters of Chaohe Dam and Baihe Dam in Miyun Reservoir were retrieved to reveal the spatio-temporal evolution of the main water quality parameters. The results show that ① the R2 of the TN and TP concentration retrieval models constructed in this study are 0.835 5 and 0.770 3, and the MSE is 0.015 3 and 0.000 8. The Ensemble Deep Belief Network (EDBN) model based on random subspace has a better retrieval effect on water quality parameters. ②TN concentration in Miyun Reservoir fluctuates with seasons, with a low concentration in summer and a relatively high concentration in autumn. The change in TP concentration is relatively stable, indicating that the control effect of phosphorus pollution in the surrounding area of Miyun Reservoir is good.③The water quality of the Baihe Dam was better than that of the Chaohe Dam. The seasons obviously affected the changes of the former, while the latter was significantly affected by human activities. The TN concentration of Miyun reservoir was in Class III, and the TP was generally in Class II. The water quality can meet the standards of drinking water sources, but it is still necessary to strengthen the supervision of nitrogen and phosphorus pollution. These results will provide an important scientific basis for efficiently monitoring water quality and water resources protection in the Miyun reservoir.
|
|
Received: 2022-09-29
Accepted: 2023-07-25
|
|
|
|
Corresponding Authors:
JIANG Qun-ou
E-mail: jiangqo.dls@163.com
|
|
[1] XU Er-qi, ZHANG Hong-qi(许尔琪, 张红旗). Chinese Journal of Applied Ecology(应用生态学报), 2018, 29(9): 2869.
[2] GAO Yang, WANG Xiao-yue, ZHANG Bai-lin, et al(高 阳, 王晓玥, 张佰林, 等). Acta Ecologica Sinica(生态学报) , 2018, 38(5): 1668.
[3] WU Huan-huan, GUO Qiao-zhen, ZANG Jin-long, et al(吴欢欢, 国巧真, 臧金龙, 等). Remote Sensing Technology and Application(遥感技术与应用), 2021, 36(4): 898.
[4] Kim Y H, Im J, Ha H K. GIScience & Remote Sensing, 2014, 51(2): 158.
[5] MENG Miao-miao, ZHENG Xiang-yang, XING Qian-guo, et al(孟苗苗, 郑向阳, 邢前国, 等). Journal of Tropical Oceanography(热带海洋学报), 2022, 41(3): 46.
[6] Castro C C, Gomez J A D, Martin J D, et al. Remote Sensing, 2020, 12(9): 1514.
[7] Van Donkelaar A, Martin R V, Brauer M, et al. Environmental Science & Technology, 2016, 50(7): 3762.
[8] YAO Jun-yang, XU Ji-ping, WANG Xiao-yi, et al(姚俊杨, 许继平, 王小艺, 等). Computers and Applied Chemistry(计算机与应用化学), 2015, 32(10): 1265.
[9] MA Feng-kui, JIANG Qun-ou，XU Li-dan, et al(马丰魁, 姜群鸥, 徐藜丹, 等). Ecology and Environmental Sciences(生态环境学报), 2020, 29(3): 569.
[10] Jiang Q, Xu L, Sun S, et al. Ecological Indicators, 2021, 124(18): 107356.
[11] ZHANG Xin, ZHAO Long, LI Ya-nan, et al(张 新, 赵 龙, 李亚楠, 等). Beijing Water(北京水务), 2021，(2): 21.
[12] Demarchi L, Kania A, Cikowski W et al. Remote Sensing, 2020, 12(11): 1842.
[13] JI Zhen-xing, KONG Fan-qiang(计振兴, 孔繁锵). Acta Photonica Sinica(光子学报), 2012, 41(1): 82.
[14] JIANG Hui, ZHOU Wen-bin, LIU Xiao-zhen(江 辉, 周文斌, 刘小真). Ecology and Environmental Science(生态环境学报), 2010，(12): 2948.
[15] Niu G, Yi X, Chen C, et al. Journal of Cleaner Production, 2020, 265: 121787.
[16] Zhang T, Fell F, Liu Z, et al. Journal of Geophysical Research，2003, 108：3286.
[17] WANG Meng-qi, ZHANG Wen, MENG Ling-kui(王梦琦, 张 文, 孟令奎). Journal of Geomatics(测绘地理信息), 2022, 47(4): 100.
[18] ZHANG Yu-hang, SUN Chang-hong, FAN Qing, et al(张雨航, 孙长虹, 范 清, 等). Journal of Arid Land Resources and Environment(干旱区资源与环境), 2021, 35(8): 10.
[19] QIN Li-huan, ZENG Qing-hui, LI Xu-yong, et al(秦丽欢, 曾庆慧, 李叙勇, 等). Chinese Journal of Ecology(生态学杂志), 2017, 36(3): 8.
|
| [1] |
XIAO Bin1, 2, HE Hong-chang1, DOU Shi-qing1*, FAN Dong-lin1, FU Bo-lin1, ZHANG Jie1, XIONG Yuan-kang1, SHI Jin-ke1. A Fine Classification Method of Citrus Fruit Trees Based on UAV
Hyperspectral Images and SULOV_XGBoost Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(02): 548-557. |
| [2] |
ZOU Yu-bo1, 2, MA Zhen-yu1, JIAO Qing-bin1, XU Liang1, PEI Jian1, 2, LI Yu-hang1, 2, XU Yu-xing1, 2, ZHANG Jia-hang1, 2, LI Hui1, 2, YANG Lin1, 2, LIU Si-qi1, 2, ZHANG Wei1, 2, TAN Xin1*. Comparative Study on Hyperspectral Inversion Models of Water
Quality Parameters[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 949-954. |
| [3] |
YANG Xin1, 2, YUAN Zi-ran1, 2, YE Yin1, 2*, WANG Dao-zhong1, 2, HUA Ke-ke1, 2, GUO Zhi-bin1, 2. Winter Wheat Total Nitrogen Content Estimation Based on UAV
Hyperspectral Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3269-3274. |
| [4] |
LIN Jian-yuan1, ZHANG Chang-xing2*, YOU Hong-jian3. Retrieval of Water Quality Parameters of Urban River Network Using Hyperspectral Date Based on Inherent Optical Parameters[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(12): 3761-3768. |
|
|
|
|
