|
|
|
|
|
|
Inland Water Chemical Oxygen Demand Estimation Based on Improved SVR for Hyperspectral Data |
SHENG Hui1, CHI Hai-xu1, XU Ming-ming1*, LIU Shan-wei1, WAN Jian-hua1, WANG Jin-jin2 |
1. College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, China
2. Zhuhai Orbita Aerospace Science & Technology Co., Ltd., Zhuhai 519080, China |
|
|
Abstract Hyperspectral data can capture the spectral changes caused by different concentrations of chemical oxygen demand (COD) in inland water bodies, and it is important to study the relationship between spectrum and COD concentrations for COD estimation. Support Vector Regression (SVR) model has the advantages of being suitable for small samples and good generalization ability, but it is difficult to select a parameter and prone to fall into the local extremum. In order to solve this problem, this study introduced Simulated Annealing-Particle Swarm Optimization (SA-PSO) into the parameter optimization process of SVR and proposed an improved SVR (SA-PSO-SVR) method to estimate the inland waters COD. This paper takes the Weihe River Basin as the research area, obtained the COD concentrations and spectral curves through field measurement. The sensitive band was determined by analyzing the response of spectral reflectance to COD at first in this paper, and the Simulated Annealing-Particle Swarm Optimization (SA-PSO) was introduced into the parameter optimization process of Support Vector Regression (SVR) to established an inversion model between the cod concentration and the sensitivity factor. The Orbita Hyper Spectral (OHS) hyperspectral data was used to verify the accuracy, and the distribution of COD concentration was obtained at last. Through spectral analysis, it can be seen that the measured above-surface spectra in this area demonstrated typical spectral signatures of second-class water, and the shape of the spectrum curve shows obvious double-peak characteristics. When the concentration increases, the reflection peak tends to move to the short wavelength direction and the reflection valley to the long wavelength direction. The Pearson’s correlation coefficient was used to analyze COD concentration and the spectral, the result showed that the best inversion factors are four band combinations of 518 nm/940.4 nm, 623.6 nm/636.8 nm, 729.2 nm/890.9 nm and 752.3 nm/857.9 nm. The model established by the SA-PSO-SVR method is accurate compared with models established by SVR, Back Propagation neural network, and linear regression method. The Mean-Relative-Error (MRE) and Root-Mean-Square-Error (RMSE) of the COD estimation model established by the SA-PSO-SVR method are 1.62% and 2.99 mg·L-1 (R2=0.86), respectively. The optimal model established by the measured water surface spectra was applied to the hyperspectral satellite image. The RMSE and MRE are 4.47 mg·L-1 and 11.87% respectively. The obtained COD inversion results of the Weihe-Xiashan reservoir area show: the overall concentration of COD is between 17 and 42 mg·L-1, and COD concentration in the Hanxinba, the northeast region of XiaShan Reservoir, the confluence of the Qu River into the Wei River are higher than other waters. The experimental results show that SA-PSO-SVR is a feasible approach for the COD inversion of hyperspectral data, providing a reference for water resources management in the Weihe River Basin.
|
Received: 2020-10-22
Accepted: 2021-02-16
|
|
Corresponding Authors:
XU Ming-ming
E-mail: xumingming@upc.edu.cn
|
|
[1] Gholizadeh M H, Melesse A M,Reddi L. Sensors, 2016, 16(8): 43.
[2] Bernardo N, Carmo A,Park E. Remote Sensing, 2019, 11(9): 22.
[3] Shen M, Duan H T,Cao Z G. Remote Sensing of Environment, 2020, 247: 17.
[4] Agrawal R K, Bawane Narendra G. Applied Soft Computing Journal, 2015, 28:217.
[5] Hafeez S, Wong M S,Ho H C,et al. Remote Sensing, 2019, 11(6): 23.
[6] Garcia-Nieto P J, Garcia-Gonzalo E, Sanchez L F,et al. Journal of Computational and Applied Mathematics,2020, 366:19.
[7] Li N, Zhu X F,Pan Y Z,et al. Journal of Remote Sensing, 2018, 22(4):559.
[8] Kahru M, Kudela R M,Anderson C R,et al. IEEE Geoscience and Remote Sensing Letters, 2015, 12(11): 2282.
[9] Bioucas-Dias J M, Plaza A,Camps-Valls G,et al. IEEE Geoscience and Remote Sensing Letters, 2013, 1(2): 6.
[10] Babankumar B, Rangoli S, Ritula T. Spatial Information Research, 2018, 26(2): 203.
[11] CHEN Yao, HUANG Chang-ping,ZHANG Li-fu,et al(陈 瑶,黄长平,张立福,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2020, 40(3): 824.
[12] Pyo J C, Duan H T,Ligaray M,et al. Remote Sensing, 2020, 12(7): 23.
[13] Gursoy O, Atun R. Polish Journal of Environmental Studies, 2019, 28(4): 2139.
[14] Ansari M, Akhoondzadeh M. Advances in Space Research, 2020, 65(5): 1490.
[15] El-Rawy M,Fathi H,Abdalla F. Environmental Geochemistry and Health, 2019, 42(7): 2101. |
[1] |
HUANG You-ju1, TIAN Yi-chao2, 3*, ZHANG Qiang2, TAO Jin2, ZHANG Ya-li2, YANG Yong-wei2, LIN Jun-liang2. Estimation of Aboveground Biomass of Mangroves in Maowei Sea of Beibu Gulf Based on ZY-1-02D Satellite Hyperspectral Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3906-3915. |
[2] |
LIU Fei1, TAN Jia-jin1*, XIE Gu-ai2, SU Jun3, YE Jian-ren1. Early Diagnosis of Pine Wilt Disease Based on Hyperspectral Data and Needle Resistivity[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 3280-3285. |
[3] |
LI Xin1, LIU Jiang-ping1, 2*, HUANG Qing1, HU Peng-wei1, 2. Optimization of Prediction Model for Milk Fat Content Based on Improved Whale Optimization Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2779-2784. |
[4] |
YANG Liu1, GUO Zhong-hui1, JIN Zhong-yu1, BAI Ju-chi1, YU Feng-hua1, 2, XU Tong-yu1, 2*. Inversion Method Research of Phosphorus Content in Rice Leaves Produced in Northern Cold Region Based on WPA-BP[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(05): 1442-1449. |
[5] |
ZHAO Ting-ting1, 3, WANG Ke-jian1, 3*, SI Yong-sheng1, 3, SHU Ying2, HE Zhen-xue1, 3, WANG Chao1, 3, ZHANG Zhi-sheng2*. Freshness Detection of Lamb Based on AW-OPS Hyperspectral
Wavelength Selection Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 830-837. |
[6] |
LI Wen, CHEN Yin-yin*, LUO Xue-ke, HE Na. Research on Testing NH3-N and COD in Water Quality Based on
Continuous Spectroscopy Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 254-259. |
[7] |
ZHANG Yan1, 2, 3,WU Hua-rui1, 2, 3,ZHU Hua-ji1, 2, 3*. Hyperspectral Latent Period Diagnosis of Tomato Gray Mold Based on TLBO-ELM Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2969-2975. |
[8] |
WANG Chun-ling1, 2, SHI Kai-yuan1, 2, MING Xing3*, CONG Mao-qin3, LIU Xin-yue3, GUO Wen-ji3. A Comparative Study of the COD Hyperspectral Inversion Models in
Water Based on the Maching Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2353-2358. |
[9] |
ZHOU Ming-rui1, 2, QU Jiang-bei2, LI Peng1, 2*, HE Yi-liang1, 2. The “Cluster-Regression” COD Prediction Model of Distributed Rural Sewage Based on Three-Dimensional Fluorescence Spectrum and
Ultraviolet-Visible Absorption Spectrum[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(07): 2113-2119. |
[10] |
ZHENG Yi1, 2, 3, WANG Yao1, 2, LIU Yan1, 2*. Study on Classification and Recognition of Mountain Meadow Vegetation Based on Seasonal Characteristics of Hyperspectral Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(06): 1939-1947. |
[11] |
JING Xia1, ZHANG Jie1, 2, WANG Jiao-jiao2, MING Shi-kang2, FU You-qiang3, FENG Hai-kuan2, SONG Xiao-yu2*. Comparison of Machine Learning Algorithms for Remote Sensing
Monitoring of Rice Yields[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1620-1627. |
[12] |
CHEN Mei-chen, YU Hai-ye, LI Xiao-kai, WANG Hong-jian, LIU Shuang, KONG Li-juan, ZHANG Lei, DANG Jing-min, SUI Yuan-yuan*. Response Analysis of Hyperspectral Characteristics of Maize Seedling Leaves Under Different Light and Temperature Environment[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3545-3551. |
[13] |
YANG Bao-hua, GAO Zhi-wei, QI Lin, ZHU Yue, GAO Yuan. Prediction Model of Soluble Solid Content in Peaches Based on Hyperspectral Images[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3559-3564. |
[14] |
ZHANG Yan-jun, KANG Cheng-long, LIU Ya-qian, FU Xing-hu*, ZHANG Jin-xiao, WANG Ming-xue, YANG Liu-zhen. Rapidly Detection of Total Nitrogen and Phosphorus Content in Water by Surface Enhanced Raman Spectroscopy and GWO-SVR Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(10): 3147-3152. |
[15] |
DAI Yuan1, XIE Ji-zheng1, YUAN Jing1, SHEN Wei1, GUO Hong-da1, SUN Xiao-ping1, WANG Zhi-gang2*. Application of Excitation-Emission Matrix (EEM) Fluorescence Combined With Linear SVM in Organic Pollution Monitoring of Water[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(09): 2839-2845. |
|
|
|
|