基于FOD和最优光谱特征的高光谱水质参数反演模型

doi:10.3964/j.issn.1000-0593(2025)03-0842-10

Abstract
References
Related Citation (15)

Download: PDF (6781 KB)
Export: BibTeX | EndNote (RIS)

Abstract Accurate and efficient acquisition of chlorophyll-a (Chl-a) concentration in water is the prerequisite for improving eutrophication and sustainable development of water bodies. This study used the hyperspectral reflectance of the water surface and the measured Chl-a water concentration as data sources. The original spectral reflectance was processed with a step size 0.1 by fractional order differentiation (FOD) technology. The characteristic bands were screened by exploring the correlation between the spectral data and the Chl-a concentration of the water body, and the variable-order spectral dataset was constructed. The Partial Least Squares (PLS) model was used to screen the optimal features to construct the dataset, which was divided into modeling set and verification set according to the ratio of 7∶3, and the support vector machines (SVM) and deep forest (DF) models were used to establish the water Chl-a concentration inversion model. It is also compared with the model constructed using the original data and the model constructed by common dimensionality reduction methods. The results show that FOD technology can reduce hyperspectral noise, mine potential spectral information to a certain extent, and improve the correlation between hyperspectral reflectance and the concentration of Chl-a in water. Compared with the Chl-a inversion model established by using the original data and PCA dimension reduction, the R² of the water Chl-a concentration inversion model established by FOD combined with PLS first screening features was increased, and the mean square error (MSE) and mean absolute error (MAE) were reduced. DF has a higher degree of fitting and prediction accuracy than the other three models, with R²=0.96, MSE=0.51 μg·L^-1, and MAE=0.64 μg·L^-1. The validation set R²=0.89, MSE=0.69 μg·L^-1, MAE=0.64 μg·L^-1. In general, it is feasible to establish a water Chl-a concentration inversion model based on the variable-order spectral dataset after FOD recombination and the preferred features of PLS. Comparative analysis of the inversion results of other models shows that DF has a good inversion effect on water Chl-a. This work provides a theoretical basis and technical support for the inversion of hyperspectral remote sensing of Chl-a in inland second-class water bodies, helps the continuous monitoring of water quality in Baiyangdian Lake, and also provides new ideas for the inversion of Chl-a from hyperspectral satellite remote sensing images in the future.

Key words：Chlorophyll a inversion;Fractional differential;Partial least squares;Deep forest;Hyperspectral spectrum

Received: 2024-01-26 Accepted: 2024-07-24

ZTFLH:

TP79

Corresponding Authors: ZHAO Qi-chao E-mail: theoddone1987@163.com

Cite this article:

ZHANG Yu-qing,ZHAO Qi-chao,LIU Qi-yue, et al. Inversion Model of Hyperspectral Water Quality Parameters Based on FOD and Optimal Spectral Characteristics[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(03): 842-851.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)03-0842-10 OR https://www.gpxygpfx.com/EN/Y2025/V45/I03/842

[1] ZHANG Xiao-chun, DAI Dan, QIN Cheng，et al(张小春，代丹，秦成，等). Journal of Hydroecology(水生态学杂志)，2023，44(5)：107.
[2] ZHANG Hao，SHI Xiao-hong，ZHAO Sheng-nan，et al(张昊，史小红，赵胜男，等). Wetland Science(湿地科学)，2023，21(6)：842.
[3] DIAO Chao, SANG Guo-qing, PENG Tao, et al(刁超，桑国庆，彭涛，等). Journal of University of Jinan (Science and Technology)[济南大学学报(自然科学版)]，2023，37(4): 408.
[4] GUAN Cheng, LIU Ya-hui, ZHANG Qing-wen, et al(管铖，刘雅辉，张清文，等). Journal of Chifeng University (Natural Science Edition)[赤峰学院学报(自然科学版)]，2023，39(10): 51.
[5] PENG Jun-jie, WANG Hong, WANG Yu, et al(彭俊杰，汪泓，王宇，等). Jiangsu Agricultural Sciences(江苏农业科学)，2024，52(7)：184.
[6] WEN Jian-guang，XIAO Qing，YANG Yi-peng，et al(闻建光, 肖青, 杨一鹏, 等). Advances in Water Science(水科学进展)，2007，18(2)：270.
[7] LÜ Heng，LI Xin-guo，ZHOU Lian-yi，et al(吕恒，李新国，周连义，等). Journal of Lake Sciences(湖泊科学)，2006，18(4)：349.
[8] SHEN Wei，JI Qian，QIU Yao-wei，et al(沈蔚，纪茜，邱耀炜，等). Journal of Hydroecology(水生态学杂志)，2021，42(3)：1.
[9] HUANG Yao-huan，JIANG Dong，ZHUANG Da-fang，et al(黄耀欢，江东，庄大方，等). Journal of Natural Disasters(自然灾害学报)，2012，21(2)：215.
[10] HAN Bao-hui，ZHAO Qi-chao，CHANG Rong，et al(韩宝辉，赵起超，常荣，等). Journal of Geo-information Science(地球信息科学学报)，2023，25(9)：1882.
[11] ZHANG Lei，WANG Hong，DONG Jun-hong，et al(张磊，汪泓，董俊红，等). Advances in Applied Mathematics(应用数学进展)，2021，10(11)：3659.
[12] AN Bai-song，WANG Xue-mei，HUANG Xiao-yu，et al(安柏耸，王雪梅，黄晓宇，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2023，43(10)：3302.
[13] LI Ai-min，XIA Guang-ping，QI Xin，et al(李爱民，夏光平，齐鑫，等). Journal of Geomatics Science and Technology(测绘科学技术学报)，2020，37(4)：388.
[14] DING Song-tao, ZHANG Xia, SHANG Kun, et al(丁松滔，张霞，尚坤，等). National Ramote Sensing Bulletin(遥感学报)，2023，27(9)：2191.
[15] TANG Jun-wu，TIAN Guo-liang，WANG Xiao-yong，et al(唐军武，田国良，汪小勇，等). National Remote Sensing Bulletin(遥感学报)，2004，8(1)：37.
[16] Lichtenthaler H K. Current Protocols in Food Analytical Chemistry. Wiley, 2001，F4.3.1.
[17] Li Yafeng, Xu Xingang, Wu Wenbiao，et al. Remote Sensing，2024，16(12)：2174.
[18] CHEN Hao-yu，XIANG Lei，GAO He，et al(陈昊宇，项磊，高贺，等). Remote Sensing for Natural Resources(自然资源遥感)，2023，35(3)：170.
[19] WANG Yi-jing，CHEN Rui-hua，ZHANG Jun-hua, et al(王怡婧，陈睿华，张俊华，等). Chinese Journal of Applied Ecology(应用生态学报)，2023，34(5)：1384.
[20] JIANG Hong, ZHOU Fei-xiang, ZHOU Guan-xu(姜红，周飞翔，周贯旭). Chemical Research and Applications(化学研究与应用)，2024，36(4)：766.