Abstract
Total suspended matter (TSM) is a core parameter in the quantitative retrieval of ocean color remote sensing and an important indicator for evaluating the quality of the aquatic environment. This study selects part of Nansi Lake in North China as the study area. Researchers used Hyperion remote sensing data and field-measured TSM concentration as data sources. Firstly, the characteristic variables with high correlation were selected based on spectral analysis. Then, seven methods such as linear regression, BP neural network (BP), KNN, random forest (RF), and random forest based on genetic algorithm optimization (GA_RF) are used to construct the inversion model of TSM concentration. The retrieval accuracy of each model shows that the machine learning models are much more accurate than the linear model. Among them, the GA_RF model retrieves the suspended solids concentration with the best performance and the highest prediction accuracy, with a determination coefficient R2 of 0.98, a root mean square error (RMSE) of 1.715 mg/L, and an average relative error (ARE) of 6.83%. Additionally, the spatial distribution of TSM concentration was inversed by Hyperion remote sensing image. The results showed that the concentration of TSM was lower in the northwest and higher in the southeast, and the concentration distribution was uneven, showing the characteristics of a typical shallow macrophytic lake. This study provides an effective method for monitoring TSM concentration and other water quality parameters in the shallow macrophytic lake and further proves the advantages of machine learning in ocean color inversion. All in all, this research provides some useful methods and suggestions for quantitative inversion of TSM concentration in shallow macrophytic lakes.
Highlights
Total suspended matter (TSM) is one of the important parameters of water quality, which directly affects the transparency and turbidity of the water body [1] and affects the growth of aquatic organisms and the primary productivity of the water body [2]
Complex, and it is difficult to use the conventional inversion model for quantitative monitoring. e ecological problems in the study area selected for this paper are relatively prominent, so this paper proposes using the machine learning method which is more suitable for the shallow macrophytic lake to quantitatively estimate the TSM concentration in the study area and hopes that the conclusions obtained from this study will be of some guidance for the inversion of water quality parameters in other shallow macrophytic lakes in the world
Using the local area of Nansi Lake as the study area, we quantitatively estimated the TSM concentration using linear models and various machine learning models, verified the accuracy of the inversion data, and mapped the spatial distribution of the TSM concentration. e following conclusions were obtained from the study: (1) e correlation coefficients of R1124 and R844 of Hyperion hyperspectral remote sensing data with the concentration of TSM are about 0.42, and the correlation coefficient of R1648.9–R2213.9 is 0.624. e TSM concentration is influenced by various factors, and there are more variables involved in model estimation. erefore, TSM concentration inversion cannot use only a certain band but requires the joint participation of multiple variables
Summary
TSM is one of the important parameters of water quality, which directly affects the transparency and turbidity of the water body [1] and affects the growth of aquatic organisms and the primary productivity of the water body [2]. E empirical method is based on the statistical relationship between measured TSM concentration data and remotely sensed spectral information to retrieve TSM concentrations. E semianalytical method is a combination of known spectral characteristics of water quality parameters and statistical models to select the optimal band or a combination of bands as variables for remote sensing retrieval, which has strong reliability and applicability and is widely used in the estimation of parameters of Case II water [6, 7]. It is the most commonly used ocean color remote sensing retrieval algorithm at present due to its relatively simple method and fewer parameters
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
