Prediction and Analysis of Chlorophyll-a Concentration in the Western Waters of Hong Kong Based on BP Neural Network

Wei-Dong Zhu, Yu-Xiang Kong, Nai-Ying He, Zhen-Ge Qiu and Zhi-Gang Lu ()
Additional contact information
Wei-Dong Zhu: School of Marine Science, Shanghai Ocean University, Shanghai 201306, China
Yu-Xiang Kong: School of Marine Science, Shanghai Ocean University, Shanghai 201306, China
Nai-Ying He: School of Marine Science, Shanghai Ocean University, Shanghai 201306, China
Zhen-Ge Qiu: School of Marine Science, Shanghai Ocean University, Shanghai 201306, China
Zhi-Gang Lu: School of Resources and Architectural Engineering, Gannan University of Science and Technology, Ganzhou 341000, China

Sustainability, 2023, vol. 15, issue 13, 1-17

Abstract: The Chlorophyll-a (Chl-a) concentration is an important indicator of water environmental conditions; thus, the simultaneous monitoring of large-area water bodies can be realized through the remote sensing-based retrieval of Chl-a concentrations. Together with hyperspectral remote sensing data, a BP neural network model was used to invert chlorophyll-a concentration, with remote sensing reflectance as the input factor. Given the presence of many bands in the hyperspectral data, selecting an appropriate band reflectance as the input factor is crucial to improving inversion accuracy. In this study, a Pearson correlation analysis method was proposed to select bands. A normality test was performed on the reflectance of each band of the Zhuhai-1 hyperspectral remote sensing data, and the significance index was p < 0.05. The absolute kurtosis value was less than 10, and the absolute skewness value was less than 3, indicating that the Pearson method was applicable. Pearson correlation analysis was utilised to calculate the correlation coefficient between the reflectance data and chlorophyll-a concentration. Five reflectance data with high correlation were selected as the input factors, and chlorophyll-a concentration was adopted as the output factor. An error backpropagation network model was constructed to predict chlorophyll-a concentration, and a Garson function was added to clarify the connection weights of the input factors in the model construction process. Model 12 was determined as the optimal model on the basis of the criteria of the coefficient of determination, the average relative variance, and the minimum mean square error. The chlorophyll-a concentration was predicted for July and November 2020 in the study area, and the results showed that the predicted values had a small error compared with the measured values. The root-mean-square error and mean relative error of the chlorophyll-a concentration predicted and measured values were 2.12 μg/L and 9.66%, respectively. Significant spatial differences in the Chl-a concentration were observed in the study area due to the influence of islands and land; the Chl-a concentration in July was generally higher than that in November. The results of these studies provide a reference for monitoring the water environment in the study area.

Keywords: hyperspectral; chlorophyll-a; BP neural network; spatiotemporal analysis (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/13/10441/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/13/10441/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2023:i:13:p:10441-:d:1185489

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().