Retrieval of Water Quality Parameters from Hyperspectral Images Using Hybrid Bayesian Probabilistic Neural Network

Yishan Zhang,Huazhong Ren,Licui Deng,Lun Wu,Pengcheng Zhang

doi:10.3390/rs12101567

Yishan Zhang, Huazhong Ren + Show 3 more

Open Access

https://doi.org/10.3390/rs12101567

Copy DOI

Abstract

The protection of water resources is of paramount importance to human beings’ practical lives. Monitoring and improving water quality nowadays has become an important topic. In this study, a novel Bayesian probabilistic neural network (BPNN) improved from ordinary Bayesian probability methods has been developed to quantitatively predict water quality parameters including phosphorus, nitrogen, chemical oxygen demand (COD), biochemical oxygen demand (BOD), and chlorophyll a. The proposed method, based on conventional Bayesian probability methods, involves feature engineering and deep neural networks. Additionally, it extracts significant information for each endmember from combinations of spectra by feature extraction, with spectral unmixing based on mathematical and statistical analysis, and calculates each of the water quality parameters. The experimental results show the great performance of the proposed model with all coefficient of determination R 2 over 0.9 greater than the values (0.6–0.8) from conventional methods, which are greater than ordinary Bayesian probability analysis. The mean percent of absolute error (MPAE) is taken into account as an important statistical criterion to evaluate model performance, and our results show that MPAE ranges from 4% (nitrogen) to 10% (COD). The root mean squared errors (RMSEs) of phosphorus, nitrogen, COD, BOD, and chlorophyll-a (Chla) are 0.03 mg/L, 0.28 mg/L, 3.28 mg/L, 0.49 mg/L, and 0.75 μg/L, respectively. In comparison with other deep learning methods, this study takes a relatively small amount of data as training data to train the proposed model and the proposed model is then tested on the same amount of testing data, achieving a greater performance. Thus, the proposed method is time-saving and more effective. This study proposes a more compatible and effective method to assist with decomposing combinations of hyperspectral signatures in order to calculate the content level of each water quality parameter. Moreover, the proposed method is practically applied to hyperspectral image data on board an unmanned aerial vehicle in order to monitor the water quality on a large scale and trace the location of pollution sources in the Maozhou River, Guangdong Province of China, obtaining well-explained and significant results.

Highlights

Monitoring the change in water quality through remote sensing techniques has recently become a topic of major interest
The results of this study shows that our proposed hybrid Bayesian probabilistic neural network (BPNN) model outperforms other models discussed in Section 4 with respect to R2, root mean squared errors (RMSEs), and mean percent of absolute error (MPAE) on the same testing dataset, where R2 is over 0.94 and MPAE is less than 10% for all water quality parameters in our study
The proposed method takes featuring reflectance, which it selects through feature engineering, and transfers it from a transferring model, as mentioned in Section 2, to be used as the as input to predict the concentrations of water quality parameters including phosphorus, nitrogen, chemical oxygen demand (COD), biochemical oxygen demand (BOD), and Chla

Summary

Introduction

Monitoring the change in water quality through remote sensing techniques has recently become a topic of major interest. Maintaining water of good quality is highly important and necessary. An efficient and labor-saving method for quantitatively computing the content level of five water quality parameters including phosphorus, nitrogen, biochemical oxygen demand (BOD), chemical oxygen demand (COD), and chlorophyll-a (Chla) has been developed due to the practical needs of human beings’ lives. High levels of Chla may cause the death of aquatic creatures such as fish and shrimp and the amount of aquatic life, including aquatic animals and plants, is highly associated with levels of BOD and COD [4]. In the past few years, multispectral remote sensing as an orthodox method was an important method to categorize the level of water quality [5]

Objectives

Methods

Results

Discussion

Conclusion