Water Quality Prediction in the Luan River Based on 1-DRCNN and BiGRU Hybrid Neural Network Model

Jianzhuo Yan,Jiaxue Liu,Hongxia Xu,Yongchuan Yu

doi:10.3390/w13091273

Abstract

The current global water environment has been seriously damaged. The prediction of water quality parameters can provide effective reference materials for future water conditions and water quality improvement. In order to further improve the accuracy of water quality prediction and the stability and generalization ability of the model, we propose a new comprehensive deep learning water quality prediction algorithm. Firstly, the water quality data are cleaned and pretreated by isolation forest, the Lagrange interpolation method, sliding window average, and principal component analysis (PCA). Then, one-dimensional residual convolutional neural networks (1-DRCNN) and bi-directional gated recurrent units (BiGRU) are used to extract the potential local features among water quality parameters and integrate information before and after time series. Finally, a full connection layer is used to obtain the final prediction results of total nitrogen (TN), total phosphorus (TP), and potassium permanganate index (COD-Mn). Our prediction experiment was carried out according to the actual water quality data of Daheiting Reservoir, Luanxian Bridge, and Jianggezhuang at the three control sections of the Luan River in Tangshan City, Hebei Province, from 5 July 2018 to 26 March 2019. The minimum mean absolute percentage error (MAPE) of this method was 2.4866, and the coefficient of determination (R2) was able to reach 0.9431. The experimental results showed that the model proposed in this paper has higher prediction accuracy and generalization than the existing LSTM, GRU, and BiGRU models.

Highlights

With the rapid development of China’s economy and science and technology, people’s production and living range is more and more extensive
We proposed a new hybrid neural network model that combines onedimensional residual convolutional neural networks (1-DRCNN) with bidirectional gated recurrent units (BiGRU), focusing on learning the potential local features of water quality time series data and capturing contextual time attribute
BiGRU, gated recurrent unit (GRU), and long short-term memory (LSTM) were implemented by Tensorflows deep learning library keras2.2.0

Summary

Introduction

With the rapid development of China’s economy and science and technology, people’s production and living range is more and more extensive. The content of total nitrogen (TN), total phosphorus (TP), and potassium permanganate (COD-Mn) in the water body has greatly increased. These factors are the main reasons for water eutrophication [1]. The deterioration of river water quality has a profound impact on the ecological health of surface water and its tributaries, which undoubtedly increases the burden of sustainable development of human drinking water. In the stage of water environment treatment, real-time prediction of water quality can provide a scientific decision-making basis for the protection and treatment of the water environment

Methods

Results

Conclusion