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

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.

[1]  Xia Wu,et al.  A novel end-to-end 1D-ResCNN model to remove artifact from EEG signals , 2020, Neurocomputing.

[2]  W. Dong,et al.  Connecting AnnAGNPS and CE-QUAL-W2 models for reservoir water quality prediction , 2011, 2011 International Conference on Electric Technology and Civil Engineering (ICETCE).

[3]  Wenhu Tang,et al.  Wind power forecasting using attention-based gated recurrent unit network , 2020, Energy.

[4]  Shang-Chen Wu,et al.  Multi-Step Short-Term Wind Speed Prediction Using a Residual Dilated Causal Convolutional Network with Nonlinear Attention , 2020, Energies.

[5]  Il Won Seo,et al.  Artificial Neural Network ensemble modeling with conjunctive data clustering for water quality prediction in rivers , 2015 .

[6]  YuanSheng Lou,et al.  Hydrological Time Series Anomaly Pattern Detection based on Isolation Forest , 2019, 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC).

[7]  Daoliang Li,et al.  Multi-scale prediction of water temperature using empirical mode decomposition with back-propagation neural networks , 2016, Comput. Electr. Eng..

[8]  Fang Liu,et al.  Air Pollution Forecasting Using a Deep Learning Model Based on 1D Convnets and Bidirectional GRU , 2019, IEEE Access.

[9]  Chuang Yu,et al.  Accurate Prediction Scheme of Water Quality in Smart Mariculture With Deep Bi-S-SRU Learning Network , 2020, IEEE Access.

[10]  Jianzhuo Yan,et al.  Prediction of water quality time series data based on least squares support vector machine , 2012 .

[11]  Anne E. Carey,et al.  Water quality modeling of the Cahaba River, Alabama , 2004 .

[12]  Jianping Wang,et al.  Prediction of dissolved oxygen in pond culture water based on K-means clustering and gated recurrent unit neural network , 2020 .

[13]  Yunfeng Yang,et al.  Annual periodicity in planktonic bacterial and archaeal community composition of eutrophic Lake Taihu , 2015, Scientific Reports.

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Marc A. Rosen,et al.  Application of sliding window technique for prediction of wind velocity time series , 2014 .

[16]  Michele Amoretti,et al.  CNN-based multivariate data analysis for bitcoin trend prediction , 2021, Appl. Soft Comput..

[17]  Sepp Hochreiter,et al.  Self-Normalizing Neural Networks , 2017, NIPS.

[18]  Zhaohui Li,et al.  A Spatial–Temporal Positioning Algorithm Using Residual Network and LSTM , 2020, IEEE Transactions on Instrumentation and Measurement.

[19]  Ahmed El-Shafie,et al.  Towards a time and cost effective approach to water quality index class prediction , 2019, Journal of Hydrology.

[20]  Xiangyu Zhou,et al.  Deep Belief Network for Meteorological Time Series Prediction in the Internet of Things , 2019, IEEE Internet of Things Journal.

[21]  K. Chau,et al.  Machine learning based marine water quality prediction for coastal hydro-environment management. , 2021, Journal of environmental management.

[22]  Qinghua Liu,et al.  Evaluation of Water Quality Using Grey Clustering , 2009, 2009 Second International Workshop on Knowledge Discovery and Data Mining.

[23]  Shang-Lien Lo,et al.  Predicting real-time coagulant dosage in water treatment by artificial neural networks and adaptive network-based fuzzy inference system , 2008, Eng. Appl. Artif. Intell..

[24]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[25]  Fei Tony Liu,et al.  Isolation-Based Anomaly Detection , 2012, TKDD.

[26]  J. Adamowski,et al.  Application of wavelet-artificial intelligence hybrid models for water quality prediction: a case study in Aji-Chay River, Iran , 2016, Stochastic Environmental Research and Risk Assessment.

[27]  G. Suciu,et al.  Study on Unmanned Surface Vehicles used for Environmental Monitoring in Fragile Ecosystems , 2020, 2020 IEEE 26th International Symposium for Design and Technology in Electronic Packaging (SIITME).

[28]  Yongchuan Yu,et al.  A Prediction Model Based on Deep Belief Network and Least Squares SVR Applied to Cross-Section Water Quality , 2020 .

[29]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[30]  Choujun Zhan,et al.  Intelligent Wide-Area Water Quality Monitoring and Analysis System Exploiting Unmanned Surface Vehicles and Ensemble Learning , 2020, Water.

[31]  Peter J. Thorburn,et al.  Predicting the Trend of Dissolved Oxygen Based on the kPCA-RNN Model , 2020 .

[32]  Kun Yu,et al.  Short-term Power Load Forecasting of Residential Community Based on GRU Neural Network , 2018, 2018 International Conference on Power System Technology (POWERCON).