Predicting the Trend of Dissolved Oxygen Based on the kPCA-RNN Model

Water quality forecasting is increasingly significant for agricultural management and environmental protection. Enormous amounts of water quality data are collected by advanced sensors, which leads to an interest in using data-driven models for predicting trends in water quality. However, the unpredictable background noises introduced during water quality monitoring seriously degrade the performance of those models. Meanwhile, artificial neural networks (ANN) with feed-forward architecture lack the capability of maintaining and utilizing the accumulated temporal information, which leads to biased predictions in processing time series data. Hence, we propose a water quality predictive model based on a combination of Kernal Principal Component Analysis (kPCA) and Recurrent Neural Network (RNN) to forecast the trend of dissolved oxygen. Water quality variables are reconstructed based on the kPCA method, which aims to reduce the noise from the raw sensory data and preserve actionable information. With the RNN’s recurrent connections, our model can make use of the previous information in predicting the trend in the future. Data collected from Burnett River, Australia was applied to evaluate our kPCA-RNN model. The kPCA-RNN model achieved R 2 scores up to 0.908, 0.823, and 0.671 for predicting the concentration of dissolved oxygen in the upcoming 1, 2 and 3 hours, respectively. Compared to current data-driven methods like Feed-forward neural network (FFNN), support vector regression (SVR) and general regression neural network (GRNN), the predictive accuracy of the kPCA-RNN model was at least 8%, 17% and 12% better than the comparative models in these three cases. The study demonstrates the effectiveness of the kPAC-RNN modeling technique in predicting water quality variables with noisy sensory data.

[1]  I. Chubarenko,et al.  Modelling of man-made contribution to salinity increase into the Vistula Lagoon (Baltic Sea) , 2001 .

[2]  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.

[3]  Özgür Kişi,et al.  Estimation of dissolved oxygen by using neural networks and neuro fuzzy computing techniques , 2017 .

[4]  Theodore B. Trafalis,et al.  Kernel principal component analysis and support vector machines for stock price prediction , 2007 .

[5]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[6]  Han Che,et al.  A real time method of contaminant classification using conventional water quality sensors. , 2015, Journal of environmental management.

[7]  Rahim Barzegar,et al.  Combining the advantages of neural networks using the concept of committee machine in the groundwater salinity prediction , 2016, Modeling Earth Systems and Environment.

[8]  Julie Josse,et al.  Regularised PCA to denoise and visualise data , 2013, Stat. Comput..

[9]  Ophélie Fovet,et al.  Transit times—the link between hydrology and water quality at the catchment scale , 2016 .

[10]  Viktor Pocajt,et al.  A linear and non-linear polynomial neural network modeling of dissolved oxygen content in surface water: Inter- and extrapolation performance with inputs' significance analysis. , 2018, The Science of the total environment.

[11]  G. Esposito,et al.  Machine Learning Algorithms for the Forecasting of Wastewater Quality Indicators , 2017 .

[12]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[13]  John R. Olson,et al.  The reference condition: predicting benchmarks for ecological and water-quality assessments , 2010, Journal of the North American Benthological Society.

[14]  P. Thorburn,et al.  Applying Multi-Layer Artificial Neural Network and Mutual Information to the Prediction of Trends in Dissolved Oxygen , 2019, Front. Environ. Sci..

[15]  Abbas Alimohammadi,et al.  Water quality analysis using a variable consistency dominance-based rough set approach , 2014, Comput. Environ. Urban Syst..

[16]  R. Macdonald,et al.  Towards environmental management of water turbidity within open coastal waters of the Great Barrier Reef. , 2013, Marine pollution bulletin.

[17]  Gustavious P. Williams,et al.  Hydrostats: A Python Package for Characterizing Errors between Observed and Predicted Time Series , 2018, Hydrology.

[18]  Alison J. King,et al.  Short-term effects of a prolonged blackwater event on aquatic fauna in the Murray River, Australia: considerations for future events , 2012 .

[19]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[20]  Jian Sha,et al.  A comparative study of multiple linear regression, artificial neural network and support vector machine for the prediction of dissolved oxygen , 2017 .

[21]  Tao Jin,et al.  A data-driven model for real-time water quality prediction and early warning by an integration method , 2019, Environmental Science and Pollution Research.

[22]  Yi-Fan Zhang,et al.  SSIM—A Deep Learning Approach for Recovering Missing Time Series Sensor Data , 2018, IEEE Internet of Things Journal.

[23]  Viktor Pocajt,et al.  Modelling of dissolved oxygen in the Danube River using artificial neural networks and Monte Carlo Simulation uncertainty analysis , 2014 .

[24]  K. Chau,et al.  Improving forecasting accuracy of medium and long-term runoff using artificial neural network based on EEMD decomposition. , 2015, Environmental research.