Evaluation of the k-nearest neighbor method for forecasting the influent characteristics of wastewater treatment plant

Abstract

The k-nearest neighbor (k-NN) method was evaluated to predict the influent flow rate and four water qualities, namely chemical oxygen demand (COD), suspended solid (SS), total nitrogen (T-N) and total phosphorus (T-P) at a wastewater treatment plant (WWTP). The search range and approach for determining the number of nearest neighbors (NNs) under dry and wet weather conditions were initially optimized based on the root mean square error (RMSE). The optimum search range for considering data size was one year. The square root-based (SR) approach was superior to the distance factor-based (DF) approach in determining the appropriate number of NNs. However, the results for both approaches varied slightly depending on the water quality and the weather conditions. The influent flow rate was accurately predicted within one standard deviation of measured values. Influent water qualities were well predicted with the mean absolute percentage error (MAPE) under both wet and dry weather conditions. For the seven-day prediction, the difference in predictive accuracy was less than 5% in dry weather conditions and slightly worse in wet weather conditions. Overall, the k-NN method was verified to be useful for predicting WWTP influent characteristics.

Keywords

influent wastewater / prediction / data-driven model / k-nearest neighbor method (k-NN)

References

[1] Butler D, Graham N J D. Modeling dry weather wastewater flow in sewer networks. Journal of Environmental Engineering, 1995, 121(2): 161–173

[2] Lin S, Liao Y, Hsieh S, Kuo J, Chen Y. A pattern-oriented approach to development of a real-time storm sewer simulation system with an SWMM model. Journal of Hydroinformatics, 2010, 12(4): 408–423

[3] Freni G, Mannian G, Viviani G. Urban storm-water quality management: centralized versus source control. Journal of Water Resources Planning and Management, 2010, 136(2): 268–278

[4] Jeppsson U, Rosen C, Alex J, Copp J,Gernaey K V, Pons M N, Vanrolleghem P A. Towards a benchmark simulation model for plant-wide control strategy performance evaluation of WWTPs. Water Science and Technology, 2008, 53(1): 287–295

[5] Gernaey K V,Flores-Alsina X, Rosen C, Benedetti L, Jeppsson U. Dynamic influent pollutant disturbance scenario generation using a phenomenological modelling approach. Journal of Environmental Modelling and Software, 2011, 26(11): 1255–1267

[6] Kim H S, Kim Y J, Cheon S P, Baek G D, Kim S S, Kim C W. Evaluation of model-based control strategy based on generated setpoint schedules for NH₄-N removal in a pilot-scale A²/O process. Chemical Engineering Journal, 2012, 203: 387–397

[7] Kim J R, Ko J H, Im J H, Lee S H, Kim S H, Kim C W, Park T J. Forecasting influent flow rate and composition with occasional data for supervisory management system by time series model. Water Science and Technology, 2006, 53(4-5): 185–192

[8] Wang H R, Wang C, Kin X, Kang J. An improved ARIMA model for precipitation simulations. Nonlinear Processes in Geophysics, 2014, 21(6): 1159–1168

[9] Valipour M, Banihabib M E, Behbahani S M R. Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez Dam Reservoir. Journal of Hydrology (Amsterdam), 2013, 476: 433–441

[10] Mohammadi K, Eslami H R. Dayyani Dardashti Sh. Comparison of regression ARIMA and ANN models for reservoir inflow forecasting using snowmelt equivalent (a case study of Karaj). Journal of Agricultural Science and Technology, 2005, 7: 17–30

[11] Khashei M, Bijari M. A new hybrid methodology for nonlinear time series forecasting. Modelling and Simulation in Engineering, 2011, 2011: 1–5

[12] Laio F, Porporato A, Revelli R,Ridolfi L. A comparison of nonlinear flood forecasting methods. Water Resources Research, 2003, 39(5): 1129

[13] Karunasinghe D S K, Liong Sh. Chaotic time series prediction with a global model: artificial neural network. Journal of Hydrology (Amsterdam), 2006, 3232(1-4): 92–105

[14] Solaimany-Aminabad M, Maleki A, Hadi M. Application of artificial neural network (ANN) for the prediction of water treatment plant influent characteristics. Journal of Advances in Environmental Health Research, 2013, 1(2): 89–100

[15] Bagheri M, Mirbagheri S A, Bagheri Z, Kamarkhani A M. Modeling and optimization of activated sludge bulking for a real wastewater treatment plant using hybrid artificial neural networks-genetic algorithm approach. Process Safety and Environmental Protection, 2015, 95: 12–25

[16] Grieu S, Traoré A, Polit M, Colprim J. Prediction of parameters characterizing the state of a pollution removal biologic process. Engineering Applications of Artificial Intelligence, 2005, 18(5): 559–573

[17] Wu C L, Chau K W. Data-driven models for monthly streamflow time series prediction. Engineering Applications of Artificial Intelligence, 2010, 23(8): 1350–1367

[18] Arroyo J, Maté C. Forecasting histogram time series with k-nearest neighbours methods. International Journal of Forecasting, 2009, 25(1): 192–207

[19] Imandoust S B, Bolandraftar M. Application of k-nearest neighbor (KNN) approach for predicting economic events: theoretical background. Int. Journal of Engineering Research and Applications, 2013, 3(5): 605–610

[20] Ponomarenko A,Avrelin N, Naidan B, Boytsov L. Comparative analysis of data structures for approximate nearest neighbor search. Journal of Mathematical Sciences, 2012, 181(6): 782–791

[21] Batista G E A P A, Silva D F. How k-nearest neighbor parameters affect its performance. In Argentine Symposium on Artificial Intelligence, 2009, 1–12

[22] Alkasassbeh M, Altarawneh G A, Hassanat A. On enhancing the performance of nearest neighbour classifiers using hassanat distance metric. Canadian Journal of Pure and Applied Sciences, 2015, 9(1): 3291–3298

[23] Tongal H. Nonlinear forecasting of stream flows using a chaotic approach and artificial neural networks. Earth Sciences Research Journal, 2013, 17(2): 119–126

[24] Nesmerak I, Blazkova S D. Analysis of the time series of waste water quality at the inflow of the wastewater treatment plant and transfer functions. Journal of Hydrology and Hydromechanics, 2014, 62(1): 55–59

[25] Yu X Y, Liong S Y. Babovic V. EC-SVM approach for real-time hydrologic forecasting. Journal of Hydroinformatics, 2004, 6(3): 209–233

[26] Toth E,Brath A, Montanari A. Comparison of short-term rainfall prediction models for real-time flood forecasting. Journal of Hydrology (Amsterdam), 2000, 239(1): 132–147

[27] Gou J, Du L, Zhang Y, Xiong T. A new distance-weighted k-nearest neighbor classifier. Journal of Information and Computational Science, 2012, 9: 1429–1436

[28] Hassanat A B, Abbadi M A, Altarawneh G A, Alhasanat A A. Solving the Problem of the K Parameter in the KNN Classifier Using an Ensemble Learning Approach. 2014

[29] Livio M. The Golden Ratio: The Story of Phi, the World’s Most Astonishing Number. New York: Broad books, 2002

[30] Han J, Kamber M. Data mining: concepts and techniques. Morgan Kaufmann publishers, San Francisco, 2001

[31] Karegowda A G, Jayaram M A, Manjunath A S. Combining Akaike’s information criterion and the golden-section search technique to find optimal numbers of k-nearest neighbors. Journal of Computer Applications, 2010, 2(1): 80–87

[32] Yanxia S, van Wyk B J, Wag Z. A new golden ratio local search-based particle swarm optimization. In: Proceedings of 2012 International Conference on Systems and Informatics, China. 2012, 754–757

[33] Teimouri M. Comparison of neural network and k-nearest neighbor methods in daily flow forecasting. Journal of Applied Sciences, 2010, 10: 1006–1010

Acknowledgements

This research was supported by the Korea Ministry of Environment as part of the Eco-innovation Project. In addition, this work was financially supported by the second stage of the Brain Korea 21 Project in 2013.

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg