Skip to main content

Application and Sensitivity Analysis of Artificial Neural Network for Prediction of Chemical Oxygen Demand


Integrating water quality forecasting model with river restoration techniques makes river restoration more effective and efficient. This research investigates how to use the Artificial Neural Network (ANN) to predict the Chemical Oxygen Demand (COD) during river restoration in Wuxi city, China. Specifically, we applied a Multi-Layer Perceptron (MLP) using ten neurons in a single hidden layer and seven input variables (Temperature, Dissolved Oxygen, Total Nitrogen, Total Phosphorus, Suspended Sediment, Transparency, and NH3-N) to simulate COD. The modeled results have a correlation coefficient of 0.966, 0.949, and 0.890 with the observations for the raining, validation, and testing phases, respectively. When presenting the trained network to an independent data set, the ANN model still shows a good predictive capability, indicating by a correlation coefficient of 0.978, a root mean square error (RMSE) of 0.628 mg/L, and a mean square error (MSE) of 0.394 mg2/L2. A sensitivity analysis was further implemented to analyze the effect of each of the input variables on prediction of COD. DO, TO, and Transparency have relatively low influences on the estimate of COD, and can be removed from the input variables. The results from this study indicate that ANN models can provide satisfactory estimates of COD during the process of bacterial treatment and is a useful supportive tool for river restoration.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6


  • Amos TK, Xie Y-B, Song Y (2012) Numerical Models for Predicting the Fate of Ammonia-Nitrogen under Bacterial Technology. J Appl Sci Environ Sanit 7(3):183–192

  • Areerachakul S (2013) The Using Artificial Neural Network to Estimate of Chemical Oxygen Demand. Int J Chem Mol Nucl Mat Met Eng 7:1891–1894

    Google Scholar 

  • Banhatti AG, Deka PC (2016) Effects of Data Pre-processing on the Prediction Accuracy of Artificial Neural Network Model in Hydrological Time Series. In: Sarma AK, Singh VP, Kartha SA, Bhattacharjya RK (eds) Urban Hydrology, Watershed Management and Socio-Economic Aspects. Springer International Publishing, Cham, pp 265–275.

    Chapter  Google Scholar 

  • Cox BA (2003) A review of dissolved oxygen modelling techniques for lowland rivers. Sci Total Environ 314:303–334

    Article  Google Scholar 

  • El-Shafie A, Najah A, Alsulami HM, Jahanbani H (2014) Optimized Neural Network Prediction Model for Potential Evapotranspiration Utilizing Ensemble Procedure. Water Resour Manag 28:947–967.

    Article  Google Scholar 

  • Fausett LV (1994) Fundamentals of neural networks: Architectures, Algorithms, and Applications. Prentice-Hall, Inc., Upper Saddle River, NJ, USA.

  • Goonetilleke A, Vithanage M (2017) Water Resources Management: Innovation and Challenges in a Changing World. Water 9:281.

    Article  Google Scholar 

  • Gusev EM, Ayzel GV, Nasonova ON (2017) Runoff evaluation for ungauged watersheds by SWAP model. 1. Application of artificial neural networks. Water Resour 44:169–179.

    Article  Google Scholar 

  • Haykin S (1999) Neural networks: A comprehensive foundation. Second Edition. Prentice Hall International, Inc., United States of America

  • Iglesias C, Torres JM, Nieto PG, Fernández JA, Muñiz CD, Piñeiro J, Taboada J (2014) Turbidity prediction in a river basin by using artificial neural networks: a case study in northern Spain. Water Resour Manag 28:319–331

    Article  Google Scholar 

  • Jia J, Jian H, Xie D, Gu Z, Chen C (2017) Multi-Perspectives’ Comparisons and Mitigating Implications for the COD and NH3-N Discharges into the Wastewater from the Industrial Sector of China. Water 9:201.

    Article  Google Scholar 

  • Liu M, Yoshimi K, Ishikawa T, Kudo K (2009) New Approach for Estimation of Pollutant Load by Using Artificial Neural Network. In: Advances in Water Resources and Hydraulic Engineering: Proceedings of 16th IAHR-APD Congress and 3rd Symposium of IAHR-ISHS. Springer, Berlin Heidelberg, Berlin, Heidelberg, pp 683–688.

    Chapter  Google Scholar 

  • Maier HR, Jain A, Dandy GC, Sudheer KP (2010) Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions. Environ Model Softw 25:891–909.

    Article  Google Scholar 

  • Majumder M (2015) Artificial Neural Network. In: Impact of Urbanization on Water Shortage in Face of Climatic Aberrations, Majumder M (Ed). Springer Singapore, Singapore, pp 49–54. doi:

  • Parmar KS, Bhardwaj R (2015) River Water Prediction Modeling Using Neural Networks, Fuzzy and Wavelet Coupled Model. Water Resour Manag 29:17–33.

    Article  Google Scholar 

  • Rahimikhoob A (2014) Comparison between M5 Model Tree and Neural Networks for Estimating Reference Evapotranspiration in an Arid Environment. Water Resour Manag 28:657–669.

    Article  Google Scholar 

  • Ranković V, Radulović J, Radojević I, Ostojić A, Čomić L (2010) Neural network modeling of dissolved oxygen in the Gruža reservoir. Serbia Ecolo Model 221:1239–1244

    Article  Google Scholar 

  • Ruben GB, Xie Y, Samuel A-A (2016) Estimation of Ammonia-Nitrogen ( NH 3-N ) Using an Artificial Neural Networks Under Bacterial Technology, Orient J Chem, 32(1):37–45

  • Shao M, Tang X, Zhang Y, Li W (2006) City clusters in China: air and surface water pollution. Front Ecol Environ 4:353–361

    Article  Google Scholar 

  • Talib A, Amat MI (2012) Prediction of Chemical Oxygen Demand In Dondang River Using Artificial Neural Network. Int J Inf Educ Technol:259–261.

  • Thambavani DS (2015) Comparative Application of ANN and PCA in Modelling of Groundwater. J Adv Chem Sci 1:22–26

    Google Scholar 

  • Wen X, Fang J, Diao M, Zhang C (2013) Artificial neural network modeling of dissolved oxygen in the Heihe River, Northwestern China. Environ Monit Assess 185:4361–4371

    Article  Google Scholar 

  • Xie Y-B, Amos TK, Song Y (2012) Bacterial technology as a sustainable solution to polluted urbanized rivers and wastewater treatment systems in China. J Appl Technol Environ Sanit 2:87–93

  • Yajing S, Xie Y, Peng F (2011) Eco-friendly domestic sewage treatment with bacterial technology. In, IEEE, pp 1294–1297

  • Yudianto D, Xie Y-B (2010) Feasibility of Bacterial Technology for Treating a Polluted Urban Streams from the Perspective of Numerical Modelling. J Environ Stud 19:419–427

  • Yudianto D, Xie Y-B (2011) Numerical modeling and practical experience of Xuxi River's natural restoration using biological treatment. Water Environ Res 83:2087–2098

  • Zhao X, Huang X, Liu Y (2012) Spatial autocorrelation analysis of Chinese inter-provincial industrial chemical oxygen demand discharge. Int J Environ Res Public Health 9:2031–2044

    Article  Google Scholar 

Download references


This study was partially supported by National Key Research and Development Program of China (2016YFC0402701), the Research Funds of State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering (20165042212), the Fundamental Research Funds for the Central Universities of China (2015B28514), and the Priority Academic Program Development of Jiangsu Higher Education Institutions.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Ke Zhang.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ruben, G.B., Zhang, K., Bao, H. et al. Application and Sensitivity Analysis of Artificial Neural Network for Prediction of Chemical Oxygen Demand. Water Resour Manage 32, 273–283 (2018).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


  • Artificial neural network
  • Chemical oxygen demand
  • Water pollution
  • River restoration