Soft Computing Techniques for Predicting Chemical Oxygen Demand in River Water

Document Type : Regular Article

Authors

1 Research Scholar, Civil Department, Vishwakarma Institute of Information Technology (VIIT), Pune, India

2 Professor, Civil Department, Vishwakarma Institute of Information Technology (VIIT), Pune, India

3 Associate Professor, Civil Department, Vishwakarma Institute of Information Technology (VIIT), Pune, India

Abstract

Organic matter in water is assessed through Chemical oxygen demand (COD). COD prediction utilizing Data driven technique (DDT) has shown to be promising and may be utilized as supplemental techniques due to the time-consuming procedure and nonlinear correlations between the factors. The current study aims to determine how well three different DDT, namely Artificial Neural Network (ANN), Multi-Gene Genetic Programming (MGGP), and Model Tree (M5T), can estimate the concentration of COD in water taken from three different sections of the Mula, Mutha, and Mula-Mutha Rivers in Pune, India. The performance of the models demonstrates that both ANN and MGGP worked brilliantly, with a correlation coefficient (between observed and projected values) that was more than 0.88 and a root mean square value of 0.7 mg/l across all three parts. The input frequency distribution in MGGP and the input variable coefficient in M5T indicate that both techniques can identify the influential factors. MGGP and MT score with readily available equations as model.

Highlights

  • The Chemical Oxygen Demand was modelled by using 3 data driven techniques namely Artificial Neural Network (ANN), Multigene genetic programming (MGGP) and M5Model Tree (MT) with three separate models developed for river Mutha, Mula and combined Mula Mutha flowing near the city of Pune in India.
  • Artificial Neural Network Models performed the best in terms of model accuracy as evident by high correlation coefficient and low Root mean square error.
  • Multi gene genetic programming and M5 Model Tree perform reasonably well and show variable importance.
  • The output in MGGP and M5T in form of equations can make them user friendly.

Keywords

Main Subjects

References

[1]     Zare Abyaneh H. Evaluation of multivariate linear regression and artificial neural networks in prediction of water quality parameters. J Environ Heal Sci Eng 2014;12:40. https://doi.org/10.1186/2052-336X-12-40.
[2]     Verma AK, Singh TN. Prediction of water quality from simple field parameters. Environ Earth Sci 2013;69:821–9. https://doi.org/10.1007/s12665-012-1967-6.
[3]     Jingsheng C, Tao Y, Ongley E. Influence of High Levels of Total Suspended Solids on Measurement of Cod and Bod in the Yellow River, China. Environ Monit Assess 2006;116:321–34. https://doi.org/10.1007/s10661-006-7374-2.
[4]     Rice EW, Bridgewater L, Association APH. Standard methods for the examination of water and wastewater. vol. 10. American public health association Washington, DC; 2012.
[5]     Londhe SN, Panchang V. Correlation of wave data from buoy networks. Estuar Coast Shelf Sci 2007;74:481–92. https://doi.org/10.1016/j.ecss.2007.05.003.
[6]     Palani S, Liong S-Y, Tkalich P. An ANN application for water quality forecasting. Mar Pollut Bull 2008;56:1586–97. https://doi.org/10.1016/j.marpolbul.2008.05.021.
[7]     Singh KP, Basant A, Malik A, Jain G. Artificial neural network modeling of the river water quality—A case study. Ecol Modell 2009;220:888–95. https://doi.org/10.1016/j.ecolmodel.2009.01.004.
[8]     Akilandeswari S, Kavitha B. Comparison of ANFIS and statistical modeling for estimation of chemical oxygen demand parameter in textile effluent. Der Chem Sin 2013;4:96–9.
[9]     Heddam S, Kisi O. Modelling daily dissolved oxygen concentration using least square support vector machine, multivariate adaptive regression splines and M5 model tree. J Hydrol 2018;559:499–509. https://doi.org/10.1016/j.jhydrol.2018.02.061.
[10]   Maier HR, Dandy GC. Neural networks for the prediction and forecasting of water resources variables: A review of modelling issues and applications. Environ Model Softw 2000;15:101–24. https://doi.org/10.1016/S1364-8152(99)00007-9.
[11]   Danandeh Mehr A, Ghadimi S, Marttila H, Torabi Haghighi A. A new evolutionary time series model for streamflow forecasting in boreal lake-river systems. Theor Appl Climatol 2022;148:255–68. https://doi.org/10.1007/s00704-022-03939-3.
[12]   Karami H, Ghazvinian H, Dehghanipour M, Ferdosian M. Investigating the Performance of Neural Network Based Group Method of Data Handling to Pan’s Daily Evaporation Estimation (Case Study: Garmsar City). J Soft Comput Civ Eng 2021;5:1–18. https://doi.org/10.22115/scce.2021.274484.1282.
[13]   Najah A, El-Shafie A, Karim OA, El-Shafie AH. Application of artificial neural networks for water quality prediction. Neural Comput Appl 2013;22:187–201. https://doi.org/10.1007/s00521-012-0940-3.
[14]   Basant N, Gupta S, Malik A, Singh KP. Linear and nonlinear modeling for simultaneous prediction of dissolved oxygen and biochemical oxygen demand of the surface water — A case study. Chemom Intell Lab Syst 2010;104:172–80. https://doi.org/10.1016/j.chemolab.2010.08.005.
[15]   Elmolla ES, Chaudhuri M, Eltoukhy MM. The use of artificial neural network (ANN) for modeling of COD removal from antibiotic aqueous solution by the Fenton process. J Hazard Mater 2010;179:127–34. https://doi.org/10.1016/j.jhazmat.2010.02.068.
[16]   Emamgholizadeh S, Kashi H, Marofpoor I, Zalaghi E. Prediction of water quality parameters of Karoon River (Iran) by artificial intelligence-based models. Int J Environ Sci Technol 2014;11:645–56. https://doi.org/10.1007/s13762-013-0378-x.
[17]   Wu X, Zhang Q, Wen F, Qi Y. A Water Quality Prediction Model Based on Multi-Task Deep Learning: A Case Study of the Yellow River, China. Water 2022;14:3408. https://doi.org/10.3390/w14213408.
[18]   Ozkan O, Ozdemır O, Azgın ST. Prediction of biochemical oxygen demand in a wastewater treatment plant by artificial neural networks. Asian J Chem 2009;21:4821–30.
[19]   Dogan E, Sengorur B, Koklu R. Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique. J Environ Manage 2009;90:1229–35. https://doi.org/10.1016/j.jenvman.2008.06.004.
[20]   Danandeh Mehr A, Safari MJS. Multiple genetic programming: a new approach to improve genetic-based month ahead rainfall forecasts. Environ Monit Assess 2019;192:25. https://doi.org/10.1007/s10661-019-7991-1.
[21]   Ay M, Kisi O. Modeling of Dissolved Oxygen Concentration Using Different Neural Network Techniques in Foundation Creek, El Paso County, Colorado. J Environ Eng 2012;138:654–62. https://doi.org/10.1061/(ASCE)EE.1943-7870.0000511.
[22]   ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. Artificial Neural Networks in Hydrology. I: Preliminary Concepts. J Hydrol Eng 2000;5:115–23. https://doi.org/10.1061/(ASCE)1084-0699(2000)5:2(115).
[23]   Dawson CW, Wilby RL. Hydrological modelling using artificial neural networks. Prog Phys Geogr Earth Environ 2001;25:80–108. https://doi.org/10.1177/030913330102500104.
[24]   Jain P, Deo MC. Neural networks in ocean engineering. Ships Offshore Struct 2006;1:25–35. https://doi.org/10.1533/saos.2004.0005.
[25]   Shahin MA. State-of-the-art review of some artificial intelligence applications in pile foundations. Geosci Front 2016;7:33–44. https://doi.org/10.1016/j.gsf.2014.10.002.
[26]   Quinlan JR. Learning with continuous classes. 5th Aust. Jt. Conf. Artif. Intell., vol. 92, World Scientific; 1992, p. 343–8.
[27]   Kulkarni P, Londhe SN, Dixit PR. A comparative study of concrete strength prediction using artificial neural network, multigene programming and model tree. Chall J Struct Mech 2019;5:42. https://doi.org/10.20528/cjsmec.2019.02.002.
[28]   Hashmi S, Halawani SM, Barukab OM, Ahmad A. Model trees and sequential minimal optimization based support vector machine models for estimating minimum surface roughness value. Appl Math Model 2015;39:1119–36. https://doi.org/10.1016/j.apm.2014.07.026.
[29]   Abolfathi S, Yeganeh-Bakhtiary A, Hamze-Ziabari SM, Borzooei S. Wave runup prediction using M5′ model tree algorithm. Ocean Eng 2016;112:76–81. https://doi.org/10.1016/j.oceaneng.2015.12.016.
[30]   Solomatine DP, Xue Y. M5 Model Trees and Neural Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China. J Hydrol Eng 2004;9:491–501. https://doi.org/10.1061/(ASCE)1084-0699(2004)9:6(491).
[31]   Solomatine DP, Dulal KN. Model trees as an alternative to neural networks in rainfall-runoff modelling. Hydrol Sci J 2003;48:399–411. https://doi.org/10.1623/hysj.48.3.399.45291.
[32]   Searson DP, Leahy DE, Willis MJ. GPTIPS: an open source genetic programming toolbox for multigene symbolic regression. Proc. Int. multiconference Eng. Comput. Sci., vol. 1, Citeseer; 2010, p. 77–80.
[33]   N. S, R. P. Genetic Programming: A Novel Computing Approach in Modeling Water Flows. Genet. Program. - New Approaches Success. Appl., IntechOpen Publishing London, UK; 2012. https://doi.org/10.5772/48179.
[34]   Gandomi AH, Alavi AH. A new multi-gene genetic programming approach to nonlinear system modeling. Part I: materials and structural engineering problems. Neural Comput Appl 2012;21:171–87. https://doi.org/10.1007/s00521-011-0734-z.
[35]   Pune Municipal Corporation. JICA Project | Pune Municipal Corporation 2023. https://www.pmc.gov.in/en/jica-project.
[36]   Report On Environmental Status of Pune Region. Kalpataru Point, Sion Circle, Sion (East) Mumbai. n.d.
[37]   Sahu P, Karad S, Chavan S, Khandelwal S. Physicochemical Analysis Of Mula Mutha River Pune. Civ Eng Urban Plan An Int J 2015;2.
[38]   Central Pollution Control Board (CPCB) | The Official Website of Ministry of Environment, Forest and Climate Change, Government of India n.d.
[39]   Fletcher D, Goss E. Forecasting with neural networks. Inf Manag 1993;24:159–67. https://doi.org/10.1016/0378-7206(93)90064-Z.
[40]   Olyaie E, Zare Abyaneh H, Danandeh Mehr A. A comparative analysis among computational intelligence techniques for dissolved oxygen prediction in Delaware River. Geosci Front 2017;8:517–27. https://doi.org/10.1016/j.gsf.2016.04.007.
[41]   Ranković V, Radulović J, Radojević I, Ostojić A, Čomić L. Neural network modeling of dissolved oxygen in the Gruža reservoir, Serbia. Ecol Modell 2010;221:1239–44. https://doi.org/10.1016/j.ecolmodel.2009.12.023.
[42]   Chowdhury MZI, Turin TC. Variable selection strategies and its importance in clinical prediction modelling. Fam Med Community Heal 2020;8. https://doi.org/10.1136/fmch-2019-000262.
[43]   Adeniran KA, Adelodun B, Ogunshina M. Artificial Neural Network Modelling of Biochemical Oxygen Demand and Dissolved Oxygen of Rivers: Case Study of Asa River. Environ Res Eng Manag 2017;72:59–74. https://doi.org/10.5755/j01.erem.72.3.14120.
[44]   G. E. McCuen. Protecting water quality 1986:180.
[45]   Hem JD. Study and interpretation of the chemical characteristics of natural water. US Geological Survey; 1959. https://doi.org/10.3133/wsp1473_ed1.
[46]   MathWorks Announces Release 2016b of the MATLAB and Simulink Product Families - MATLAB & Simulink. MathWorks 2016.
[47]   Singh HK. Prediction of shear strength of deep beam using Genetic Programming 2014.
[48]   Melesse AM, Khosravi K, Tiefenbacher JP, Heddam S, Kim S, Mosavi A, et al. River water salinity prediction using hybrid machine learning models. Water 2020;12:2951.
[49]   Garg SK. Water Supply Engineering. Khanna Publishers; 2010.
[50]   Metcalf E. Wastewater Engineering Treatment and Reuse (4th edition) (2004) | Akhid Maulana - Academia.edu. 4th editio. 2004.
[51]   Rahimikhoob A, Behbahani SMR, Banihabib ME. Comparative study of statistical and artificial neural network’s methodologies for deriving global solar radiation from NOAA satellite images. Int J Climatol 2013;33:480–6. https://doi.org/10.1002/joc.3441.
[52]   Danandeh Mehr A, Jabarnejad M, Nourani V. Pareto-optimal MPSA-MGGP: A new gene-annealing model for monthly rainfall forecasting. J Hydrol 2019;571:406–15. https://doi.org/10.1016/j.jhydrol.2019.02.003.
[53]   Ay M, Kisi O. Modelling of chemical oxygen demand by using ANNs, ANFIS and k-means clustering techniques. J Hydrol 2014;511:279–89. https://doi.org/10.1016/j.jhydrol.2014.01.054.

Files

History

  • Receive Date: 19 October 2022
  • Revise Date: 22 April 2023
  • Accept Date: 23 April 2023
  • First Publish Date: 23 April 2023

Share

How to cite

Statistics