Modeling Earth Systems and Environment

, Volume 4, Issue 1, pp 61–68 | Cite as

Modelling of impact of water quality on recharging rate of storm water filter system using various kernel function based regression

Original Article


In this paper, recharging rate of stormwater filter system is assessed by using predictive models of Gaussian Process (GP) and Support Vector Machines (SVM). Four kernel functions: normalized poly kernel, polynomial kernel, Pearson VII kernel (PUK) and radial basis kernel (RBF) were used with both modelling approaches (GP and SVM). A dataset consists of 678 measurements was collected from the experimental investigations on the infiltration of the storm-water filter system. Out of 678 observations, randomly selected 462 observations were used for training, whereas remaining 216 were used for testing the model. Input variables were comprise of cumulative time (T), the thickness of medium sand bed (B), size of medium sand (S) and concentration of impurities (Conc.), whereas the recharging rate (R) was considered as output. Correlation coefficient (C.C) and root mean square error (RMSE) were used to compare the performance of both modelling approaches. The evaluation of result suggests that Pearson VII based GP regression approach works well as compared to the other kernel functions based on GP and SVM models. Sensitivity analysis suggested that the size of medium sand (S) is an important parameter for predicting the recharging rate of stormwater filter system. Parametric study outcomes suggested that the higher size of medium sand increases the recharging rate, and a higher concentration of impurities in water decreases the recharging rate. Moreover, on expanding the thickness of the medium sand bed the recharging rate of the storm water filter system was observed to be increased.


Gaussian process Support vector machines Pearson VII kernel Radial basis kernel Recharging rate 


  1. Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on Computational learning theory. ACM, pp 144–152Google Scholar
  2. Farooq S, Al-Yousef AK (1993) Slow sand filtration of secondary effluent. J Environ Eng 119(4):615–630CrossRefGoogle Scholar
  3. Huang S, Chang J, Huang Q, Chen Y (2014) Monthly streamflow prediction using modified EMD-based support vector machine. J Hydrol 511:764–775CrossRefGoogle Scholar
  4. Kaledhonkar MJ, Singh OP, Ambast SK, Tyagi NK, Tyagi KC (2003) Artificial groundwater recharge through recharge tubewells: a case study. J Inst Eng (India)-AG 84:28–32Google Scholar
  5. Kambale JB, Sarangi A, Singh DK, Singh AK (2009) Performance evaluation of filtration unit of groundwater recharge shaft: laboratory study. Curr Sci 471–474Google Scholar
  6. Kisi O, Cimen M (2011) A wavelet-support vector machine conjunction model for monthly streamflow forecasting. J Hydrol 399(1):132–140CrossRefGoogle Scholar
  7. Kumar S, Kamra SK, Yadav RK, Sharma JP (2012) Evaluation of sand-based stormwater filtration system for groundwater recharge wells. Curr Sci 395–404Google Scholar
  8. Kumar M, Ranjan S, Tiwari NK, Gupta R (2017) Plunging hollow jet aerators-oxygen transfer and modelling. ISH J Hydraul Eng 1–7Google Scholar
  9. Kuss M (2006) Gaussian process models for robust regression, classification, and reinforcement learning (Doctoral dissertation, Technische Universität)Google Scholar
  10. Le Coustumer S, Barraud S (2007) Long-term hydraulic and pollution retention performance of infiltration systems. Water Sci Technol 55(4):235–243CrossRefGoogle Scholar
  11. Mohanty S, Jha MK, Kumar A, Panda DK (2013) Comparative evaluation of numerical model and artificial neural network for simulating groundwater flow in Kathajodi–Surua Inter-basin of Odisha, India. J Hydrol 495:38–51CrossRefGoogle Scholar
  12. Rasmussen CE, Williams CK (2006) Gaussian processes for machine learning, vol 1. MIT press, CambridgeGoogle Scholar
  13. Sadiq R, Al-Zahrani MA, Sheikh AK, Husain T, Farooq S (2004) Performance evaluation of slow sand filters using fuzzy rule-based modelling. Environ Model Softw 19(5):507–515CrossRefGoogle Scholar
  14. Sihag P, Tiwari NK, Ranjan S (2017a) Modelling of infiltration of sandy soil using gaussian process regression. Modeling Earth Syst Environ 3(3):1091–1100CrossRefGoogle Scholar
  15. Sihag P, Tiwari NK, Ranjan S (2017b) Prediction of unsaturated hydraulic conductivity using adaptive neuro-fuzzy inference system (ANFIS). ISH J Hydraul Eng 1–11Google Scholar
  16. Singh KK, Jain P (2015) Performance evaluation of filtration system for groundwater recharging well in the presence of medium sand-mixed storm water. Int J Civ Environ Eng 9(3):252–255Google Scholar
  17. Singh B, Sihag P, Singh K (2017) Modelling of impact of water quality on infiltration rate of soil by random forest regression. Model Earth Syst Environ 3(3):999–1004CrossRefGoogle Scholar
  18. Siriwardene NR, Deletic A, Fletcher TD (2007) Clogging of stormwater gravel infiltration systems and filters: insights from a laboratory study. Water Res 41(7):1433–1440CrossRefGoogle Scholar
  19. Thomas RL (1968) Coarse filter media for artificial recharge. Illinois State Water Survey, Urbana Report of Investigation 60Google Scholar
  20. Tiwari NK, Sihag P, Ranjan S (2017) Modeling of infiltration of soil using adaptive neuro-fuzzy inference system (ANFIS). J Eng Technol Educ 11(1):13–21Google Scholar
  21. Vapnik VN, Vapnik V (1998) Statistical learning theory, vol 1. Wiley, New YorkGoogle Scholar
  22. Xing B, Gan R, Liu G, Liu Z, Zhang J, Ren Y (2015) Monthly mean streamflow prediction based on bat algorithm-support vector machine. J Hydrol Eng 21(2):04015057CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.National Institute of TechnologyKurukshetraIndia
  2. 2.Ambuja Cement FoundationRabriyawasIndia

Personalised recommendations