Advertisement

Modeling Earth Systems and Environment

, Volume 3, Issue 4, pp 1371–1382 | Cite as

Application of automatic relevance determination model for groundwater quality index prediction by combining hydro-geochemical and geo-electrical data

  • Saumen Maiti
  • Anasuya Das
  • Rhythm Shah
  • Gautam Gupta
Original Article
  • 62 Downloads

Abstract

In this study, an automatic relevance determination-based Bayesian neural network (ARD-BNN) approach is employed combing hydro-geochemical and geo-electrical information to predict groundwater quality index (GWQI) of coastal Maharashtra, India. In the first step, to incorporate geo-electrical information for GWQI forward computation, the weight corresponding to true resistivity of the earth layer is estimated via ARD-BNN modelling using training sample generated for groundwater classification. In the second step, incorporating earth resistivity weight information, a total of 1500 training samples are created honouring World Health Organisation (WHO) guidelines for GWQI prediction. Prior to actual data analysis, we explored the algorithm on GWQI variable series assorted with different level of complex (red) noise to examine the bounds of network hyper-parameter. What distinguishes our approach from previous approach for ARD-BNN optimization is that we seek to develop a mechanism which allows specific weight estimation and provides insight into which hyper parameters and their bounds are appropriate to predict GWQI from noise intervened GWQI data. The model shows excellent performance between predicted and computed GWQI both in training (trn) and test (tst) data with Pearson’s correlation coefficient (rtrn ~ 0.91 and rtst ~ 0.90), root-mean-squared-error (RMSE) error (RMSEtrn ~ 1.2 and RMSEtst ~ 1.4), reduction of error (RE) (REtrn ~ 0.98 and REtst ~ 0.97), and index of agreement (IA) (IAtrn ~ 0.95 and IAtst ~ 0.93). Red noise analysis shows that the ARD-BNN model is robust up to the noise level of 20% in the input variable for GWQI prediction. The network adopted relevance analysis to indicate the relative importance of input parameter in the prediction of GWQI via ARD-BNN modelling which showed that chloride [Cl], [pH], [HCO3 ] and sodium [Na+] are dominant while considering various simulations for characterizing the GWQI of coastal Maharashtra. The approach used here, could be useful in understanding the relative contribution and/or modelling pollution source in many other environmental applications.

Keywords

Bayesian neural networks Automatic relevance determination Groundwater quality parameter Groundwater quality index Konkan 

Notes

Acknowledgements

Authors are thankful to the Director, IIT (ISM), Dhanbad and Director, IIG, Navi Mumbai for their kind permission to publish the work. AD is thankful to ISM JRF fellowship in which the some analysis work is done Partial financial benefit from the Ministry of Earth Sciences, Govt. of India, New Delhi, India, is also thankfully acknowledged (Grant no: MoES/P.O. (Geosci)/44/2015).

References

  1. American Public Health Association (APHA) (1985) Standard methods for the examination of water and waste, 16th edn. Am. Public Health Assoc., Washington, DC, p 100Google Scholar
  2. Bishop CM, (1995) Neural networks for pattern recognition. Oxford University Press, OxfordGoogle Scholar
  3. Brown CH (1998) Applied multivariate statistics in geohydrology and related sciences. Springer, BerlinCrossRefGoogle Scholar
  4. Brown RM, McClelland NI, Deininger RA, Tozer RG, (1970) A water quality index: do we dare? Water Sew Works 117:339–343Google Scholar
  5. Brown E, Skougstad MW, Fishmen MJ (1974) Methods for collection and analysis of water samples for dissolved minerals and gases. Govt. Printing Office, WashingtonGoogle Scholar
  6. Calster BV, Timmerman D, Nabney IT, Valentin L, Testa AC, Holsbeke CV, Vergote I, Huffel SV (2008) Using Bayesian neural networks with ARD input selection to detect malignant ovarian masses prior to surgery. Neural Comput Appl 17:489–500CrossRefGoogle Scholar
  7. Central Ground Water Board (CGWB) (2009) Groundwater information Sindhudurg district Maharashtra by S.C. Paranjape, A report for Ministry of Water Resources, Government of India, p 16Google Scholar
  8. Das A, Maiti S, Naidu S, Gupta G (2016) Estimation of spatial variability of aquifer parameters from geophysical methods: a case study of Sindhudurg district, Maharashtra, India. Stoch Environ Res Risk Assess. doi: 10.1007/s00477-016-1317-4 Google Scholar
  9. Fetter CW (1988) Applied hydrogeology. Charles E. Merrill, ColumbusGoogle Scholar
  10. Gazzaz NM, Yusoff MK, Aris AZ, Juahir H, Ramli MF (2012) Artificial neural network modeling of the water quality index for Kinta River (Malaysia) using water quality variables as predictors. Mar Pollut Bull 64(11):2409–2420CrossRefGoogle Scholar
  11. Hem JD (1970) Study and interpretation of the chemical characteristicsof natural water. Water Supply Paper-1473, US Geological Survey, p 363Google Scholar
  12. Hippert HS, Tylor JW (2010) An evaluation of Bayesian techniques for controlling model complexity and selecting inputs in a neural networks for short-term load forecasting. Neural Netw 23:386–395CrossRefGoogle Scholar
  13. Horton RK (1965) An index number system for rating water quality. J Water Pollut Control Fed 37:300–305Google Scholar
  14. Krishna kumar S, Logeshkumaran A, Magesh NS, Godson PS, Chandrasekar N (2014) Hydro-geochemistry and application of water quality index (WQI) for groundwater quality assessment, Anna Nagar, part of Chennai city, Tamil Nadu, India. Appl Water Sci. doi: 10.1007/s13201-014-0196-4 Google Scholar
  15. Lopez G, Batlles FJ, Tovar-Pescador J (2005) Selection of input parameters to model direct solar irradiance by using artificial neural networks. Energy 30:1675–1684CrossRefGoogle Scholar
  16. MacKay DJC (1992) A practical Bayesian framework for back-propagation net- works. Neural Comput 4(3):448–472CrossRefGoogle Scholar
  17. Magesh NS, Krishnakumar S, Chandrasekar N, Soundranayagam JP (2013) Groundwater quality assessment using WQI and GIS techniques, Dindigul district, Tamil Nadu, India. Arab J Geosci 6(11):4179–4189CrossRefGoogle Scholar
  18. Maiti S, Tiwari RK (2010) Neural network modeling and an uncertainty analysis in Bayesian framework: a case study from the KTB borehole site. J Geophys Res 115:B10208. doi: 10.1029/2010JB000864 CrossRefGoogle Scholar
  19. Maiti S, Erram VC, Gupta G, Tiwari RK (2012) ANN based inversion of DC resistivity data for groundwater exploration in hard rock terrain of western Maharashtra (India). J Hydrol 464–465:281–293. doi: 10.1016/j.jhydrol.2012.07.020 Google Scholar
  20. Maiti S, Erram VC, Gupta G, Tiwari RK, Kulkarni UD, Sangpal RR (2013) Assessment of groundwater quality: a fusion of geochemical and geophysical information via Bayesian Neural Networks. Environ Monit Assess 185:3445–3465. doi: 10.1007/s10661-012-2802-y CrossRefGoogle Scholar
  21. Moller MA (1993) Scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6:525–533CrossRefGoogle Scholar
  22. Nabney IT (2004) Netlab algorithms for pattern recognition. Springer, New YorkGoogle Scholar
  23. Najah A, El-Shafie A, Karim OA, El-Shafie AH (2013) Application of artificial neural networks for water quality prediction. Neural Comput Appl 22:S187–S201. doi: 10.1007/s00521-012-0940-3 CrossRefGoogle Scholar
  24. Pradhan SK, Patnaik D, Rout SP (2001) Water quality index for the groundwater in and around a phosphatic fertilizer plant. Indian J Environ Prot 21:355–358Google Scholar
  25. Ramakrishnaiah CR, Sadashivaiah C, Ranganna G (2009) Assessment of water quality index for the groundwater in Tumkur Taluk, Karnataka State, India. E J Chem 6(2):523–530CrossRefGoogle Scholar
  26. Sadat-Noori SM, Ebrahimi K, Liaghat AM (2014) Groundwater quality assessment using the water quality index and GIS in Saveh–Nobaran aquifer. Iran Environ Earth Sci 71:3827–3843CrossRefGoogle Scholar
  27. Sahu M, Mahapatra SS, Sahu HB (2011) Prediction of water quality index using neuro fuzzy inference system. Water Qual Expo Health 3:175–191CrossRefGoogle Scholar
  28. Schoeller H, (1959) Arid zone hydrology, recent developments. UNESCO, ParisGoogle Scholar
  29. Schoeller H (1967) Methods and techniques of groundwater investigationand development. Water Resources Series-33. UNESCO, ParisGoogle Scholar
  30. Singh AK, Mondal GC, Singh S, Singh PK, Singh TB, Tewary BK, Sinha A (2007) Aquatic geochemistry of dhanbad, Jharkhand: source evaluation and quality assessment. J Geol Soc India 69:1088–1102Google Scholar
  31. Stigter TY, Ribeiro L, Carvalho Dill AMM (2006) Application of a groundwater quality index as an assessment and communication tool in agro-environmental policies-Two Portuguese case studies. J Hydrol 327:578–591. doi: 10.1016/j.hydrol.2005.12.001 CrossRefGoogle Scholar
  32. Todd DK (1959) Groundwater hydrology. Wiley, New York, pp 277–294Google Scholar
  33. Vadiati M, Asghari-Moghaddam A, Nakhaei M, Adamowski J (2016) A fuzzy-logic based decision-making approach for identification of groundwater quality based on groundwater quality indices. J Environ Manag. doi: 10.1016/j.jenvman.2016.09.082 Google Scholar
  34. Van der Bann M, Jutten C (2000) Neural networks in geophysical applications. Geophysics 65:1032–1047CrossRefGoogle Scholar
  35. Vasanthavigar M, Srinivassamoorthy K, Vijayaragavan K, Rajiv Ganthi R, Chidambaram S, Anandhan P, Manivannan R, Vasudevan S (2010) Application of water quality for ground water quality assessment: Thirumanimuttar Sub basin, Tamil Nadu, India. Environ Monit Assess 171:595–609CrossRefGoogle Scholar
  36. Wang D, Lu WZ (2006) Interval estimation of urban ozone level and selection of influential factors by employing automatic relevance determination model. Chemosphere 62:1600–1611CrossRefGoogle Scholar
  37. Willmott CJ (1981) On the validation of models. Phys Geogr 2:184–194Google Scholar
  38. World Health Organization (WHO) (1984) Guideline of drinking quality. World Health Organization, Washington, DC, pp 333–335Google Scholar
  39. Zou ZH, Wang H (2010) Adaptive neuro fuzzy inference system for classification of water quality status. J Environ Sci 22:1891–1896CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Saumen Maiti
    • 1
  • Anasuya Das
    • 1
  • Rhythm Shah
    • 1
  • Gautam Gupta
    • 2
  1. 1.Department of Applied GeophysicsIndian Institute of Technology (Indian School of Mines)DhanbadIndia
  2. 2.Indian Institute of Geomagnetism (DST)Navi MumbaiIndia

Personalised recommendations