Skip to main content

Advertisement

SpringerLink
Log in

Assessment of groundwater quality: a fusion of geochemical and geophysical information via Bayesian neural networks

  • Published:
Environmental Monitoring and Assessment Aims and scope Submit manuscript

Abstract

Deplorable quality of groundwater arising from saltwater intrusion, natural leaching and anthropogenic activities is one of the major concerns for the society. Assessment of groundwater quality is, therefore, a primary objective of scientific research. Here, we propose an artificial neural network-based method set in a Bayesian neural network (BNN) framework and employ it to assess groundwater quality. The approach is based on analyzing 36 water samples and inverting up to 85 Schlumberger vertical electrical sounding data. We constructed a priori model by suitably parameterizing geochemical and geophysical data collected from the western part of India. The posterior model (post-inversion) was estimated using the BNN learning procedure and global hybrid Monte Carlo/Markov Chain Monte Carlo optimization scheme. By suitable parameterization of geochemical and geophysical parameters, we simulated 1,500 training samples, out of which 50 % samples were used for training and remaining 50 % were used for validation and testing. We show that the trained model is able to classify validation and test samples with 85 % and 80 % accuracy respectively. Based on cross-correlation analysis and Gibb’s diagram of geochemical attributes, the groundwater qualities of the study area were classified into following three categories: “Very good”, “Good”, and “Unsuitable”. The BNN model-based results suggest that groundwater quality falls mostly in the range of “Good” to “Very good” except for some places near the Arabian Sea. The new modeling results powered by uncertainty and statistical analyses would provide useful constrain, which could be utilized in monitoring and assessment of the groundwater quality.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  • American Public Health Association (APHA). (1985). Standard methods for the examination of water and waste (16th ed., p. 100). Washington: American Public Health Association.

    Google Scholar 

  • Appelo, C. A. J., & Postma, D. (2005). Geochemistry, groundwater and pollution (2nd ed., p. 404). Leiden: Balkema.

    Book  Google Scholar 

  • Bishop, C. M. (1995). Neural networks for pattern recognition. Oxford: Oxford University Press.

  • Bohlke, J. K. (2002). Groundwater recharge and agricultural contamination. Hydrogeology Journal, 10, 153–179.

    Article  CAS  Google Scholar 

  • Brown, C. H. (1998). Applied multivariate statistics in geo-hydrology and related sciences. Berlin: Springer.

    Book  Google Scholar 

  • Brown, E., Skougstad, M. W., & Fishmen, M. J. (1974). Methods for collection and analysis of water samples for dissolved minerals and gases. Washington: Government Printing Office.

    Google Scholar 

  • Central Ground Water Board (CGWB), (2009). Groundwater information Sindhudurg district Maharashtra, p.16.

  • Duane, S., Kennedy, A. D., Pendleton, B., & Roweth, D. (1987). Hybrid Monte Carlo. Physics Letters B, 195, 216–222.

    Article  CAS  Google Scholar 

  • Duraiswami, R., & Patankar, U. (2011). Occurrence of fluoride in the drinking water sources from Gad River basin, Maharashtra. Journal of Geological Society of India, 77, 167–174.

    Article  CAS  Google Scholar 

  • Fetter, C. W. (1988). Applied hydrogeology. Columbus: Merrill.

    Google Scholar 

  • Gibbs, R. J. (1970). Mechanisms controlling world water chemistry. Science, 170, 1088–1090.

    Article  CAS  Google Scholar 

  • Hem, J. D. (1970). Study and interpretation of the chemical characteristics of natural water. Water Supply Paper-1473, US Geological Survey, pp 363.

  • Kannan, N., & Joseph, S. (2010). Quality of groundwater in the shallow aquifers of a paddy dominated agricultural river basin, Kerala, India. International Journal of Civil Environmental Engineering, 2, 160–178.

    Google Scholar 

  • Long, A. J., & Valder, J. F. (2011). Multivariate analyses with end-member mixing to characterize groundwater flow: wind cave and associated aquifers. Journal of Hydrology, 409, 315–327.

    Article  Google Scholar 

  • Maiti, S., & Tiwari, R. K. (2009). A hybrid Monte Carlo method based artificial neural networks approach for rock boundaries identification: a case study from the KTB bore hole. Pure and Applied Geophysics, 166, 2059–2090. doi:10.1007/s00024-009-0533-y.

    Article  Google Scholar 

  • Maiti, S., & Tiwari, R. K. (2010). Neural network modeling and an uncertainty analysis in Bayesian framework: a case study from the KTB borehole site. Journal of Geophysical Research, 115, B10208. doi:10.1029/2010JB000864.

    Article  Google Scholar 

  • Maiti, S., Gupta, G., Erram, V. C., & Tiwari, R. K. (2011). Inversion of Schlumberger resistivity sounding data from the critically dynamic Koyna region using Hybrid Monte Carlo-based neural network approach. Nonlinear Processes in Geophysics, 18, 179–192. doi:10.5194/npg-18-179-2011.

    Article  Google Scholar 

  • Maiti, S., Gupta, G., Erram, V. C., & Tiwari, R. K. (2012). Delineation of shallow resistivity structure around Malvan, Konkan region, Maharashtra by neural network inversion using vertical electrical sounding measurements. Environmental Earth Sciences. doi:10.1007/s12665-012-1779-8.

  • Matlab version 7.10.0. (2010). Natick, Massachusetts: The Math Works Inc., (http://www.mathworks.com).

  • Menke, W. (1984). Geophysical data analysis: discrete inverse theory. New York: Academic.

    Google Scholar 

  • Mondal, N. C., Singh, V. S., Saxena, V. K., & Singh, V. P. (2011). Assessment of seawater impact using major hydrochemical ions: a case study from Sadras, Tamilnadu, India. Environmental Monitoring and Assessment, 177, 315–335.

    Article  CAS  Google Scholar 

  • Nabney, I. T. (2004). Netlab algorithms for pattern recognition. New York: Springer.

    Google Scholar 

  • Naik, P., Awashti, A. K., Anand, A. V. S. S., & Behera, P. N. (2009). Hydrogeochemistry of the Koyna River basin, India. Environmental Earth Sciences, 59, 613–629.

    Article  CAS  Google Scholar 

  • Panda, U. C., Sundaray, S. K., Rath, P., Nayak, B. B., & Bhatta, D. (2006). Application of factor and cluster analysis for characterization of river and estuarine water systems—a case study: Mahanadi River (India). Journal of Hydrology, 331, 434–445.

    Article  CAS  Google Scholar 

  • Park, S. C., Yun, S., Chae, G. T., Yoo, I. S., Shin, K. S., & Heo, C. H. (2005). Regional hydrochemical study on salinization of coastal aquifers, western coastal area of South Korea. Journal of Hydrology, 313, 182–194.

    Article  CAS  Google Scholar 

  • Pawar, N. J., Pondhe, G. M., & Patil, S. F. (1998). Groundwater pollution due to sugar-mill effluent at Sonai, Maharashtra, India. Environmental Geology, 34(213), 151–158.

    Article  CAS  Google Scholar 

  • Poulton, M. (2001). Computational neural networks for geophysical data processing. New York: Pergamon.

  • Pradhan, B., & Pirasteh, S. (2011). Hydro-chemical analysis of the ground water of the basaltic catchments: Upper Bhatsai Region, Maharashtra. The Open Hydrology Journal, 5, 51–57.

    Article  CAS  Google Scholar 

  • Prasanna, M. V., Chidambaram, S., Shahul, A., Hameed, A., & Srinivasamoorthy, K. (2011). Hydrogeochemical analysis and evaluation of groundwater quality in the Gadilam river basin, Tamil Nadu, India. Journal of Earth System Science, 120, 85–98.

    Article  CAS  Google Scholar 

  • Raghunath, R., Sreedhara Murthy, T. R., & Raghavan, B. R. (2001). Spatial distribution of pH, EC and total dissolved solids of Nethravathi river basin, Karnataka state, India. Pollution Research, 20, 413–418.

    Google Scholar 

  • Rajmohan, N., & Elango, L. (2006). Hydrogeochemistry and its relation to groundwater level fluctuation in the Palar and Cheyyar river basins, southern India. Hydrological Process, 20, 2415–2427.

    Article  CAS  Google Scholar 

  • Rao, P. M., Sekhar, P., & Yadav, Y. S. (2004). Water quality studies on Kolleru lake and its infalling drains of A.P., India. In A. Kumar (Ed.), Water pollution (p. 171). New Delhi: APH.

    Google Scholar 

  • Schoeller, H. (1959). Arid zone hydrology, recent developments. Paris: UNESCO.

    Google Scholar 

  • Schoeller, H. (1967). Methods and techniques of groundwater investigation and development (Water Resources Series 33). Paris: UNESCO.

    Google Scholar 

  • Song, S. H., Lee, J. Y., & Park, N. (2007). Use of vertical electrical soundings to delineate seawater intrusion in a coastal area of Byunsan, Korea. Environmental Geology, 52, 1207–1219.

    Article  CAS  Google Scholar 

  • Subba Rao, N. (2006). Seasonal variation of groundwater quality in a part of Guntur district, Andhra Pradesh, India. Environmental Geology, 49, 413–429.

    Article  Google Scholar 

  • Sun, T., Pan, S. B., & Li, Y. J. (2004). Application of artificial neural network model to groundwater quality assessment and classification. Hydrogeology and Engineering Geology, 3, 58–61.

    Google Scholar 

  • Tarantola, A. (1987). Inverse problem theory. New York: Elsevier.

    Google Scholar 

  • Tiwari, R. K., & Maiti, S. (2011). Bayesian neural network modeling of tree-ring temperature variability record from the Western Himalayas. Nonlinear Processes in Geophysics, 18, 515–528. doi:10.5194/npg-18-515-2011.

    Article  Google Scholar 

  • Todd, D. K. (1959). Groundwater hydrology (pp. 277–294). New York: Wiley.

    Google Scholar 

  • Van der Bann, M., & Jutten, C. (2000). Neural networks in geophysical applications. Geophysics, 65, 1032–1047.

    Article  Google Scholar 

  • Willmott, C. J. (1981). On the validation of models. Physical Geography, 2, 184–194.

    Google Scholar 

  • World Health Organization (WHO). (1984). Guideline of drinking quality (pp. 333–335). Washington: World Health Organization.

    Google Scholar 

  • Zou, Z. H., & Wang, H. (2007). Application of BP modeling based on random samples to assessment on natural water quality. Environmental Engineering, 25, 69–71.

    Google Scholar 

  • Zou, Z. H., & Wang, H. (2010). Adaptive neuro fuzzy inference system for classification of water quality status. Journal of Environmental Sciences, 22, 1891–1896.

    Article  Google Scholar 

Download references

Acknowledgments

We are thankful to the Directors, Indian Institute of Geomagnetism, New-Panvel and NGRI, Hyderabad for their kind permission to publish the work.

Author information

Authors and Affiliations

  1. Indian Institute of Geomagnetism (DST), Navi Mumbai, 410218, India

    Saumen Maiti, V. C. Erram & Gautam Gupta

  2. CSIR—National Geophysical Research Institute, Hyderabad, 500606, India

    Ram Krishna Tiwari

  3. Nowrosjee Wadia College of Science, Pune, 411001, India

    U. D. Kulkarni & R. R. Sangpal

Authors
  1. Saumen Maiti
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. V. C. Erram
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Gautam Gupta
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ram Krishna Tiwari
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. U. D. Kulkarni
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. R. R. Sangpal
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Saumen Maiti.

Appendix

Appendix

Fig. 9
figure 9

Concentration map of a pH, b electrical conductivity (EC), c total dissolved solids (TDS), and d bicarbonate \( \left( {{\text{HCO}}_3^{ - }} \right) \). Units are expressed in log10. The surface maps were constructed using triangle-based cubic interpolation in Matlab

Full size image
Fig. 10
figure 10

Concentration map of a chloride (Cl−), b sulfate \( \left( {{\text{SO}}_4^{{2 - }}} \right) \), c nitrate \( \left( {{\text{NO}}_3^{ - }} \right) \), and d calcium (Ca2+). Units are expressed in log10. The surface maps were constructed using triangle-based cubic interpolation in Matlab

Full size image
Fig. 11
figure 11

Concentration map of a true resistivity (ρ), b magnesium (Mg2+), c sodium (Na+), and d potassium (K+). Units are expressed in log10. The surface maps were constructed using triangle-based cubic interpolation in Matlab

Full size image
Fig. 12
figure 12

Cross plots of a–b Na+ and Mg2+ with TDS, c–d Cl− and \( {\text{SO}}_4^{{2 - }} \) with TDS, e–f Mg2+ and Na+ with Cl−, and g–h Ca2+ and K+ with Cl−

Full size image
Fig. 13
figure 13

Comparison of the results of the best Bayesian neural network (BNN) model and observed data. Error bar shows 90 % confidence level

Full size image

Rights and permissions

Reprints and permissions

About this article

Cite this article

Maiti, S., Erram, V.C., Gupta, G. et al. Assessment of groundwater quality: a fusion of geochemical and geophysical information via Bayesian neural networks. Environ Monit Assess 185, 3445–3465 (2013). https://doi.org/10.1007/s10661-012-2802-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10661-012-2802-y

Keywords

Search

Navigation