Estimation of the Spatial Variation of Pollution Load by Neural Models and Surface Algorithms

  • Mrinmoy MajumderEmail author
  • Pankaj Roy
  • Rabindra Nath Barman
  • Asis Mazumdar


The present study tried to predict spatial variation of water pollutants with the help of two pollution factors: spatial variation of stream flow and spatial variation of water quality and neurogenetic algorithms. The two pollution factors were, respectively, industrial pollution (IP) factor, which identifies the intensity and presence of industrial pollutants from common water quality parameters that got influenced due to the release of industrial effluents in a river and organic pollution (OP) factor, which tries to estimate the intensity of organic pollutants from common quality parameters that get affected due to anthropogenic presence in the adjacent catchments. A neurogenetic model was prepared to estimate industrial pollution (IP) and organic pollution (OP) factors where observed stream flow data from 42 gauged and ungauged sampling points within two river networks in the Eastern India and land use of adjacent catchments of the sampling points were taken as input. The IP and OP factors are prepared to be directly proportional to water pollution, that is, if the factors are more than 0.7, water is polluted and if the same are less than 0.5, water is not polluted at all. The pattern identification capability of neurogenetic models enforces the authors for selection of neurogenetic models for the prediction of the above two factors. After the model was validated with the help of common validation equations, the selected model was applied to predict future IP and OP of the same region due to changed climate scenario generated by PRECIS climate model. The output of PRECIS was fed to PARITYCGD model (9), which estimated the stream flow due to the changed climatic scenario that was again used to predict IP and OP of the sampling points. The estimated values were fed to a surface algorithm to show the spatial variation of the two factors within the river basins. According to the results, area under water pollution from industries were more than the area that was not under pollution during the A2 scenario of climate change, but in B2 the trend reverses and more area without industrial pollution would emerge. But in case of water polluted by organic wastes, more area was predicted to be without pollution than area under pollution in case of A2 scenario and for B2 scenario of climate change the area without pollution will get increased in a fast rate from 2010 to 2100 and in 2071–2100 the increase would be maximum. As A2 scenario was predicted to be economic but without any restrictions on CO2 emission, the future land use was generated as industrially active but still area under pollution was more in A2 than in B2, which was imagined to be environmentally stable and with severe restrictions on CO2 emission.


Climate change industrial and organic pollution stream flow water pollution 


  1. Country Profile: India. Library of Congress Country Studies (2004) Retrieved from on May 18, 2008
  2. EPA (2003) National Management Measures to Control Nonpoint Source Pollution from Agriculture Document No. EPA-841-B-03-004Google Scholar
  3. EPA (2008) Integrated Pest Management Principles (IPM) principles. Retrieved from: on 22nd July, 2009
  4. Gupta T (2006) The politics of toilets. Retrieved from
  5. Hopfenberg R, Pimentel D (2008) Human population numbers as a function of food supply Retrieved on February 2008Google Scholar
  6. National Geographic Society (1995) Water: a story of hope. National Geographic Society, Washington, DCGoogle Scholar
  7. National Geographic (2007) Mumbai slum: Dharavi, National Geographic, May 2007Google Scholar
  8. Pink DH (2006) Investing in tomorrow’s liquid gold. Yahoo. Retrieved from on 30 July 2009
  9. Shandilya R (2007) Facts about water pollution. Retrieved from on 30 July 2009
  10. United States Geological Survey (USGS) (1998) Denver, CO. Ground water and surface water: a single resource. USGS Circular 1139Google Scholar
  11. U.S. EPA (2005) Protecting water quality from agricultural runoff. Fact Sheet No. EPA-841-F-05-001Google Scholar
  12. U.S. EPA (2004) Report to congress: impacts and control of CSOs and SSOs. Document No. EPA-833-R-04-001Google Scholar
  13. U.S. EPA (2004) Primer for municipal wastewater treatment systems. Document No. EPA 832-R-04-001Google Scholar
  14. US EPA (2008) Green infrastructure case studies: Philadelphia, 9 December 2008Google Scholar
  15. US Natural Resources Conservation Service (NRCS), Washington, DC. National Conservation Practice Standards. National Handbook of Conservation Practices. Accessed on 2009-03-28Google Scholar
  16. West L (2006) World water day: a billion people worldwide lack safe drinking water. Retrieved from on 30 July 2009
  17. World Health Organization (WHO) (1992) Environmental health criteria 134 – cadmium international programme on chemical safety (IPCS) monographGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2010

Authors and Affiliations

  • Mrinmoy Majumder
    • 1
    • 2
    Email author
  • Pankaj Roy
    • 1
  • Rabindra Nath Barman
    • 1
    • 3
  • Asis Mazumdar
    • 1
    • 2
  1. 1.School of Water Resources EngineeringJadavpur UniversityKolkataIndia
  2. 2.Regional Center, National Afforestation and Eco-development BoardJadavpur UniversityKolkataIndia
  3. 3.Department of ProductionNational Institute of TechnologyAgartalaIndia

Personalised recommendations