Skip to main content

Advertisement

SpringerLink
Log in

Development of a sequential Artificial Neural Network for predicting river water levels based on Brahmaputra and Ganges water levels

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Bangladesh is land of rivers with about 700 km shoreline at the Bay of Bengal. More than 300 rivers flow over the land of Bangladesh having an area of about 1,47,000 km2. A wide part of this country frequently face flood hazard caused by the excessive flow from three major rivers named the Ganges, the Brahmaputra and the Meghna due to heavy monsoon rainfalls on the upstream catchment area. The control of water flow is an international issue shared among Bangladesh, Nepal and India. Among 57 trans-boundary rivers, 54 enter into Bangladesh from India. Seasonal flood management is a regular exercise and costly event in Bangladesh. Among the several tools of flood management, flood forecasting is a major non-structural measure to protect the people and property from the damage of flood. Hence, the water experts of Bangladesh use several water models to assess the flood. All those are hydrodynamic models based on the mathematical framework of the elliptic differential equations. The hydrodynamic models require huge and reliable data to run the model and predict the flood elevations at river cross sections ahead of time. The models are complex and require calibration and validations for geophysical and morphological changes of river cross sections. Flood Forecast Warning Cell forecasts the flood levels during the monsoon period in more than 80 locations spread over the Bangladesh in major rivers which are generated based on boundary water levels at the Ganges, Brahmaputra and estimated rainfalls using rainfall runoff and river models. In order to circumvent the scarcity of reliable and accurate hydrological data, reduce run time and to make faster and simpler flood level prediction, this research investigated a method of using Artificial Neural Network (ANN) to generate the water levels along the rivers at selected locations. The proposed ANN can predict the incoming flood properly using boundary water levels at Bahadurabad in Brahmaputra and at Harding Bridge in the Ganges. The developed ANN has been given the name as ‘Bangladesh River Artificial Neural Network System’ and used to provide an early flood warning system.

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.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. ASCE: Task Committee on Application of Artificial Neural Networks in Hydrology (2000) Artificial neural networks in hydrology, II: hydrologic application. J Hydrol Eng 5:124–136

    Article  Google Scholar 

  2. ASCE: Task Committee on Application of Artificial Neural Networks in Hydrology (2000) Artificial neural networks in hydrology. I: preliminary concepts. J Hydrol Eng 5:115–123

    Article  Google Scholar 

  3. Brath A, Rosso R (1993) Adaptive calibration of a conceptual model for flash flood forecasting. Water Resour Res 29:2561–2572

    Article  Google Scholar 

  4. Brath A, Montanari A, Toth E (2002) Neural networks and nonparametric methods for improving real-time flood forecasting through conceptual hydrological models, Hydrol Earth Syst Sci 6:627–639. http://www.hydrol-earth-syst-sci.net/6/627/2002/

  5. Bowden GJ, Dandy GC, Maier HR (2005) Input determination for neural network models in water resources applications. Part 1—background and methodology. J Hydrol 301:93–107

    Article  Google Scholar 

  6. Bowden GJ, Dandy GC, Maier HR (2005) Input determination for neural network models in water resources applications. Part 2. Case study: forecasting salinity in a river. J Hydrol 301:93–107

    Article  Google Scholar 

  7. Carriere PSM, Gaskari R (1996) Performance of a virtual runoff hydrographic system. J Water Resour Plan Manag 122(6):120–125

    Article  Google Scholar 

  8. Corzo G, Solomatine D (2007) Knowledge-based modularization and global optimization of artificial neural network models in hydrological forecasting. Neural Netw 20:528–536

    Article  Google Scholar 

  9. Corzo G, Solomatine D, de Wit M, Werner M, Uhlenbrook S, Price R (2009) Combining semi-distributed process based and data-driven models in flow simulation: a case study of the Meuse river basin. Hydrol Earth Syst Sci Discuss 6:729–766. http://www.hydrol-earth-syst-sci-discuss.net/6/729/2009/

  10. Corzo GA, Solomatine DP (2007) Base flow separation techniques for modular artificial neural networks modelling in flow forecasting. Hydrol Sci J 52:491–507

    Article  Google Scholar 

  11. Fernando DAK, Jayawardena AW (1998) Runoff forecasting using RBF networks with OLS algorithm. J Hydrol Eng 3(3):203–209

    Article  Google Scholar 

  12. Gupta HV, Sorooshian S, Yapo PO (1998) Toward improved calibration of hydrologicmodels: multiple and non-commensurable measures of information. Water Resour Res 34(4):751–763

    Article  Google Scholar 

  13. Heppenstall AJ, See LM, Abrahart RJ (2006) Timing optimisation applied to neural network rainfall-runoff modelling of a large catchment in northern England. Geophys Res Abstr 8:06509

    Google Scholar 

  14. Hjelmfelt AT, Wang M (1996) Predicting runoff using artificial neural networks. Surface Water Hydrol 1:233–244

    Google Scholar 

  15. Hsu KL, Gupta HV, Sorooshian S (1995) Artificial neural network modeling of the rainfall-runoff process. Water Resour Res 31(10):2517–2530

    Article  Google Scholar 

  16. JRC (2014, June 10). Retrieved from Joint River Commission, Bangladesh: http://www.jrcb.gov.bd/index.html

  17. Karunanithi N, Grenney WJ, Whiteley D, Bovee K (1994) Neural networks for river flow prediction. ASCE J Comput Civil Eng 8(2):201–220

    Article  Google Scholar 

  18. Levenberg K (1944) A method for the solution of certain problems in least squares. Q Appl Math 2:164–168

    MATH  MathSciNet  Google Scholar 

  19. Library of Congress, US (2014). River systems. Retrieved June 10, 2014, from country studies: http://countrystudies.us/bangladesh/25.htm

  20. Mathworks (2011) MATLAB. MATLAB Software. USA: Mathworks Inc. Retrieved from http://www.mathworks.com

  21. Mirza MMQ (1997) The runoff sensitivity of the Ganges river basin to climate change and implications. J Environ Hydrol 5:1

    Google Scholar 

  22. Ministry of Agriculture, Bangladesh (2014) Bangladesh agriculture at a Glance. Retrieved June 10, 2014, from Ministry of Agriculture (MOA), The Government of the Peoples’ Republic of Bangladesh: http://www.moa.gov.bd/statistics/bag.htm

  23. PRIO (2013) Water scarcity in Bangladesh—transboundary rivers, conflict and cooperation. Oslo, Norway: Peach Research Institute Oslo. Retrieved from http://file.prio.no/publication_files/prio/PRIO%20Report%20-%20Water%20Scarcity%20in%20Bangladesh.pdf

  24. Vogl TJ (1988) Accelerating the convergence of the backpropagation method. Biol Cybern 59(1988):257–263

    Article  Google Scholar 

  25. Zhang B, Govindaraju RS (1998) Using modular neural networks to predict watershed runoff. ASCE Water Resour Eng Conf 98:897–902

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Civil Engineering Department, College of Engineering, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia

    Mohammed Saiful Alam Siddiquee

  2. GIS Division, CEGIS, Dhaka, Bangladesh

    Mollah Md Awlad Hossain

Authors
  1. Mohammed Saiful Alam Siddiquee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mollah Md Awlad Hossain
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohammed Saiful Alam Siddiquee.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Siddiquee, M.S.A., Hossain, M.M.A. Development of a sequential Artificial Neural Network for predicting river water levels based on Brahmaputra and Ganges water levels. Neural Comput & Applic 26, 1979–1990 (2015). https://doi.org/10.1007/s00521-015-1871-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-015-1871-6

Keywords

Search

Navigation