Meteorology and Atmospheric Physics

, Volume 101, Issue 1–2, pp 93–108 | Cite as

Long lead monsoon rainfall prediction for meteorological sub-divisions of India using deterministic artificial neural network model

Article
First Online:
Received:
Accepted:

Summary

The advantages of artificial neural network technique for explaining the nonlinear behavior between the inputs and output is explored to forecast the monsoon rainfall of 36 meteorological sub-divisions of India. The model uses the past years of monsoon rainfall data only to forecast the monsoon rainfall of coming year. Monthly rainfall time series data for each of the 36 meteorological sub-divisions constructed by Guhathakurta and Rajeevan (2007) is used for the present study. The model captures well the input-output nonlinear relations and predicted the seasonal rainfall quite accurately during the independent period. All India monsoon rainfall forecasts were generated by using area weighted rainfall forecasts of all the sub-divisions. For the first time the idea of up-scaling is introduced in monsoon rainfall prediction using neural network technique and it is shown that up scaling helps to capture the variability of the all India rainfall better. This helps to predict the extreme years like 2002, 2004 better than the neural network model developed based on single time series of all India rainfall. However, derivation of smaller scale (sub-divisions) forecast model may be more useful than the all India forecast.

Keywords

Root Mean Square Error Neural Network Model Monsoon Rainfall Summer Monsoon Rainfall Rainfall Time Series 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bishop, C 1995Neural networks for pattern recognitionOxford University PressOxfordGoogle Scholar
  2. Elsner, JB, Tsonis, AA 1992Nonlinear prediction, chaos and noiseBull Amer Meteor Soc734960CrossRefGoogle Scholar
  3. Goswami, P, Kumar, P 1997Experimental annual forecast of all India mean summer monsoon rainfall for 1997 using a neural network modelCurrent Sci72781782Google Scholar
  4. Goswami, P, Srividya,  1996A novel neural network design for long range prediction of rainfall patternCurrent Sci70447457Google Scholar
  5. Guhathakurta, P 2006Long range monsoon rainfall prediction of 2005 for the districts and sub-division Kerala with artificial neural networkCurrent Sci90773779Google Scholar
  6. Guhathakurta P, Rajeevan M (2007) Trends in rainfall pattern over India. Int J Climatol; DOI: 10.1002/joc.1640 2007Google Scholar
  7. Guhathakurta, P, Rajeevan, M, Thapliyal, V 1999Long rang forecasting Indian summer monsoon rainfall by a hybrid principal component neural network modelMeteorol Atmos Phys71255266CrossRefGoogle Scholar
  8. Kang, I-S, Shukla, J 2006Dynamic seasonal prediction and predictability. Chap. 15: The Asian monsoonSpringer PraxisChicherster585612Google Scholar
  9. Lorenz, EN 1969Three approaches to atmospheric predictabilityBull Amer Meteor Soc50345349Google Scholar
  10. Navone, HD, Ceccatto, HA 1994Predicting Indian monsoon rainfall: a neural network approachClim Dyn10302312CrossRefGoogle Scholar
  11. Navone, HD, Granitto, PM, Verdes, PF, Ceccatto, HA 2001A learning algorithm for neural network ensembles. Inteligencia artificialRevista Iberoamericana de Inteligencia Artificial127074Google Scholar
  12. Rajeevan, M, Guhathakurta, P, Thapliyal, V 2000New models for long range forecasts of summer monsoon rainfall over North West and Peninsular IndiaMeteorol Atmos Phys73211225CrossRefGoogle Scholar
  13. Rajeevan, M, Pai, DS, Dikshit, SK, Kelkar, RR 2004IMD’s new operational models for long-range forecast of southwest monsoon rainfall over India and their verification for 2003Current Sci86422431Google Scholar
  14. Rumelhart, D, Hinton, GE, Williams, RJ 1986Learning internal representation by error propagationMIT PressCambridge318362Google Scholar
  15. Sarle WS (1995) Stopped training and other remedies for overfitting. Proc. 27th Symposium on the Interface of Computing Science and Statistics, pp. 352–60Google Scholar
  16. Tang, B 1995Periods of linear development of the ENSO cycle and POP forecast experimentJ Climate8582691CrossRefGoogle Scholar
  17. Tangang, FT, Hsieh, WW, Tang, B 1997Forecasting the equatorial sea surface temperatures by neural network modelsClimate Dyn13135147CrossRefGoogle Scholar
  18. Tangang, FT, Tang, B, Monahan, AH, Hsieh, WW 1998Forecasting ENSO events: a neural network-extended EOF approachJ Climate112941CrossRefGoogle Scholar
  19. Webster, PJ, Magana, VO, Palmer, TN, Shukla, J, Thomas, RA, Yanai, M, Yasunari, T 1998Monsoons: Processes, predictability, and the prospects for predictionJ Geophys Res1031445114510CrossRefGoogle Scholar
  20. World Meteorological Organization (WMO) (2002) WMO Statement on the scientific basis for, and limitations of, weather and climate forecasting. Abridged report with resolutions. 54th Session of the WMO Executive Council, Geneva, 2002Google Scholar
  21. Zhang, GP 2007A neural network ensemble method with jittered training data for time series forecastingInform Sci17753295346CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2008

Authors and Affiliations

  1. 1.India Meteorological DepartmentPuneIndia

Personalised recommendations