JACIII Vol.18 No.6 pp. 999-1006
doi: 10.20965/jaciii.2014.p0999


Monthly Maximum Accumulated Precipitation Forecasting Using Local Precipitation Data and Global Climate Modes

Junaida Binti Sulaiman, Herdianti Darwis, and Hideo Hirose

Department of Systems Design and Informatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka-shi, 820-8502 Fukuoka, Japan

February 20, 2014
June 13, 2014
Online released:
November 20, 2014
November 20, 2014
artificial neural networks, particle swarm optimization, extreme precipitation, seasonal autoregressive integrated moving average (ARIMA), regression analysis

Successive days of precipitation are known to cause flooding in monsoon-susceptible countries. Forecasting of daily precipitation facilitates the prediction of the occurrences of rainfall and number of wet days. Using the maximum five-day accumulated precipitation (MX5d), we can predict the magnitude of precipitation in a specific period as it may indicate the extreme precipitation. In this study, a method to forecast monthly extreme precipitation using artificial neural networks (ANNs) is assessed using past MX5d data and global climate indices such as Southern Oscillation Index (SOI), Madden Julian Oscillation (MJO), and Dipole Mode Index (DMI) in Kuantan and Kota Bharu, Malaysia. The use of combined inputs (MX5d with SOI, MJO, and DMI) is proposed to investigate the concurrent effect of lagged values of local precipitation data and global climate indices on seasonal extreme precipitation. Four cases of data are sampled representing two major seasonal variations in Malaysia. The analysis of extreme precipitation trends is important for the prediction of high precipitation events. ANNs are widely applied in the hydrology field because of their nonlinear ability in predicting nonstationary and seasonal data. In this paper, we have compared ANNs with seasonal autoregressive integrated moving average (ARIMA) and regression analysis using out-of-sample test data. The results for Kuantan indicate that seasonal ARIMA is the best method to forecast extreme precipitation when MX5d lags are used as input. For Kota Bharu, ANN exhibits better generalization ability than ARIMA and regression analysis when dual inputs (lagged MX5d and lagged global climate indices) are utilized in the model.

  1. [1] R. S. V. Teegavarapu, A. Goly, C. Viswanathan, and P. Behera, “Precipitation Extremes and Climate Change: Evaluation Using Descriptive WMO Indices,” World Environmental and Water Resources Congress 2012, No.2011, pp. 1927-1936, 2012.
  2. [2] Z. Zeng, W. W. Hsieh, A. Shabbar, and W. R. Burrows, “Seasonal prediction of winter extreme precipitation over Canada by support vector regression,” Hydrology and Earth System Sciences, Vol.15, No.1, pp. 65-74, Jan. 2011.
  3. [3] L. Foresti, A. Pozdnoukhov, and D. Tuia, “Extreme precipitation modelling using geostatistics and machine learning algorithms,” geoENV VII Geostatistics for Environmental Applications, No.Ml, pp. 41-52, 2010.
  4. [4] S. Othman, “Adaptation to Climate Change and Reducing Natural Disaster Risk: A Study on Country Practices and Lesson between Malaysia and Japan,” Malaysian Meteorological Department, Kuala Lumpur, Malaysia, 2011.
  5. [5] A. El-Shafie, A. Noureldin, M. Taha, A. Hussain, and M. Mukhlisin, “Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia,” Hydrology and Earth System Sciences, Vol.16, No.4, pp. 1151-1169, Apr. 2012.
  6. [6] N. Q. Hung, M. S. Babel, S. Weesakul, and N. K. Tripathi, “An artificial neural network model for rainfall forecasting in Bangkok, Thailand,” Hydrology and Earth System Sciences, Vol.13, No.8, pp. 1413-1425, Aug. 2009.
  7. [7] J. Sulaiman and H. Hirose, “A method to predict heavy precipitation using the Artificial Neural Networks with an application,” 2012 7th Int. Conf. on Computing and Convergence Technology (ICCCT), Vol.3-5, pp. 663-667, Dec. 2012.
  8. [8] R. May, G. Dandy, and H. Maier, “Review of Input Variable Selection Methods for Artificial Neural Network,” Artificial Neural Networks – Methodological Advances and Biomedical Applications, K. Suzuki (Ed.), pp. 9-44, InTech, 2011.
  9. [9] K. P. Sudheer, a. K. Gosain, and K. S. Ramasastri, “A data-driven algorithm for constructing artificial neural network rainfall-runoff models,” Hydrological Processes, Vol.16, No.6, pp. 1325-1330, Apr. 2002.
  10. [10] G. Zhang, B. Eddy Patuwo, and M. Y. Hu, “Forecasting with artificial neural networks,” Int. J. of Forecasting, Vol.14, No.1, pp. 35-62, Mar. 1998.
  11. [11] S. Chattopadhyay and G. Chattopadhyay, “Comparative study among different neural net learning algorithms applied to rainfall time series,” Meteorological Applications, Vol.15, No.2, pp. 273-280, 2008.
  12. [12] S. S. Monira, Z. M. Faisal, and H. Hirose, “A Neural Network Ensemble Incorporated with Dynamic Variable Selection for Rainfall Forecast,” 2011 12th ACIS Int. Conf. on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, pp. 7-12, Jul. 2011.
  13. [13] C. H. Aladag, U. Yolcu, and E. Egrioglu, “A New Multiplicative Seasonal Neural Network Model Based on Particle Swarm Optimization,” Neural Processing Letters, Vol.37, No.3, pp. 251-262, Sep. 2012.
  14. [14] G. E. P. Box, G. M. Jenkins, and G. C. Reissel, “Time Series Analysis Forecasting and Control,” 3rd edition, Prentice Hall, 1994.
  15. [15] National Climatic Data Centre, USA [Accessed November 15, 2013].
  16. [16] WorldMeteorological Organization, “Guidelines on Analysis of extremes in a changing climate in support of informed decisions for adaptation,” Geneva, 2009.
  17. [17] P. Kun Liong and N. A. Shaari, “A Study on The Extreme Daily Rainfall Cases in Northwest Peninsular Malaysia,” Research Publication No. 6/2011, Malaysian Meteorological Department, Kuala Lumpur, Malaysia, 2011.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, IE9,10,11, Opera.

Last updated on Mar. 28, 2017