Fuzzy Spatial Forecasting Model of Rainfall Distribution for Flood Early Warning
Flood is commonly known as one of the most frequent type of natural disaster worldwide that occurred when the ground is not able to absorb and accommodate the heavy rainfall. Flood might be caused by increased levels of river water more than the river bank or the dams. Many methods have been proposed to forecast the rainfall distribution but mostly the forecasting accuracy of the existing method are questionable. In this paper, a fuzzy time series method was proposed to forecast the rainfall distribution. The objectives of this paper, first is to formulate fuzzy spatial forecasting model for rainfall distribution for each month in Perlis. Second, to predict the accurate rainfall values in future for early warning of flood in order to reduce flood issues. Using the fuzzy spatial forecasting method, the historical data of rainfall in Perlis were used to forecast. After that, several rules was applied to determine whether the rainfall forecasting trend value goes downward or upward movement Then, the mean square error (MSE) was calculated to compare the forecasting rainfall results of various forecasting method. The smaller the value of MSE, the better the forecasting model. The monthly historical rainfall distribution in Perlis for 4 years had been used to illustrate the forecasting algorithm of the new fuzzy time series method. The experimental results of this research exhibited higher forecasting accuracy for forecasting rainfall compare to existing methods.
KeywordsFlood Fuzzy forecasting Rainfall distribution
The study was funded by “Long Term Research Grant (LRGS) (UUM/RIMPC/P-30)” and the authors also thank the Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA for providing the laboratory facilities for completing the study.
- Bernama (2011) More people evacuated in flood-hit Perlis. Borneo Post http://www.theborneopost.com/2011/04/02/more-people-evacuated-in-flood-hit-perlis/
- Bol’shev LN (2001) Encyclopedia of mathematic. Statistical estimator. http://www.encyclopediaofmath.org/index.php/Statistical_estimator
- Ceballos A, Martinez-Fernandez J, Luengo-Ugidos MA (2004) Analysis of rainfall trends and dry periods on pluviometric gradient representative of Mediterranean climate in the Duero Basin, Spain. J Arid Env 58:215–233Google Scholar
- Chen SM, Hsu CC (2004) A new method to forecast enrollments using fuzzy time series. Int J Appl Sci Eng 2:234–244Google Scholar
- El-Shafie AH, El-Shafie A, El Mazoghi HG, Shehata A, Taha MR (2011) Artificial neural network techniques for rainfall forecasting applied to Alexandria, Egypt. Int J Phys Sci 6(6):1306–1316Google Scholar
- Flood List (2014) About flood. http://floodlist.com/aboutfloods
- Lazim M, Alias (2011) Introductory business forecasting a practical approach, 3rd edn. University Publication Center (UPENA), Shah AlamGoogle Scholar
- The official portal for department of irrigation and drainage Malaysia(2013). Flood management—program activities. Definition of flood. http://www.water.gov.my/our-services-mainmenu-252/flood-mitigation-mainmenu-323/programme-aamp-activities-mainmenu-199?lang=en
- Tymvios F, Savvidou K, Michaelides SC (2010) Association of geo potential height patterns with heavy rainfall events in Cyprus meteorological services, Nicosia, Cyprus. J Refereed Proc Spec Publ 23:73–78Google Scholar
- Wackerly D, Mendenhall W, Acheaffier RL (2007) Mathematical statistics with application, 7th edn. Brooks/Cole Cengage Learning, USAGoogle Scholar
- Zaw WT, Naing TT (2009) Modelling of rainfall prediction over Myanmar using polynomial regression. Int Conf Comput Eng Technol 1:316–320Google Scholar