Flood forecasting

1345 Words3 Pages

For water level forecasting especially in the flood period, the data were selected only from July to October which is a regular monsoon flood season in Myanmar and most Asian countries. In order to characterize the variation of water level at Mawlaik station, descriptive statistics were calculated. As shown in Fig. 2, the frequency distribution exhibits almost a normal distribution, although the data was slightly skewed. The Kolmogorov-Smirnov test was also used to numerically check the normality of the data whose size is 2706. The null hypothesis of normality is rejected if the probability (p) value is smaller than the significance level of 0.05. Since the p value associated with the normality test is 0.001, the test statistically detected a non-normal distribution of the large data set. However, with a low skewness (0.3) and small kurtosis (-0.56), there seem to be trivial departures from normality for the water level series at Mawlaik station and the distribution is reasonably close to the normality. For large sample sizes, significant results would be derived even in the case of a small deviation from normality, but detecting non-normality would not affect any statistical analysis (Ghasemi and Zahediasl 2012). It is also imperative that the training and validation sets are representative of the same population. In the model development 80% of the flood season data (1990-2007) were used for calibration while 20% (2008-2011) were used for validation. For ANN models, the calibration data were further randomly divided into 80% for training set and 20% for the testing set. Before applying the ANN models, the calibration data sets of river stage and rainfall were standardized in a linear scale subtracting the mean and divided by th... ... middle of paper ... ...din AY (2010) Artificial neural network model for river flow forecasting in a developing country. IWA Journal of Hydroinformatics 12(1): 22-34. Sentu D, Regulwar DG (2011) Inflow prediction by different neural network architectures: A case study. International journal of earth sciences and engineering 4(6): 225-230. Tareghian R, Kashefipour SM (2007) Application of Fuzzy Systems and Artificial Neural Networks for flood forecasting. Journal of Applied Sciences 7(22): 3451-3459. Thirumalaiah K, Deo MC (1998) Real-Time Flood Forecasting Using Neural Networks. Computer Aided Civil and Infrastructure Engineering 13: 101-111. Wang W (2006) Stochasticity, Nonlinearity and Forecasting of Streamflow Processes. Amsterdam, IOS Press. Wu C L, Chau KW, Li Y S (2008) River stage prediction based on a distributed support vector regression. Journal of hydrology 358: 96-111.

Open Document