Fariborz Yosefvand; Saeid Shabanlou
Abstract
In this study, for the first time, groundwater level (GWL) variations of the Sarab-e Qanbar well located in the city of Kermanshah, are simulated over a 13-year period by a hybrid model named WANFIS (wavelet-adaptive neuro fuzzy inference system). In order to develop the hybrid model, the wavelet transform ...
Read More
In this study, for the first time, groundwater level (GWL) variations of the Sarab-e Qanbar well located in the city of Kermanshah, are simulated over a 13-year period by a hybrid model named WANFIS (wavelet-adaptive neuro fuzzy inference system). In order to develop the hybrid model, the wavelet transform and the adaptive neuro fuzzy inference system (ANFIS) model are utilized. Furthermore, the 9 and 4 year data are used for training and testing the artificial intelligence models, respectively. Moreover, the effective lags are detected by the autocorrelation function (ACF) and then eight different models are developed for each of the ANFIS and WANFIS models using them. After that, all mother wavelets are evaluated and Dmey mother wavelet is chosen as the most optimal. For this mother wavelet, the values of scatter index (SI), variance account for (VAF) and Root mean square error (RMSE) are obtained 0.192, 94.951 and 3.117, respectively. Next, the superior model is detected through the analysis of the results obtained by all ANFIS and WANFIS models. The superior model estimates the objective function values with reasonable accuracy. For example, the correlation coefficient (R), Scatter Index (SI) and variance account for (VAF) for this model are obtained 0.974, 0.192 and 94.951, respectively. The modeling results indicate that the wavelet transform noticeably enhances the ANFIS model accuracy. Finally, the lags of the time series data for the Sarab-e Qanbar well including (t-1), (t-2), (t-3) and (t-4) are introduced as the most effective lags.
Sajad Shahabi; Masoud Reza Hessami Kermani
Volume 2, Issue 1 , March 2015, , Pages 122-130
Abstract
In this paper we present a method to perform flood frequency analysis (FFA) when the assumption of stationary is not important (or not valid). A wavelet transform model is developed to FFA. A full series is applied to FFA using two different wavelet functions, and then a combined method is investigated. ...
Read More
In this paper we present a method to perform flood frequency analysis (FFA) when the assumption of stationary is not important (or not valid). A wavelet transform model is developed to FFA. A full series is applied to FFA using two different wavelet functions, and then a combined method is investigated. In the combined method, all discharge data which were less than the lowest value of annual maximum (AM) discharge were removed. Furthermore, energy function of wavelet was used for FFA. The data was decomposed into some details and an approximation through different wavelet functions and decomposition levels. The approximation series was employed to FFA. This was performed using discharge data from of the Polroud River in Iran. This paper analysis was performed on the daily maximum discharge data from the Tollat station in the north of Iran. Data from 1975 to 2007 was evaluated by wavelet analysis. The study shows that wavelet full series model results (density function) are too small in compared with the results of combined method and they are both lesser than traditional methods (AM and PD). In other hand the results of energy function method is closed to the combined method when they are compared with the full series data results. These wavelet models were assessed with the AM and PD methods. The concrete result of this paper is that, the basin hydrologic conditions and data's nature are very important parameters to improve FFA and to select the best method of analysis.
