作者: Maryam Shafaei , Ozgur Kisi
DOI: 10.1007/S11269-015-1147-Z
关键词:
摘要: Accurate predicting of lake level fluctuations is essential and basic in water resources management for supply purposes. The complicated because it affected by nonlinear hydrological processes. This paper applies integrated wavelet auto regressive moving average (ARMA), adaptive neuro fuzzy inference system (ANFIS) support vector regression (SVR) models forecasting monthly fluctuations. First, time series decomposed into low high frequency components using discrete transform. Then, each component separately predicted ARMA, ANFIS SVR models. Finally, the are summed to obtain estimated original series. performance proposed WSVR (Wavelet-SVR), WANFIS (Wavelet-ANFIS) WARMA (Wavelet-ARMA) compared with single Results show that give better precision levels study region when model found be slightly than other