Evaluation of the success of the hybrid wavelet-based ANFIS approach in the estimation of monthly stream flows of the Bitlis River, Turkey

Abstract

This study aimed to predict monthly flows using an adaptive neuro-fuzzy inference system (ANFIS) and wavelet-ANFIS (W-ANFIS) and to determine the effect of wavelet transformation on the success of the machine learning model. For this purpose, the model inputs are divided into three subcomponents with Daubechies 10 mother wavelets. Subcomponents with the highest correlation were chosen as inputs. The most suitable models were selected by dividing the inputs into 3–7 sub-sets, using 11 different lagged input combinations, and testing various membership functions. In establishing the ANFIS model, 75% of the data were used for training and 25% for testing. The performance of ANFIS models was evaluated with root mean square error, Pearson correlation coefficient, determination coefficients, and Taylor diagram. A model with two sub-sets, a hybrid learning algorithm, a Gbellmf membership function, and 400 iterations was selected as the most suitable. It was concluded that the W-ANFIS model used with the wavelet transform method increased the success of the established ANFIS model. Moreover, it was suggested that the W-ANFIS hybrid machine learning model established in the study can be used effectively in similar climatic regions fed by snowmelt and dominated by a semi-arid climate. HIGHLIGHTS A hybrid approach is designed by combining the wavelet transform ANFIS model to estimate monthly stream flows.; The wavelet-ANFIS model is quite successful compared to the single ANFIS model in semi-arid climates fed by snowmelt.; The hybrid wavelet-ANFIS model, established using streamflow values with a delay of up to 6 months in estimating monthly stream flows, has the highest accuracy.;

Keywords

• adaptive neuro-fuzzy inference system (anfis)
• bitlis river
• daubechies wavelet
• discrete wavelet transform (dwt)
• streamflow