Evaluating Decision Tree Efficiency in Combination with Wavelet Transform to Predict Groundwater Level Fluctuation

Accurate monitoring of groundwater levels and estimating their fluctuations in the future is of importance, especially in arid and semi-arid areas. regarding the high capabilities of AI-based models in the modeling of hydrologic phenomena, this research used the MP5 decision tree, in combination with the wavelet transform, to predict groundwater level fluctuations of the Kerman-Bagheyn plane. To develop the wavelet-decision tree (W-M5p) hybrid model, the wavelet transformation outputs were exported to the MP5 as inputs. Several statistical criteria, including coefficient of correlation (R), agreement index (Ia), and scattering index (SI), were used to evaluate the performance of the hybrid model compared to the single model. The results indicated that, even when the inputs of the hybrid model includes only the meteorological data from a synoptic station (the water level of previous periods were not used in the analysis), that the performance of the WM5P was superior to the single model in the prediction of groundwater fluctuations. The WM5P model with three months of forecast horizon with the Coif4 wavelet and decomposition level of 6 reduced the SI value from 0.6394 to 0.0181 and, at the same time, increased the Ia from 0.6898 to 0.9998. Consequently, the Coiflet4 with decomposition levels of 5 and 6 was the most efficient wavelet in the hybrid model for reliable estimation of the Kerman-Bagheyn plane groundwater level.