Evaluation of Hybrid Metaheuristic Models in Estimating Electrical Conductivity (Case Study: Kakarza River, Lorestan Province)

Electrical conductivity (EC) is an important indicator for monitoring water quality in rivers. Electrical conductivity is inherently related to the concentration of dissolved ionic compounds present in aquatic environments, including various salts and minerals. Estimating electrical conductivity is crucial for environmental monitoring and assessing the overall health of aquatic ecosystems. In this research, a hybrid intelligent model based on the Support Vector Regression (SVR) approach was developed to estimate the electrical conductivity of river water. For this purpose, three optimization algorithms, including Wavelet, Whale, and Particle Swarm Optimization (PSO), were used to model the electrical conductivity of the river flow. For modeling, statistics and information from the Kakarza River hydrometric station, located in Lorestan province, were used as a case study in ۷ combined scenarios of input parameters for the years ۲۰۰۳-۲۰۲۳. To evaluate the performance of the models, the evaluation criteria of correlation coefficient, root mean square error, mean absolute error, and Nash-Sutcliffe coefficient were used. The results showed that combined scenarios in the models under investigation improve the model performance. Furthermore, the results obtained from the evaluation criteria showed that the Support Vector Regression-Wavelet model has a correlation coefficient of ۰.۹۸۰, a root mean square error of ۰.۳۴۴ (ppm), a mean absolute error of ۰.۱۷۲ (ppm), and a Nash-Sutcliffe coefficient of ۰.۹۸۵ in the validation phase. Overall, the results showed that the use of intelligent models based on the support vector regression approach can be an effective approach in river engineering sustainability.

کلیدواژه ها:

Kakarza River ، water quality ، Electrical conductivity ، Wavelet