علوم و مهندسی آبیاری

علوم و مهندسی آبیاری

Modeling of longitudinal dispersion coefficients in meandering streams using soft computing techniques

نوع مقاله : مقاله پژوهشی

نویسندگان
1 Assistant Professor of Water Engineering and Environment Faculty, Shahid Chamran Univeristy of Ahvaz,Ahvaz, Iran.
2 Assistant professor, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
3 Shahid Chamran university f ahvaz
چکیده
Modeling and estimating the longitudinal dispersion coefficient (LDC) of pollutants in rivers play a crucial role in reducing contamination and improving river water quality. In the present study, the LDC in meandering rivers was modeled and estimated using soft computing techniques, including the Group Method of Data Handling (GMDH) and Artificial Neural Network (ANN) models. For this purpose, flow depth, channel width, mean velocity, shear velocity, and river path sinuosity factor were considered as input parameters. Simulation results indicated that the GMDH model with two hidden layers—comprising four neurons in the first hidden layer and three neurons in the second—was able to predict the longitudinal dispersion coefficient with satisfactory statistical accuracy (R^2=0.85). Similarly, the ANN model with a single hidden layer containing ten neurons and a logarithmic sigmoid activation function provided reliable predictive performance (R^2=0.90). Analysis of the GMDH model structure revealed that the ratio of mean velocity to shear velocity plays a dominant role in predicting the longitudinal dispersion coefficient in meandering rivers.
کلیدواژه‌ها
موضوعات


مقالات آماده انتشار، پذیرفته شده
انتشار آنلاین از 21 مهر 1405

  • تاریخ دریافت 0-892 فروردین 786
  • تاریخ بازنگری 0-724 فروردین 786
  • تاریخ پذیرش 0-710 فروردین 786
  • تاریخ انتشار 21 مهر 1405