Paper Title
Genetic Algorithm To Predict The Longitudinal Dispersion Coefficient In Natural Rivers

Abstract
Although different studies have been carried out on estimating Longitudinal Dispersion Coefficient (LDC) in natural rivers, the inaccuracy and less user-friendliness of the provided models to predict LDC requires more research to focus on. Thus, the main objective of this study is to develop an empirical model by means of genetic algorithm. For this purpose, a set of patterns containing hydraulic and geometric characteristics of 30 rivers in United States was used for calibration of the model and testing the acquired results. Results show that the pattern including the river curvature parameter has the best performance for LDC prediction model. The best model resulted in 0.9435 and 0.9419 for the coefficient of determination (R2) in calibration and test data sets, respectively. Detailed comparison of the implemented model respect to the precedent studies confirmed the genetic algorithm as an accurate estimator for LDC. Keywords- Genetic Algorithm, Longitudinal Dispersion Coefficient, Natural Rivers, Empirical Models