A framework development for predicting the longitudinal dispersion coefficient in natural streams using an artificial neural network

2010 ◽  
Vol 30 (3) ◽  
pp. 439-449 ◽  
Author(s):  
R. Noori ◽  
A.R. Karbassi ◽  
H. Mehdizadeh ◽  
M. Vesali-Naseh ◽  
M.S. Sabahi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Dispersion Coefficient ◽  
Longitudinal Dispersion ◽  
Longitudinal Dispersion Coefficient ◽  
Natural Streams ◽  
Artificial Neural ◽  
Framework Development

A Genetic Algorithm-Artificial Neural Network Method for the Prediction of Longitudinal Dispersion Coefficient in Rivers

2011 ◽  
pp. 358-374
Author(s):  
Jianhua Yang ◽  
Evor L. Hines ◽  
Ian Guymer ◽  
Daciana D. Iliescu ◽  
Mark S. Leeson ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Dispersion Coefficient ◽  
Longitudinal Dispersion ◽  
Longitudinal Dispersion Coefficient ◽  
Artificial Neural ◽  
Input Variables ◽  
Training Examples ◽  
Artificial Neural Network Ann ◽  
Trained Neural Network

In this chapter a novel method, the Genetic Neural Mathematical Method (GNMM), for the prediction of longitudinal dispersion coefficient is presented. This hybrid method utilizes Genetic Algorithms (GAs) to identify variables that are being input into a Multi-Layer Perceptron (MLP) Artificial Neural Network (ANN), which simplifies the neural network structure and makes the training process more efficient. Once input variables are determined, GNMM processes the data using an MLP with the back-propagation algorithm. The MLP is presented with a series of training examples and the internal weights are adjusted in an attempt to model the input/output relationship. GNMM is able to extract regression rules from the trained neural network. The effectiveness of GNMM is demonstrated by means of case study data, which has previously been explored by other authors using various methods. By comparing the results generated by GNMM to those presented in the literature, the effectiveness of this methodology is demonstrated.

Experimental study on longitudinal mixing in open channel flow with various vegetation patterns

2020 ◽  
Author(s):  
Hyoungchul Park ◽  
Jinhwan Hwang
Keyword(s):  
Shear Flow ◽  
Dispersion Coefficient ◽  
Longitudinal Dispersion ◽  
Velocity Shear ◽  
Vegetation Patterns ◽  
Longitudinal Dispersion Coefficient ◽  
Mean Velocity ◽  
Natural Streams ◽  
Longitudinal Mixing ◽  
The Impact

<p>In natural streams, vegetation considerably has an influence on the flow characteristics in a variety of ways. For example, vegetation distorts flow structure in both lateral and vertical directions and changes the magnitude of turbulence and shear flow. Due to these effects, diluted contaminants in river transport and disperse differently. Accordingly, many previous researchers have investigated the impact of vegetation on the mixing process. Most of them have estimated the dispersion coefficient since this is the crucial parameter to quantify the degree of dispersion of contaminants numerically. They mainly studied in diverse characteristics of vegetation, such as density or submergence, etc., and identified the change in hydraulic parameters involving the dispersion coefficient.</p><p>In this work, considering the vegetation distributed in various forms in the natural river, we studied the effect of vegetation patterns on the longitudinal mixing coefficient. Six types of spatial patterns considered in this study are represented numerically by introducing the standardized Morisita index. Laboratory experiments with artificial emergent vegetation were performed in multiple vegetation patterns, and the longitudinal dispersion coefficient was estimated from the measured concentration curves by applying the routing technique. And we analyzed the cause of change in dispersion coefficient by calculating not only the dispersion coefficient but also the magnitude of mean velocity, shear flow, turbulence, etc.</p><p>According to the experimental results, the mean velocity in the vegetated channel is almost the same regardless of the type of pattern but is always lower than that in the non-vegetated channel. The longitudinal dispersion coefficient gets larger as the arrangement changes from uniform to 2D clumped pattern. The cause of change in coefficient is closely related to the spatial velocity gradients in both lateral and vertical directions since the spatial heterogeneity of velocity increases the magnitude of shear flow.</p>

Sign in / Sign up

Export Citation Format

Share Document