Predicting Longitudinal Dispersion Coefficient in Natural Streams by Artificial Neural Network

Abstract

An artificial neural network ͑ANN͒ model was developed to predict the longitudinal dispersion coefficient in natural streams and rivers. The hydraulic variables ͓flow discharge ͑Q͒, flow depth ͑H͒, flow velocity ͑U͒, shear velocity ͑u * ͒, and relative shear velocity ͑U / u * ͔͒ and geometric characteristics ͓channel width ͑B͒, channel sinuosity ͑ ͒, and channel shape parameter ͑␤͔͒ constituted inputs to the ANN model, whereas the dispersion coefficient ͑K x ͒ was the target model output. The model was trained and tested using 71 data sets of hydraulic and geometric parameters and dispersion coefficients measured on 29 streams and rivers in the United States. The training of the ANN model was accomplished with an explained variance of 90% of the dispersion coefficient. The dispersion coefficient values predicted by the ANN model satisfactorily compared with the measured values corresponding to different hydraulic and geometric characteristics. The predicted values were also compared with those predicted using several equations that have been suggested in the literature and it was found that the ANN model was superior in predicting the dispersion coefficient. The results of sensitivity analysis indicated that the Q data alone would be sufficient for predicting more frequently occurring low values of the dispersion coefficient ͑K x Ͻ 100 m 2 /s͒. For narrower channels ͑B / H Ͻ 50͒ using only U / u* data would be sufficient to predict the coefficient. If ␤ and were used along with the flow variables, the prediction capability of the ANN model would be significantly improved.

Developing an Expert System for Predicting Pollutant Dispersion in Natural Streams

“…Comparisons of real measurements with results of equation 2 shows that in uniform flows average error of this equation is 30% and in non-uniform flows it is reaches to 4 times of real data (FaghforMaghrebi & Givehchi, 2007). It is difficult to use equation 2 in real and applied cases because the geometry of cross section h(y) and transverse velocity profile v(h) aren't available and can't be determined simply and because its impracticalities Fisher et al (Fisher et al, 1979) using several simple non-dimensional parameters proposed another equation (Tayfour & Singh, 2005) …”

“…In this equation √(u'2) is the deviation of velocity and shows size of deviation of average turbulent velocity from cross sectional average velocity (Tayfour & Singh, 2005 (Tayfour and Singh, 2005) Quien and quifer (1979) (Deong et al, 2001) Fisher (1976) 22 * 0.011 (Fisher et al, 1979) Liu and Chen(1980)…”

“…0.55 (Seo and Bake, 2002) Liu(1980) (Seo and Bake, 2002) Awasa and Ottawa(1991) (Tavakollizadeh and Kashefipur, 2007) Seo and chang (1998) (Seo and Cheong, 1998) Kasiez and Rodriguez(1998) (Sedighnezhad et al, 2007) Huang and li(1999) (Kashefipur and Falconer, 2002) Tavakolizadeh (2007) (Tavakollizadeh and Kashefipur, 2007) Tayfour and Singh (Tayfour & Singh, 2005) based on the ability of artificial neural networks determined longitudinal dispersion coefficient in natural rivers (Tayfour & Singh, 2005).…”

GA-optimized model predicts dispersion coefficient in natural channels

“…Recently, the artificial neural networks have been employed in the prediction of the dispersion coefficient using flow and channel geometric characteristics (Tayfur & Singh 2005;Rowinski et al 2005;Tayfur 2006). ANNs have an ability to capture relationships from given patterns and this ability has enabled them to be employed in the solution of large-scale complex problems.…”

Estimation of parameters of the transient storage model by means of multi-layer perceptron neural networks / Estimation des paramètres du modèle de transport TSM au moyen de réseaux de neurones perceptrons multi-couches

“…The only such attempt was presented recently by Cheong et al (2007), who applied the nonlinear multi-variable robust minimum covariance determinant method. Earlier, an approach pertaining to artificial neural networks (ANNs) applied to the Fickian model turned out to be successful Rowiński et al, 2005b;Tayfur & Singh, 2005;Piotrowski et al, 2006b) and, therefore, it has been decided to verify whether this approach would allow improvement in the evaluation of the TSM parameters. The main problem is that available data, necessary to optimize the system, are rather scarce and the data requirements are larger than in the case of the Fickian model, mainly because the TSM parameters have less recognized physical interpretation.…”