Dispersion Coefficient Prediction Using Empirical Models and ANNs

被引：27

作者：

Antonopoulos V.Z. ^{[1
]}

Georgiou P.E. ^{[1
]}

Antonopoulos Z.V. ^{[1
]}

机构：

[1] Department of Hydraulics, Soil Science and Agricultural Engineering, School of Agriculture, Aristotle University of Thessaloniki, Thessaloniki

来源：

Environmental Processes | 2015年 / 2卷 / 02期

关键词：

Artificial neural networks; Axios river; Dispersion coefficient; Empirical equations; Mass transport; Pollution;

D O I：

10.1007/s40710-015-0074-6

中图分类号：

X52 [水体污染及其防治];

学科分类号：

0815 ;

摘要：

The concentration of a conservative pollutant is changed along a river, as a result of transport processes. The dispersion coefficient is the most important parameter of mass transport in rivers. In this paper, the dispersion coefficient was estimated in a section of Axios River, with the analytical procedure of Fischer method, under different hydrological and hydrodynamic conditions. An empirical equation and a model of artificial neural networks (ANNs) for dispersion coefficient were proposed, based on the data estimated with analytical Fischer method. The dispersion coefficients predicted by the proposed models and other empirical equations reported in earlier studies were compared to the coefficients obtained in the present study. The most accurate equations for dispersion coefficient were used to predict the concentration of conservative toxic pollutants released instantaneously in Axios River upstream of the border of Greece-Former Yugoslav Republic of Macedonia (FYROM). © 2015 Springer International Publishing Switzerland.

引用

页码：379 / 394

页数：15

共 40 条

[1]

Akratos C.S., Papaspyros J.N.E., Tsichrintzis V.A., An artificial neural networks model and design equations for BOD and COD removal prediction in horizontal subsurface flow constructed wetlands, Chem Eng J, 143, pp. 96-110, (2008)

[2]

Antonopoulos V.Z., Antonopoulos Z.V., Estimation of dispersion coefficient in Axios river, Proceedings of the Conference of the "Greek Hydrotechnical Association" and the "Greek Committee for Water Resources Management", Volos, pp. 427-434, (2009)

[3]

Antonopoulos Z.V., Vafeiadis M., Katsifarakis K.L., Spachos T., Simulation of a karstic aquifer using artificial neural networks, Int. Conf. of Protection and Restoration of the Environment XI, E-proceedings, Thessaloniki, pp. 279-287, (2012)

[4]

Artificial neural networks in hydrology II: Hydrological applications, J Hydrol Eng, 5, 2, pp. 115-123, (2000)

[5]

Chapra S.C., Surface Water-quality Modeling, (1997)

[6]

Deng Z.Q., Singh V.P., Bengtsson L., Longitudinal dispersion coefficient in straight rivers, J Hydraul Eng ASCE, 127, pp. 919-927, (2001)

[7]

Diamantopoulou M.J., Georgiou P.E., Papamichail D.M., A time delay artificial neural network approach for flow routing in a river system, Hydrol Earth Syst Sci Discuss, 3, pp. 2735-2756, (2006)

[8]

Diamantopoulou M.J., Antonopoulos V.Z., Papamichail D.M., Cascade correlation artificial neural networks for estimating missing monthly values of water quality parameters in rivers, Water Resour Manag, 21, pp. 649-662, (2007)

[9]

Dogan E., Sengorur B., Koklu R., Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique, J Environ Manag, 90, 2, pp. 1229-1235, (2009)

[10]

Etemad-Shahidi A., Taghipour M., Predicting longitudinal dispersion coefficient in natural streams using M5' model tree, J Hydraul Eng ASCE, 138, pp. 542-555, (2012)

← 1 2 3 4 →