Stochastic approach to determination of suspended sediment concentration in tidal rivers by artificial neural network and genetic algorithm

Author:

Adib A.1,Jahanbakhshan H.1

Affiliation:

1. Civil Engineering Department, Engineering Faculty, Shahid Chamran University, Ahvaz, Iran.

Abstract

Because of the interaction between tidal and fluvial flows in tidal rivers, sampling and measurement of suspended sediment concentration is very complex. Determination of suspended sediment concentration in tidal rivers is a very important problem in some countries such as Canada and United Kingdom (UK) (for example Bay of Fundy in Canada and Bristol Channel in UK). A numerical model cannot show suspended sediment concentration in tidal river accurately. Fluvial flows bring sand and gravel particles from the watershed, while tidal flow brings silt particles from the sea in flood time and returns them to the sea in ebb time. Interaction between tidal and fluvial flows, relation between suspended sediment concentration and return periods of them, correction of suspended sediment distribution coefficient for use in tidal limit of rivers, finding the best method for determination of suspended sediment concentration in tidal limit of rivers and optimization of it are major difficulties and challenges for determination of suspended sediment concentration. For overcoming these challenges in this research, a perceptron artificial neural network is trained and validated by observed data. For training of the artificial neural network (ANN), Levenberg–Marquardt training method is applied. For decreasing of the mean square error (MSE) and increasing of efficiency coefficient, parameters of ANN are optimized by genetic algorithm (GA) method. The GA method optimizes the number of nodes of hidden layers of ANN that is trained by Levenberg–Marquardt training method. Two sets of data are introduced into a network. Inputs of first network are distance from upstream of river, flood return period, and tide return period. These return periods are determined by observed data and governing stochastic distribution on them. Inputs of second network are distance from upstream of river, flood discharge, and ebb height. Output of these networks is suspended sediment concentration. Observed data show that maximum suspended sediment concentration is concerned with ebb that tidal flow and fluvial flow are in one direction. Because of a shortage of observed data especially in extreme conditions, a numerical model was developed. This model was calibrated by observed data. Results of numerical model convert to two regression relations. These relations are functions of distance from the upstream of river, discharge of flood (or flood return period) at upstream, and ebb height (or ebb return period) at downstream. Then the artificial neural network is tested with the remainder of observed data and results of the numerical model. Sensitive analysis shows that distance from the upstream of river and flood discharge are the most effective governing factors on suspended sediment concentration in first and second network, respectively. For the case study, the Karun River in south west of Iran is considered. This river is the most important tidal river in Iran.

Publisher

Canadian Science Publishing

Subject

General Environmental Science,Civil and Structural Engineering

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3