1. Title, Journal and Authors
Title : River Water Quality Modelling using Artificial Neural Network Technique
Journal : Science Direct
Authors : Archana Sarkara*, Prashant Pandeyb
2. Summary
Cities namely New Delhi and Mathura located upstream of the Yamuna River that has discharged non-pretreatment waste to the river have made the impaired water quality of the river. In contrast, the demand of the Indian authorities for using the river water has been increased as time passes. Thus, accurate measurement and simulation of the water quality have been important for the plan for using the basin and management for the pollution of water quality. The purpose of this study is to predict the Dissolved Oxygen(DO) concentration that facilitates the self-purification of rivers and used as an indicator for water quality. In this study, Artificial Neural Network was used for simulating the DO concentration, feed forward error backpropagation technique was used for updating the weights. Data sets composed of electrical conductivity, travel time, flow discharge, pH, Biochemical Oxygen Demand(BOD), Temperature, DO was used for study, and compared to each data sets consisted of various combination by input stations and input variables, namely: (A) all data sets (Mathura-upstream, central, downstream) except DO values at downstream, 14 input nodes, (B) all data sets for the upstream and central, 10 input nodes, (C) all data sets for the upstream, 5 input nodes. The performance of the ANN evaluated by statistical methods (Root Mean Square Error, Coefficient of Correlation, Coefficient of Determination). As a result, the data set(B) shows the performance of accurate prediction (RMSE = 1.52, R = 0.928). The results indicated that optimization of data sets and nodes leads to accurate prediction of ANN.
3. Originality and Creativity
4. Application to research
5. Contact
Yeong-gyu Gu / Intern student
Environmental Systems Engineering Lab.
School of Earth Sciences and Environmental EngineeringGwangju Institute of Science and Technology
1 Oryong-dong Buk-gu Gwangju, 500-712, Korea
Phone : +82-10-6589-6653
E-mail : kududrb1@naver.com