1. Title, Journal and Authors

Title: Efficient river water quality index prediction considering minimal number of inputs variables

Journal: Engineering Applications of Computational Fluid Mechanics

Authors: Faridah Othman, M.E. Alaaeldin, Mohammed Seyam, Ali Najah Ahmed, Fang Yenn Teo, Chow Ming Fai, Haitham Abdulmohsin Afan, Mohsen Sherif, Ahmed Sefelnasr & Ahmed El-Shafie

 

2. Summary

This study progress monitoring in Klang River basin, Malaysia.

This study analyze the river water quality and calculate the parameter for six factors [COD, BOD, DO, SS, pH, AN] that effect to the Water Quality Index(WQI).

Of all six factors, the most influential factor is DO and the most un-influential factor is pH.

 

3. Originality and Creativity

This study make the input approach method by using the ANNs(Artificial Neural Networks) to calculate exact Water Quality Index(WQI) value.

After many attempts, MLP of many neural network models is decided to the most suitable model. In this study, 6 neurons were set for the input layer, 7 neurons for the hidden layer, and 1 neurons for the output layer.

And for the performance evaluation of this model, evaluation methods such as MAE (mean absolute error), ABS (maximum and minimum absolute error), RMSE (root mean square error), and NRMSE (normalized root mean square error) were used.

 

4. Application to research

 

 

5. Contact

Kyoungrim Ma / M.S. program

 

Environmental Systems Engineering Lab.

School of Earth Sciences and Environmental Engineering

Gwangju Institute of Science and Technology

1 Oryong-dong Buk-gu Gwangju, 500-712, Korea

 

Phone : 010-5058-6832

E-mail : dkvmfhelxp34@gm.gist.ac.kr