Application of artificial neural network models for predicting water quality index
This study discusses the development and validation of an Artificial Neural Network (ANN) model in estimating water quality index (WQI) in the Langat River Basin, Malaysia. The ANN model has been developed and tested using data from 30 monitoring stations. The modeling data was divided into two sets...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://web.utm.my/ipasa/images/stories/MJCE/2004/vol_16_no_2/Application%20of%20Artificial%20Neural%20Network%20Models%20for%20Predicting%20Water%20Quality%20Index.pdf http://web.utm.my/ipasa/images/stories/MJCE/2004/vol_16_no_2/Application%20of%20Artificial%20Neural%20Network%20Models%20for%20Predicting%20Water%20Quality%20Index.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study discusses the development and validation of an Artificial Neural Network (ANN) model in estimating water quality index (WQI) in the Langat River Basin, Malaysia. The ANN model has been developed and tested using data from 30 monitoring stations. The modeling data was divided into two sets. For the first set, ANNs were trained, tested and validated using six independent water quality variables as input parameters. Consequently, Multiple Linear Regression (MLR) was applied to eliminate independent variables that exhibit the lowest contribution in variance. Independent variables that accounted for approximately 71% of the variance in WQI are Dissolved Oxygen (DO), Biochemical Oxygen Demand (BOD), Suspended Solids (SS) and Ammoniacal-Nitrate (AN). The Chemical Oxygen Demand (COD) and pH contributed only 8% and 2% to the variance, respectively. Thus, in the second data set, only four independent variables were used to train, test and validate the ANNs. We found that the correlation coefficient given by six independent variables (0.92) is only slightly better in
estimating WQI compared to four independent variables (0.91) which demonstrates that ANN is capable of estimating WQI with acceptable accuracy when it is trained by eliminating COD and pH as independent variables. |
|---|