Browse by author
Lookup NU author(s): Dr Jie ZhangORCiD
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
The escalating environmental harm inflicted upon rivers is an unavoidable outcome resulting from climatefluctuations and anthropogenic activities, leading to a catastrophic impact on water quality and thousands ofindividuals succumb to waterborne diseases. Consequently, the water quality monitoring stations have beenestablished worldwide. Regrettably, the real-time evaluation of Water Quality Index (WQI) is hindered by theintricate nature of off-site water quality parameters. Thus, there is a pressing need to create a precise and robustwater quality prediction model. The dynamic and non-linear characteristics of water quality parameters posesignificant challenges for conventional machine learning algorithms like multi-linear regression, as they struggleto capture these complexities. In this particular investigation, machine learning model called FeedforwardArtificial Neural Networks (FANNs) was employed to develop WQI prediction model of Batu Pahat River,Malaysia exclusively utilizing on-site parameters. The proposed method involves a consideration of whether toinclude or exclude parameters such as BOD and COD, which are not measured in real time and can be costly tomonitor as model inputs. Validation accuracy values of 99.53%, 97.99%, and 91.03% were achieved in threedifferent scenarios: the first scenario utilized the full input, the second scenario excluded BOD, and the thirdscenario excluded both BOD and COD. It was suggested that the model has better predictive power between inputvariables and output variables. Factor contributed to river pollution has been identified and mitigation plan forBatu Pahat river pollution has been proposed. This could provide an effective alternative to compute thepollution, better manage water resources and mitigate negative impacts of climate change of river ecosystems.
Author(s): Azha SF, Sidek LM, Ahmad Z, Zhang J, Basri H, Zawawi MH, Noh NM, Ahmed AN
Publication type: Article
Publication status: Published
Journal: Ecological Indicators
Year: 2023
Volume: 156
Print publication date: 01/12/2023
Online publication date: 06/11/2023
Acceptance date: 29/10/2023
Date deposited: 29/11/2023
ISSN (print): 1470-160X
ISSN (electronic): 1872-7034
Publisher: Elsevier
URL: https://doi.org/10.1016/j.ecolind.2023.111190
DOI: 10.1016/j.ecolind.2023.111190
Data Access Statement: Data will be made available on request.
Altmetrics provided by Altmetric
