Publication:
Development of prediction model for phosphate in reservoir water system based machine learning algorithms

Simple item page
dc.citedby12
dc.contributor.authorLatif S.D.en_US
dc.contributor.authorBirima A.H.en_US
dc.contributor.authorAhmed A.N.en_US
dc.contributor.authorHatem D.M.en_US
dc.contributor.authorAl-Ansari N.en_US
dc.contributor.authorFai C.M.en_US
dc.contributor.authorEl-Shafie A.en_US
dc.contributor.authorid57216081524en_US
dc.contributor.authorid23466519000en_US
dc.contributor.authorid57214837520en_US
dc.contributor.authorid57226012037en_US
dc.contributor.authorid51664437800en_US
dc.contributor.authorid57214146115en_US
dc.contributor.authorid16068189400en_US
dc.date.accessioned2023-05-29T09:42:33Z
dc.date.available2023-05-29T09:42:33Z
dc.date.issued2022
dc.descriptionDecision trees; Eutrophication; Forecasting; Learning systems; Neural networks; Phosphate fertilizers; Predictive analytics; Reservoirs (water); Stochastic systems; Support vector machines; Water pollution; Water quality; Water supply; Conventional modeling; Cross validation; Developed model; Non-point source pollution; Prediction model; Primary sources; Statistical indices; Water quality parameters; Learning algorithmsen_US
dc.description.abstractPhosphate (PO4) is a major component of most fertilizers, and when erosion and runoff occur, large amounts of it enter the water bodies, causing several problems such as eutrophication. Feitsui reservoir, the primary source of water supply to Taipei, reported half of the reservoir's pollutants from nonpoint-source pollution. The value of the PO4 in the water body fluctuates in highly nonlinear and stochastic patterns. However, conventional modeling techniques are no longer sufficiently effective in predicting accurately such stochastic patterns in the concentrations of PO4 in water. Therefore, this study proposes different machine learning algorithms: the artificial neural network (ANN), support vector machine (SVM), random forest (RF), and boosted trees (BT) to predict the concentration of PO4. Monthly measured data between 1986 and 2014 were used to train and test the accuracy of these models. The performances of these models were examined using different statistical indices. Hyperparameters optimization such as cross-validation was performed to enhance the precision of the models. Five water quality parameters were used as input to the proposed models. Different input combinations were explored to optimize the precision. The findings revealed that ANN outperformed the other three models to capture the changes in the concentrations of PO4 with high precision where RMSE is equal to 1.199, MAE is equal to 0.858, and R2 is equal to 0.979, MSE is equal to 1.439, and finally, CC is equal to 0.9909. The developed model could be used as a reliable means for managing eutrophication problems. � 2021 THE AUTHORSen_US
dc.description.natureFinalen_US
dc.identifier.ArtNo101523
dc.identifier.doi10.1016/j.asej.2021.06.009
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85110194763
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85110194763&doi=10.1016%2fj.asej.2021.06.009&partnerID=40&md5=ea07a43edb74e5a5a8197a1a0aeafcd6
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/27314
dc.identifier.volume13
dc.publisherAin Shams Universityen_US
dc.relation.ispartofAll Open Access, Gold, Green
dc.sourceScopus
dc.sourcetitleAin Shams Engineering Journal
dc.titleDevelopment of prediction model for phosphate in reservoir water system based machine learning algorithmsen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS