Publication:
Evaluation of deep learning algorithm for inflow forecasting: a case study of Durian Tunggal Reservoir, Peninsular Malaysia

Simple item page
dc.citedby16
dc.contributor.authorLatif S.D.en_US
dc.contributor.authorAhmed A.N.en_US
dc.contributor.authorSathiamurthy E.en_US
dc.contributor.authorHuang Y.F.en_US
dc.contributor.authorEl-Shafie A.en_US
dc.contributor.authorid57216081524en_US
dc.contributor.authorid57214837520en_US
dc.contributor.authorid6505807165en_US
dc.contributor.authorid55807263900en_US
dc.contributor.authorid16068189400en_US
dc.date.accessioned2023-05-29T09:05:53Z
dc.date.available2023-05-29T09:05:53Z
dc.date.issued2021
dc.descriptionalgorithm; artificial neural network; input-output analysis; memory; prediction; resource management; support vector machine; water management; water resource; Malaysia; West Malaysia; Durio zibethinusen_US
dc.description.abstractForecasting of reservoir inflow is one of the most vital concerns when it comes to managing water resources at reservoirs to mitigate natural hazards such as flooding. Machine learning (ML) models have become widely prevalent in capturing the complexity of reservoir inflow time-series data. However, the model structure's selection required several trails-and-error processes to identify the optimal architecture to capture the necessary information of various patterns of input�output mapping. In this study, the effectiveness of a deep learning (DL) approach in capturing various input�output patterns is examined and applied to reservoir inflow forecasting. The proposed DL approach has a distinct benefit over classical ML models as all the hidden layers are stacked afterward to train on a diverging set of topologies derived from the previous layer's output. Given the nonlinearity of day-to-day data about reservoir inflow, a deep learning algorithm centered on the long short-term memory (LSTM) and two standard machine learning algorithms, namely support vector machine (SVM) and artificial neural network (ANN), were deployed in this study for forecasting reservoir inflow on a daily basis. The gathered data pertained to historical daily inflow from 01/01/2018 to 31/12/2019. The area of study was Durian Tunggal Reservoir, Melaka, Peninsular Malaysia. The choice of the input set was made on the basis of the autocorrelation function. The formulated model was assessed on the basis of statistical indices, such as mean absolute error (MAE), root mean square error (RMSE), and the coefficient of determination (R2). The outcomes indicate that the LSTM model performed much better than SVM and ANN. Based on the comparison, LSTM outperformed other models with MAE = 0.088, RMSE = 0.27, and R2 = 0.91. This research demonstrates that the deep learning technique is an appropriate method for estimating the daily inflow of the Durian Tunggal Reservoir, unlike the standard machine learning models. � 2021, The Author(s), under exclusive licence to Springer Nature B.V.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.1007/s11069-021-04839-x
dc.identifier.epage369
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85108002163
dc.identifier.spage351
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85108002163&doi=10.1007%2fs11069-021-04839-x&partnerID=40&md5=d81396eb9e4abe97eb436d2374ba4fc0
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/25982
dc.identifier.volume109
dc.publisherSpringer Science and Business Media B.V.en_US
dc.sourceScopus
dc.sourcetitleNatural Hazards
dc.titleEvaluation of deep learning algorithm for inflow forecasting: a case study of Durian Tunggal Reservoir, Peninsular Malaysiaen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS