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

Latif, Sarmad Dashti and Ahmed, Ali Najah and Sathiamurthy, Edlic and Huang, Yuk Feng and El-Shafie, Ahmed (2021) Evaluation of deep learning algorithm for inflow forecasting: A case study of Durian Tunggal Reservoir, Peninsular Malaysia. Natural Hazards, 109 (1). pp. 351-369. ISSN 0921-030X, DOI https://doi.org/10.1007/s11069-021-04839-x.

Full text not available from this repository.


Forecasting 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 (R-2). 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 R-2 = 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.

Item Type: Article
Funders: Ministry of Education (MOE) through Fundamental Research Grant Scheme (FRGS) [FRGS/1/2019/TK01/UNITEN/02/3]
Uncontrolled Keywords: Water resources management; Inflow prediction model; Long short-term memory (LSTM); Artificial neural network (ANN); Support vector machine (SVM); Malaysia
Subjects: Q Science > QE Geology
Divisions: Faculty of Engineering
Depositing User: Ms Zaharah Ramly
Date Deposited: 07 Apr 2022 06:50
Last Modified: 12 Apr 2022 06:18
URI: http://eprints.um.edu.my/id/eprint/27887

Actions (login required)

View Item View Item