Comparative Analysis of Recurrent Neural Network Architectures for Reservoir Inflow Forecasting

Muslume Sevba Colak,Shahaboddin Shamshirband,Halit Apaydin,Hajar Feizi,Mohammad Taghi Sattari,Kwok-Wing Chau

doi:10.3390/w12051500

Muslume Sevba Colak, Shahaboddin Shamshirband + Show 4 more

Open Access

https://doi.org/10.3390/w12051500

Copy DOI

Abstract

Due to the stochastic nature and complexity of flow, as well as the existence of hydrological uncertainties, predicting streamflow in dam reservoirs, especially in semi-arid and arid areas, is essential for the optimal and timely use of surface water resources. In this research, daily streamflow to the Ermenek hydroelectric dam reservoir located in Turkey is simulated using deep recurrent neural network (RNN) architectures, including bidirectional long short-term memory (Bi-LSTM), gated recurrent unit (GRU), long short-term memory (LSTM), and simple recurrent neural networks (simple RNN). For this purpose, daily observational flow data are used during the period 2012–2018, and all models are coded in Python software programming language. Only delays of streamflow time series are used as the input of models. Then, based on the correlation coefficient (CC), mean absolute error (MAE), root mean square error (RMSE), and Nash–Sutcliffe efficiency coefficient (NS), results of deep-learning architectures are compared with one another and with an artificial neural network (ANN) with two hidden layers. Results indicate that the accuracy of deep-learning RNN methods are better and more accurate than ANN. Among methods used in deep learning, the LSTM method has the best accuracy, namely, the simulated streamflow to the dam reservoir with 90% accuracy in the training stage and 87% accuracy in the testing stage. However, the accuracies of ANN in training and testing stages are 86% and 85%, respectively. Considering that the Ermenek Dam is used for hydroelectric purposes and energy production, modeling inflow in the most realistic way may lead to an increase in energy production and income by optimizing water management. Hence, multi-percentage improvements can be extremely useful. According to results, deep-learning methods of RNNs can be used for estimating streamflow to the Ermenek Dam reservoir due to their accuracy.

Highlights

Large dam structures are built to reserve water for different supply objectives, such as drinking water irrigation, hydroelectric generation, and flood control
The historical observation streamflow data are compared with the computed streamflow from artificial neural networks and recurrent neural network (RNN), such as bidirectional long short-term memory (Bi-long short-term memory (LSTM)), gated recurrent unit (GRU), LSTM, and simple RNN using seven lag days
A novel approach to streamflow simulation based on recurrent neural networks is presented

Summary

Introduction

Large dam structures are built to reserve water for different supply objectives, such as drinking water irrigation, hydroelectric generation, and flood control. Generating clean energy, especially in developing countries, is a major focus of managers of hydroelectric dams. By determining the amount of streamflow to the dam, the annual volume of input water can be calculated and used for optimal water allocation for various sectors of consumption, including drinking, agriculture, hydropower, and so forth. Accurate forecasting of streamflow is always a key problem in hydrology for flood hazard mitigation. This problem is more considerable when flood control or energy production are involved. Artificial neural networks (ANNs) are used widely and accurately to estimate various hydrological parameters; they may not be developed in more than one or two hidden layers [2]. Deep learning is a new approach to ANNs and is a branch of machine learning

Methods

Results

Conclusion