Comparative Analysis of Recurrent Neural Network Architectures for Reservoir Inflow Forecasting

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.

[1]  Saeed Samadianfard,et al.  Performance evaluation of ANNs and an M5 model tree in Sattarkhan Reservoir inflow prediction , 2017 .

[2]  M. Pal,et al.  M5 model tree application in daily river flow forecasting in Sohu Stream, Turkey , 2013, Water Resources.

[3]  T. Sathish,et al.  River Flow Forecasting using Recurrent Neural Networks , 2004 .

[4]  Dennis P. Lettenmaier,et al.  Columbia River Streamflow Forecasting Based on ENSO and PDO Climate Signals , 1999 .

[5]  Yinhai Wang,et al.  Deep Stacked Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction , 2017 .

[6]  K. Brindha,et al.  Spatial interpolation methods and geostatistics for mapping groundwater contamination in a coastal area , 2017, Environmental Science and Pollution Research.

[7]  M. Taghi Sattari,et al.  Flow estimations for the Sohu Stream using artificial neural networks , 2012, Environmental Earth Sciences.

[8]  Eric Huang,et al.  Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control , 2014 .

[9]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[10]  SchmidhuberJürgen,et al.  2005 Special Issue , 2005 .

[11]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[12]  Fredi Tröltzsch,et al.  System Modeling and Optimization , 2011, IFIP Advances in Information and Communication Technology.

[13]  Yen-Ming Chiang,et al.  Identifying the Sensitivity of Ensemble Streamflow Prediction by Artificial Intelligence , 2018, Water.

[14]  Karl Rihaczek,et al.  1. WHAT IS DATA MINING? , 2019, Data Mining for the Social Sciences.

[15]  Jihn-Sung Lai,et al.  A deterministic linearized recurrent neural network for recognizing the transition of rainfall–runoff processes , 2007 .

[16]  M. Firat,et al.  Comparison of Artificial Intelligence Techniques for river flow forecasting , 2008 .

[17]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[18]  Li-Chiu Chang,et al.  Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting , 2020 .

[19]  Michael J. Stewardson,et al.  Comparison of six rainfall-runoff modelling approaches , 1993 .

[20]  Bo Liu,et al.  Projected streamflow in the Huaihe River Basin (2010–2100) using artificial neural network , 2010 .

[21]  Yousry Mahmoud Ghazaw,et al.  Runoff forecasting by artificial neural network and conventional model , 2011 .

[22]  Karsten Schulz,et al.  Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks , 2018, Hydrology and Earth System Sciences.

[23]  Mahesh Pal,et al.  Performance evaluation of artificial neural network approaches in forecasting reservoir inflow , 2012 .

[24]  Wang Dongsheng,et al.  Simulating Reservoir Operation Using a Recurrent Neural Network Algorithm , 2019, Water.

[25]  Li-Chiu Chang,et al.  Reinforced recurrent neural networks for multi-step-ahead flood forecasts , 2013 .

[26]  Karsten Schulz,et al.  Rainfall–runoff modelling using Long Short-Term Memory (LSTM) networks , 2018, Hydrology and Earth System Sciences.

[27]  Chu Zhang,et al.  Data Pre-Analysis and Ensemble of Various Artificial Neural Networks for Monthly Streamflow Forecasting , 2018 .

[28]  Feng Xu,et al.  A Flood Forecasting Model Based on Deep Learning Algorithm via Integrating Stacked Autoencoders with BP Neural Network , 2017, 2017 IEEE Third International Conference on Multimedia Big Data (BigMM).

[29]  Soroosh Sorooshian,et al.  Modeling and simulating of reservoir operation using the artificial neural network, support vector regression, deep learning algorithm , 2018, Journal of Hydrology.

[30]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[31]  Ebrahim Teimoury,et al.  Hub-and-spoke logistics network design for third party logistics service providers , 2016 .

[32]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[33]  Shinjiro Kanae,et al.  Improved Forecasting of Extreme Monthly Reservoir Inflow Using an Analogue-Based Forecasting Method: A Case Study of the Sirikit Dam in Thailand , 2018, Water.

[34]  Shenglian Guo,et al.  Improving the Reliability of Probabilistic Multi-Step-Ahead Flood Forecasting by Fusing Unscented Kalman Filter with Recurrent Neural Network , 2020, Water.