Downstream Water Level Prediction of Reservoir based on Convolutional Neural Network and Long Short-Term Memory Network
Publication: Journal of Water Resources Planning and Management
Volume 147, Issue 9
Abstract
Accurate calculation of power generation output is crucial to the operation and management of reservoir. The calculation of power generation output is related to the downstream water level, which usually is obtained by interpolation of discharge flow. However, the interpolation method has a large error and adversely affects the output calculation, especially for medium and low water head reservoirs. This study explored the relevant factors of the downstream water level and accurately predicted it from historical operational data. The maximal information coefficient and feature combination were used to select feature inputs, and a deep neural network was designed based on a convolutional neural network and a long short-term memory network to predict the downstream water level of a reservoir. To verify the performance of designed model, it was compared with the interpolation method and 4 state-of-the-art prediction methods using 12 validation sets of Gezhouba Reservoir. The experimental results showed that downstream water level obtained by the designed model was closer to the actual water level than was the interpolated water level. Compared with four state-of-the-art prediction methods, the designed method also was very competitive. Finally, the influence of CNNLSTM on power generation output is compared with traditional interpolation method. The comparison results showed that the convolutional neural network–long short-term memory network method reduced the influence of the interpolation method by 92.74% on average.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request, including the code and model for the downstream water level prediction in the study, and the historical downstream water level data of Gezhouba in 2017.
Acknowledgments
This work is supported by the National Natural Science Foundation of China (Nos. 51979113, U1865202, 51709119, and 51809098) and the National Public Research Institutes for Basic R & D Operating Expenses Special Project (CKSF2017061/SZ) Special thanks are given to the anonymous reviewers and editors for their constructive comments.
References
Aboutalebi, M., O. Bozorg Haddad, and H. A. Loaiciga. 2015. “Optimal monthly reservoir operation rules for hydropower generation derived with SVR-NSGAII.” J. Water Res. Plann. Manage. 141 (11): 04015029. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000553.
Ajmera, T. K., and M. K. Goyal. 2012. “Development of stage–discharge rating curve using model tree and neural networks: An application to Peachtree Creek in Atlanta.” Expert Syst. Appl. 39 (5): 5702–5710. https://doi.org/10.1016/j.eswa.2011.11.101.
Chang, F.-J., and Y.-T. Chang. 2006. “Adaptive neuro-fuzzy inference system for prediction of water level in reservoir.” Adv. Water Resour. 29 (1): 1–10. https://doi.org/10.1016/j.advwatres.2005.04.015.
Cheng, C., H. Wu, X. Wu, J. Shen, and J. Wang. 2017. “Power generation scheduling for integrated large and small hydropower plant systems in Southwest China.” J. Water Res. Plann. Manage. 143 (8): 04017027. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000771.
Chua, A. S., N. Benedek, L. Chen, M. W. Finnis, and A. P. Sutton. 2010. “Erratum: A genetic algorithm for predicting the structures of interfaces in multicomponent systems.” Nat. Mater. 9 (461): 418–422. https://doi.org/10.1038/nmat2739.
Date, A., A. Date, and A. Akbarzadeh. 2013. “Investigating the potential for using a simple water reaction turbine for power production from low head hydro resources.” Energy Convers. Manage. 66 (Feb): 257–270. https://doi.org/10.1016/j.enconman.2012.09.032.
Ding, Y., R. Deng, X. Xie, X. Xu, Y. Zhao, X. Chen, and A. Krylov. 2018. “No-reference stereoscopic image quality assessment using convolutional neural network for adaptive feature extraction.” IEEE Access 6 (Jun): 37595–37603. https://doi.org/10.1109/ACCESS.2018.2851255.
Gers, F. A., J. Schmidhuber, and F. Cummins. 2000. “Learning to forget: Continual prediction with LSTM.” Neural Comput. 12 (10): 2451–2471. https://doi.org/10.1162/089976600300015015.
Ghorbani, M. A., R. C. Deo, V. Karimi, Z. M. Yaseen, and O. Terzi. 2018. “Implementation of a hybrid MLP-FFA model for water level prediction of Lake Egirdir, Turkey.” Stochastic Environ. Res. Risk Assess. 32 (6): 1683–1697. https://doi.org/10.1007/s00477-017-1474-0.
Kingma, D. P., and J. Ba. 2014. Adam: A method for stochastic optimization. Ithaca, NY: Cornell Univ.
Klein, S., J. P. W. Pluim, M. Staring, and M. A. Viergever. 2009. “Adaptive stochastic gradient descent optimisation for image registration.” Int. J. Comput. Vision 81 (3): 227–239. https://doi.org/10.1007/s11263-008-0168-y.
Le Callet, P., C. Viard-Gaudin, and D. Barba. 2006. “A convolutional neural network approach for objective video quality assessment.” IEEE Trans. Neural Networks 17 (5): 1316–1327. https://doi.org/10.1109/TNN.2006.879766.
LeCun, Y., Y. Bengio, and G. Hinton. 2015. “Deep learning.” Nature 521 (7553): 436–444. https://doi.org/10.1038/nature14539.
Li, D., X. Wang, and D. K. Dey. 2019. “Power link functions in an ordinal regression model with Gaussian process priors.” Environmetrics 30 (6): e2564. https://doi.org/10.1002/env.2564.
Liu, Y., H. Qin, L. Mo, Y. Wang, D. Chen, S. Pang, and X. Yin. 2019. “Hierarchical flood operation rules optimization using multi-objective cultured evolutionary algorithm based on decomposition.” Water Resour. Manage. 33 (1): 337–354. https://doi.org/10.1007/s11269-018-2105-3.
Liu, Y., L. Ye, H. Qin, X. Hong, J. Ye, and X. Yin. 2018. “Monthly streamflow forecasting based on hidden Markov model and Gaussian Mixture Regression.” J. Hydrol. 561 (Jun): 146–159. https://doi.org/10.1016/j.jhydrol.2018.03.057.
Mirzavand, M., and R. Ghazavi. 2015. “A stochastic modelling technique for groundwater level forecasting in an arid environment using time series methods.” Water Resour. Manage. 29 (4): 1315–1328. https://doi.org/10.1007/s11269-014-0875-9.
Morshed, J., and J. J. Kaluarachchi. 1998. “Application of artificial neural network and genetic algorithm in flow and transport simulations.” Adv. Water Resour. 22 (2): 145–158. https://doi.org/10.1016/S0309-1708(98)00002-5.
Mukherjee, A., and P. Ramachandran. 2018. “Prediction of GWL with the help of GRACE TWS for unevenly spaced time series data in India: Analysis of comparative performances of SVR, ANN and LRM.” J. Hydrol. 558 (Mar): 647–658. https://doi.org/10.1016/j.jhydrol.2018.02.005.
Peng, T., J. Zhou, C. Zhang, and Y. Zheng. 2017. “Multi-step ahead wind speed forecasting using a hybrid model based on two-stage decomposition technique and AdaBoost-extreme learning machine.” Energy Convers. Manage. 153 (Dec): 589–602. https://doi.org/10.1016/j.enconman.2017.10.021.
Phat, V. N., and H. Trinh. 2010. “Exponential stabilization of neural networks with various activation functions and mixed time-varying delays.” IEEE Trans. Neural Networks 21 (7): 1180–1184. https://doi.org/10.1109/TNN.2010.2049118.
Reich, B. J., M. Fuentes, and D. B. Dunson. 2011. “Bayesian spatial quantile regression.” J. Am. Stat. Assoc. 106 (493): 6–20. https://doi.org/10.1198/jasa.2010.ap09237.
Schmidhuber, J. 2015. “Deep learning in neural networks: An overview.” Neural Networks 61 (Jan): 85–117. https://doi.org/10.1016/j.neunet.2014.09.003.
Shafaei, M., and O. Kisi. 2016. “Lake level forecasting using wavelet-SVR, wavelet-ANFIS and wavelet-ARMA conjunction models.” Water Resour. Manage. 30 (1): 79–97. https://doi.org/10.1007/s11269-015-1147-z.
Shang, Y., Y. Xu, L. Shang, Q. Fan, Y. Wang, and Z. Liu. 2019. “A method of direct, real-time forecasting of downstream water levels via hydropower station reregulation: A case study from Gezhouba Hydropower Plant, China.” J. Hydrol. 573 (Jun): 895–907. https://doi.org/10.1016/j.jhydrol.2019.04.017.
Shao, Q., D. Dutta, F. Karim, and C. Petheram. 2018. “A method for extending stage-discharge relationships using a hydrodynamic model and quantifying the associated uncertainty.” J. Hydrol. 556 (Jan): 154–172. https://doi.org/10.1016/j.jhydrol.2017.11.012.
Shen, Y., and J. Wang. 2008. “An improved algebraic criterion for global exponential stability of recurrent neural networks with time-varying delays.” IEEE Trans. Neural Networks 19 (3): 528–531. https://doi.org/10.1109/TNN.2007.911751.
Shimizu, Y., S. Giri, S. Yamaguchi, and J. Nelson. 2009. “Numerical simulation of dune–flat bed transition and stage-discharge relationship with hysteresis effect.” Water Resour. Res. 45 (4): W04429. https://doi.org/10.1029/2008WR006830.
Shiri, J., S. S. Band, O. Kisi, S. Karimi, S. M. Bateni, S. H. Hosseini, and A. Hashemi. 2016. “Prediction of water-level in the Urmia Lake using the extreme learning machine approach.” Water Resour. Manage. 30 (14): 5217–5229. https://doi.org/10.1007/s11269-016-1480-x.
Wang, J., L. Zhang, Q. Guo, and Z. Yi. 2018. “Recurrent neural networks with auxiliary memory units.” IEEE Trans. Neural Networks Learn. Syst. 29 (5): 1652–1661. https://doi.org/10.1109/TNNLS.2017.2677968.
Wang, X., J. Zhang, X. Yu, J. Lv, and X. Zhang. 2019. “Multi-objective intelligent start-up strategy for small hydropower plants based on adaptive variable parameters of water head.” J. Renewable Sustainable Energy 11 (1): 14703. https://doi.org/10.1063/1.5043368.
Zhang, M., W. Li, and Q. Du. 2018. “Diverse region-based CNN for hyperspectral image classification.” IEEE Trans. Image Process. 27 (6): 2623–2634. https://doi.org/10.1109/TIP.2018.2809606.
Zhang, Z., H. Qin, Y. Liu, Y. Wang, L. Yao, Q. Li, J. Li, and S. Pei. 2019a. “Long short-term memory network based on neighborhood gates for processing complex causality in wind speed prediction.” Energy Convers. Manage. 192 (Jul): 37–51. https://doi.org/10.1016/j.enconman.2019.04.006.
Zhang, Z., H. Qin, Y. Liu, L. Yao, X. Yu, J. Lu, Z. Jiang, and Z. Feng. 2019b. “Wind speed forecasting based on quantile regression minimal gated memory network and kernel density estimation.” Energy Convers. Manage. 196 (Sep): 1395–1409. https://doi.org/10.1016/j.enconman.2019.06.024.
Zhang, Z., L. Ye, H. Qin, Y. Liu, C. Wang, X. Yu, X. Yin, and J. Li. 2019c. “Wind speed prediction method using shared weight long short-term memory network and Gaussian process regression.” Appl. Energy 247 (Aug): 270–284. https://doi.org/10.1016/j.apenergy.2019.04.047.
Zhao, J., J. M. Zurada, J. Yang, and W. Wu. 2018. “The convergence analysis of SpikeProp algorithm with smoothing L1/2 regularization.” Neural Networks 103 (Jul): 19–28. https://doi.org/10.1016/j.neunet.2018.03.007.
Information & Authors
Information
Published In
Journal of Water Resources Planning and Management
Volume 147 • Issue 9 • September 2021
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Aug 13, 2020
Accepted: Mar 31, 2021
Published online: Jul 15, 2021
Published in print: Sep 1, 2021
Discussion open until: Dec 15, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.