A Decomposition-Ensemble Learning Model Based on LSTM Neural Network for Daily Reservoir Inflow Forecasting
- 143 Downloads
Reservoir inflow forecasting is one of the most important issues in delicacy water resource management at reservoirs. Considering the non-linearity and of daily reservoir inflow data, a decomposition-ensemble learning model based on the long short-term memory neural network (DEL-LSTM) is developed in this paper for daily reservoir inflow forecasting. DEL-LSTM employs the logarithmic transformation based preprocessing method to cope with the non-stationary of the inflow data. Then, the ensemble empirical mode decomposition and Fourier spectrum methods are used to decompose the inflow data into the trend term, period term, and random term. For each decomposed term, a regression model based on the LSTM neural network is built to obtain the corresponding prediction result. Finally, the prediction results of the three items are integrated to get the final prediction result. Case studies on the Ankang reservoir in China have been conducted by using data from 1/1/1943 to 12/31/1971. Experimental results illustrated the superiority of the decomposition-ensemble framework and the LSTM neural network in forecasting daily reservoir inflow with big fluctuations. Comparing with some representative models, the proposed DEL-LSTM performs better in prediction accuracy, the average absolute percentage error is reduced to 13.11%, and the normalized mean square error is reduced by 4%, the coefficient of determination was increased by 5%.
KeywordsReservoir inflow forecasting LSTM Decomposition-ensemble learning
This work was supported by the National Natural Science Foundation of China under Grant No. 61303119, the Science Basic Research Plan in Shanxi Province of China under Grant No. 2018JM6009, the Fund Program for the Scientific Activities of Selected Returned Overseas Professionals in Shanxi Province under Grant No. 2017021, and the Fundamental Research Funds for the Central Universities under Grant No. JB140304.
Compliance with Ethical Standards
Conflict of interests
- Abdel-Nasser M, Mahmoud K (2017) Accurate photovoltaic power forecasting models using deep lstm-rnn. Neural Computing and Applications pp 1–14Google Scholar
- Hj Bao, Ll Wang, Li Zj, Ln Zhao, Gp Zhang (2010) Hydrological daily rainfall-runoff simulation with btopmc model and comparison with xin’anjiang model. Water Sci Eng 3(2):121–131Google Scholar
- Box GE, Jenkins GM, Reinsel GC, Ljung GM (2015) Time series analysis: forecasting and control. Wiley, New YorkGoogle Scholar
- Gensler A, Henze J, Sick B, Raabe N (2016) Deep learning for solar power forecasting<a̱an approach using autoencoder and lstm neural networks. In: 2016 IEEE international conference on systems, man, and cybernetics (SMC), pp 002,858–002,865Google Scholar
- Hadi SJ, Tombul M (2018) Forecasting daily streamflow for basins with different physical characteristics through data-driven methods. Water Resources 433 Management pp 1–18Google Scholar
- Rao AR, Hamed KH, Chen HL (2012) Nonstationarities in hydrologic and environmental time series, vol 45. Springer Science & Business MediaGoogle Scholar
- Xingjian S, Chen Z, Wang H, Yeung DY, Wong WK, Wc Woo (2015) Convolutional lstm network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems, pp 802–810Google Scholar