Journal
MATHEMATICAL BIOSCIENCES AND ENGINEERING
Volume 19, Issue 2, Pages 1633-1648Publisher
AMER INST MATHEMATICAL SCIENCES-AIMS
DOI: 10.3934/mbe.2022076
Keywords
runoff forecasting; variational mode decomposition; convolution neural networks; long short-term memory
Categories
Funding
- Natural Science Basic Research Program of Shaanxi Province [2019JLZ-15, 2019JLZ-16, 2017JQ5076]
- Special Scientific Research Program of Shaanxi Provincial Education Department [17JK0558]
- Science and Technology Program of Shaanxi Province [2018slkj-4, 2019slkj-13, 2020slkj-16]
Ask authors/readers for more resources
This paper proposes a novel hybrid runoff forecasting model based on variational mode decomposition, convolutional neural networks, and long short-term memory. By considering potential correlation information, the model improves the runoff forecasting performance. Experimental results demonstrate the superiority and stability of the model compared to baseline models.
Accurate runoff forecasting plays a vital role in water resource management. Therefore, various forecasting models have been proposed in the literature. Among them, the decomposition-based models have proved their superiority in runoff series forecasting. However, most of the models simulate each decomposition sub-signals separately without considering the potential correlation information. A neoteric hybrid runoff forecasting model based on variational mode decomposition (VIVID), convolution neural networks (CNN), and long short-term memory (LSTM) called VIVID-CNN-LSTM, is proposed to improve the runoff forecasting performance further. The two-dimensional matrix containing both the time delay and correlation information among sub-signals decomposing by VIVID is firstly applied to the CNN. The feature of the input matrix is then extracted by CNN and delivered to LSTM with more potential information. The experiment performed on monthly runoff data investigated from Huaxian and Xianyang hydrological stations at Wei River, China, demonstrates the VIVID-superiority of CNN-LSTM to the baseline models, and robustness and stability of the forecasting of the VIVID-CNN-LSTM for different leading times.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available