Research on Daily Runoff Simulation Based on VMD-CNN-LSTM
DOI:
https://doi.org/10.54691/rcxam671Keywords:
Variational Mode Decomposition; Convolutional Neural Network; Long Short-Term Memory Network; Daily Runoff Simulation.Abstract
Runoff simulation plays a crucial role in hydrological research and water resource management for scientific planning and flood control strategy formulation. To address runoff data non-stationarity, this study develops a VMD-CNN-LSTM ensemble model integrating Variational Mode Decomposition, Convolutional Neural Network, and Long Short-Term Memory network, aiming to enhance simulation accuracy and model generalization. Validated using 2008-2016 daily runoff data from the Wuding River Basin, the model demonstrates superior performance with training and testing period R2 values of 0.955 and 0.946, and Nash-Sutcliffe efficiency coefficients of 0.945 and 0.938 respectively, outperforming both standalone LSTM and CNN-LSTM models. Notably, the integrated model shows enhanced capability in peak runoff simulation while maintaining stable accuracy, confirming its robust generalization capacity for hydrological applications.
Downloads
References
[1] Ma K, He D, Liu S, et al. Novel time-lag informed deep learning framework for enhanced streamflow prediction and flood early warning in large-scale catchments[J]. Journal of Hydrology, 2024, 631: 130841.
[2] BAO Lina,TANG Deshan,HU Xiaobo 1 ,CHU Shi-ji 1. Runoff Prediction Model Based on Wavelet Decomposition and Arima Error Correction: Research and Application [J]. Journal of Changjiang River Scientific Research Institute,2018,35(12):18-21,33.
[3] Lei Xiaohui,Wang Hao,Liao Weihong. et al. Advances in hydro-meteorological forecast under changing environment [J]. Journal of Hydraulic Engineering,2018.49(1):9-18.
[4] Wen Xiaohu, Feng Qi, Deo R C, et al. Two-phase extreme learning machines integrated with the complete ensemble empirical mode decomposition with adaptive noise algorithm for multi-scale runoff prediction problems[J]. Journal of Hydrology,2019,570: 167-184.
[5] Deng Chao,Chen Chunyu. et al. Catchment runoff simulation by coupling data assimilation andmachine learning methods [J]. Advances in Water Science,2023,34(06):839-849.
[6] Deng H, Chen W, Huang G. Deep insight into daily runoff forecasting based on a CNN-LSTM model[J]. Natural Hazards, 2022, 113(3): 1675-1696.
[7] Yuan R, Cai S, Liao W, et al. Daily runoff forecasting using ensemble empirical mode decomposition and long short-term memory[J]. Frontiers in Earth Science, 2021, 9: 621780.
[8] Yao Z, Wang Z, Wang D, et al. An ensemble CNN-LSTM and GRU adaptive weighting model based improved sparrow search algorithm for predicting runoff using historical meteorological and runoff data as input[J]. Journal of Hydrology, 2023, 625: 129977.
[9] Dragomiretskiy, K., & Zosso, D. (2014). Variational mode decomposition. IEEE Transactions on Signal Processing, 62(3), 531-544.
[10] HUANG NE., LONG SR., WU MLC., et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society. Mathematical, physical and engineering sciences,1998,454(1971):903-995.
[11] LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. Gradient-based learning applied to document recognition. Proceedings of the IEEE,1998, 86(11), 2278-2324.
[12] Hochreiter, S., & Schmidhuber, J. Long short-term memory. Neural computation,1997, 9(8), 1735-1780.
[13] Bharti B, Pandey A, Tripathi S K, et al. Modelling of runoff and sediment yield using ANN, LS-SVR, REPTree and M5 models[J]. Hydrology Research, 2017, 48(6): 1489-1507.
[14] Deng H, Chen W, Huang G. Deep insight into daily runoff forecasting based on a CNN-LSTM model[J]. Natural Hazards, 2022, 113(3): 1675-1696.
[15] Li Wenjia, Wu Lili, Wen Xiaohu, et al. Runoff simulation study based on LSTM-Seq2seq modeloptimized by Attention mechanism [J]. Journal of Glaciology and Geocryology,2023,1-13.
[16] Yang S, Kang T, Bu J, et al. Evaluating the impacts of climate change and vegetation restoration on the hydrological cycle over the Loess Plateau, China[J]. Water, 2019, 11(11): 2241.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Scientific Journal of Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
