A Monthly Runoff Forecast Model Combining Time Series Decomposition and CNN-LSTM

LEI Qing-wen; GAO Pei-qiang; LI Jian-lin

doi:10.11988/ckyyb.20220004

PDF(1406 KB)

Journal of Changjiang River Scientific Research Institute ›› 2023, Vol. 40 ›› Issue (6) : 49-54. DOI: 10.11988/ckyyb.20220004

Water Resources

A Monthly Runoff Forecast Model Combining Time Series Decomposition and CNN-LSTM

LEI Qing-wen^1,2, GAO Pei-qiang^3,4, LI Jian-lin⁵

Author information +

History +

Abstract

To address the limitations of conventional models in fully capturing the complex nonlinear characteristics of runoff sequences, a monthly runoff prediction model is proposed by integrating the Seasonal-Trend decomposition procedure based on Loess (STL) with convolutional neural networks (CNN) and long short-term memory neural networks (LSTM). In this model, the runoff sequence is first decomposed into trend components, seasonal components, and residual terms of random fluctuations using STL. The decomposed component sequences are then input to the CNN for convolutional operations and subsampling, and the CNN outputs feature sequences that capture temporal relationships. These sequences are further processed by LSTM and the predicted runoff values are obtained through fully connected layers. With the monthly runoff data from the Taolai River gauge station in the Heihe River Basin as an example, the prediction performance of three models, LSTM, STL-CNN, and STL-CNN-LSTM, is compared and analyzed. The validation results demonstrate that the model integrating STL and CNN-LSTM achieves the lowest prediction error and the highest accuracy. Compared to conventional models that directly analyze the original runoff sequence, this model significantly improves the ability to predict monthly runoff.

Key words

runoff forecast / Seasonal-Trend decomposition procedure based on Loess(STL) / non-linear characteristics / convolutional neural networks(CNN) / CNN-LSTM

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LEI Qing-wen, GAO Pei-qiang, LI Jian-lin. A Monthly Runoff Forecast Model Combining Time Series Decomposition and CNN-LSTM[J]. Journal of Changjiang River Scientific Research Institute. 2023, 40(6): 49-54 https://doi.org/10.11988/ckyyb.20220004

References

[1] 周育琳, 穆振侠, 彭亮, 等. 基于互信息与神经网络的天山西部山区融雪径流中长期水文预报[J]. raybet体育在线院报, 2018, 35(8): 17-21.
[2] 周建中, 彭甜. 长江上游径流混沌动力特性及其集成预测研究[J]. raybet体育在线院报, 2018, 35(10): 1-9.
[3] 王树威, 李建林, 崔延华, 等. 混沌理论与BPNN耦合的径流中长期预测模型[J]. 水资源与水工程学报, 2021, 32(3): 73-79.
[4] 雷晓辉, 王浩, 廖卫红, 等. 变化环境下气象水文预报研究进展[J]. 水利学报, 2018, 49(1): 9-18.
[5] 李继清, 王爽, 吴月秋, 等. 径流预报的极点对称模态分解-Elman网络模型[J]. 水力发电学报, 2021, 40(7): 13-22.
[6] 梁浩,黄生志,孟二浩,等.基于多种混合模型的径流预测研究[J].水利学报,2020,51(1):112-125.
[7] MENG E H, HUANG S Z, HUANG Q, et al. A Robust Method for Nonstationary Streamflow Prediction based on Improved EMD-SVM Model[J]. Journal of Hydrology, 2019, 568: 462-478.
[8] KISI O.Acombined Generalized Regression Neural Network Wavelet Model for Monthly Streamflow Prediction[J]. Journal of Civil Engineering, 2011, 15(8): 1469-1479.
[9] WEN X H, FENG Q,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.
[10]FENG Z K, NIU W J, TANG Z Y, et al. Monthly Runoff Time Series Prediction by Variational Mode Decomposition and Support Vector Machine based on Quantum-Behaved Particle Swarm Optimization[J]. Journal of Hydrology, 2020, 583: 124627.
[11]李继清, 王爽, 段志鹏, 等. 基于ESMD-BP神经网络组合模型的中长期径流预报[J]. 应用基础与工程科学学报, 2020, 28(4): 817-832.
[12]徐冬梅,庄文涛,王文川.基于CEEMDAN-WD-PSO-LSSVM模型的月径流预测研究[J]. 中国农村水利水电, 2021(8): 54-58,66.
[13]TAN Q F, LEI X H, WANG X, et al. An Adaptive Middle and Long-Term Runoff Forecast Model using EEMD-ANN Hybrid Approach[J]. Journal of Hydrology, 2018, 567: 767-780.
[14]包丽娜, 唐德善, 胡小波, 等. 基于小波分解及Arima误差修正的径流预测模型及应用[J]. raybet体育在线院报, 2018, 35(12): 18-21,33.
[15]CLEVELAND R B,CLEVELAND W S,MCRAE J E,et al.STL: A Seasonal-Trend Decomposition Procedure based on Loess[J]. Journal of Official Statistics,1990, 6(1): 3-33.
[16]朱新丽, 李彦彬, 李红星, 等. 基于小波多孔算法的黑河径流变异规律分析[J]. 水利水电技术(中英文), 2021, 52(10): 46- 58.
[17]王丽丽, 李新, 冉有华, 等. 基于奇异谱分析-灰狼优化-支持向量回归混合模型的黑河正义峡月径流预测[J]. 遥感技术与应用, 2020, 35(2): 355-364.
[18]雷庆文, 闫磊, 鲁东阳, 等. 基于粒子群算法的P-III型分布极大似然估计研究[J]. 中国农村水利水电, 2022(7): 128-131,139.
[19]GB/T 22482—2008,水文情报预报规范[S]. 北京: 中国标准出版社, 2009.
[20]练继建, 孙萧仲, 马超, 等. 基于EEMD-AR模型的丹江口水库年径流随机模拟与预报[J]. 水利水电科技进展, 2017, 37(5): 16-21.