基于奇异谱和混沌支持向量机模型预测三峡水库月径流
Monthly Runoff Prediction Based on Singular Spectrum Analysis and Chaotic Support Vector Machines

作者: 汪芸 , 郭生练 , 曹广晶 , 鲍正风 :;

关键词: 月径流预测奇异谱分析季节性一阶自回归小波神经网络混沌支持向量机三峡水库Monthly Runoff Prediction Singular Spectrum Analysis Seasonal Autoregressive Model Wavelet Neural Network Chaotic Support Vector Machines Three Gorges Reservoir

摘要: 径流时间序列在一定程度上可看作是一种被噪声污染的一些准周期信号的组合。为了提高径流预测精度,利用奇异谱分析方法对三峡水库1882~2010的入库径流资料进行预处理,得到重建序列,并分别运用季节性一阶自回归、小波神经网络和混沌支持向量机模型对原始和重建序列进行模拟预测,分析比较三个模型的预测精度。结果表明奇异谱分析法不仅可以浓缩主要信息和减小误差,也能够明显地提高月径流预测精度;基于奇异谱分析方法的混沌支持向量机模型的模拟预测精度最高,检验期模型的确定性系数高达86.9%,年均最大、最小月径流相对误差分别为9%7%

Abstract: The runoff time series is often assumed as a combination of quasi-periodic signals contaminated by noises to some extent. The singular spectrum analysis method is used to preprocess inflow data of the Three Gorges Reservoir from 1882 to 2010 and a new reconstructed sequence is obtained. The seasonal autoregressive model, wavelet neural network model and chaotic support vector machines are applied to simulate and predict the original and reconstructed inflow data series. The results show that the singular spectrum analysis method for data preprocessing not only can concentrate the main information and reduce errors, but also significantly improve the accuracy of the monthly runoff prediction. The chaotic support vector machines coupled with singular spectrum analysis performs best among these models, which determination coefficient (DC) attains to 86.9%, relative errors of annual average maximum monthly inflow (REmax) and minimum monthly inflow (REmin) are equal to 9% and –7% during the testing period, respectively.

文章引用: 汪芸 , 郭生练 , 曹广晶 , 鲍正风 (2012) 基于奇异谱和混沌支持向量机模型预测三峡水库月径流。 水资源研究, 1, 72-78. doi: 10.12677/JWRR.2012.13011

参考文献

[1] 李超群, 郭生练, 张俊, 等. 改进的NLPM-ANN模型及其在径流预报中的应用研究[J]. 武汉大学工学学报, 2009, 42(1): 1-5. LI Chaoqun, GUO Shenglian, ZHANG Jun, et al. A modified NLPM-ANN model and its application to flood forecasting. Engineering Journal of Wuhan University, 2009, 42(1): 1-5. (in Chinese)

[2] CANNAS, B., FANNI, A., SEE, L., et al. Data preprocessing for river flow forecasting using neural networks: Wavelet trans- forms and data partitioning. Physics and Chemistry of the Earth, 2006, 31(18): 1164-1171.

[3] WANG, W. S., JIN, J. L. and LI, Y. Q. Prediction of inflow at Three Gorges Dam in Yangtze River with wavelet network model. Water Resources Management, 2009, 23: 2791-2803.

[4] 三峡梯调通信中心, 中国科学院兰州寒区旱区环境与工程研究所. 三峡梯级水库调度中长期水文气象预报业务系统技术报告[R], 2005. TGR, CAS. The middle and long-term hydrometeorological forecasting system for the Three Gorges cascade reservoirs, 2005. (in Chinese)

[5] 于国荣, 夏自强. 混沌时间序列支持向量机模型及其在径流预测中应用[J]. 水科学进展, 2008, 19(1): 116-121. YU Guorong, XIA Ziqiang. Prediction model of chaotic time series based on support vector machine and its application to runoff. Advance in Water Resource, 2008, 19(1): 116-121. (in Chinese)

[6] WU, C. L., CHAU, K. W. Rainfall-runoff modeling using artificial neural network coupled with singular spectrum analysis. Journal of Hydrology, 2011, 399: 394-409.

[7] GOLYANDINA, N., NEKRUTKIN, V. and ZHIGLJAVSKY, A. Analysis of time series structure: SSA and the related techniques. Boca Raton: Chapman & Hall/CRC, 2001.

[8] 汪芸, 郭生练, 李响. 奇异谱分析在中长期径流预测中的应用研究[J]. 人民长江, 2011, 42(5): 4-7. WANG Yun, GUO Shenglian and LI Xiang. Application of singular spectrum analysis method in mid-long term runoff prediction. Yangtze River, 2011, 42(5): 4-7. (in Chinese)

[9] CHAU, K. W., WU, C. L. Hydrological predictions using data- driven models coupled with data preprocessing techniques. Saar- brücken: LAP Lambert Academic Publishing, 2010.

分享
Top