SSA-LSSVM在中长期径流预测中的应用研究
Application of SSA-LSSVM in Mid-Long Term Runoff Prediction
DOI: 10.12677/JWRR.2016.55049, PDF,  被引量    国家自然科学基金支持
作者: 巴欢欢, 郭生练, 钟逸轩, 刘章君：武汉大学水资源与水电工程科学国家重点实验室，湖北 武汉；水资源安全保障湖北省协同创新中心，湖北 武汉
关键词: 中长期径流预测；奇异谱分析；季节性一阶自回归；支持向量机；最小二乘支持向量机；水布垭水库；Mid-Long Term Runoff Prediction； Singular Spectrum Analysis； SAR Model； SVM； LSSVM； Shuibuya Reservoir
摘要: 为提高中长期径流预测精度，利用奇异谱分析(SSA)对输入资料进行数据预处理，消除噪声，得到重建序列。以水布垭水库1951~2009年的入库月径流资料为依据，选用季节性一阶自回归模型、支持向量机模型和最小二乘支持向量机模型作为径流预测模型，对原始序列和重建序列进行模拟预测。结果表明，基于奇异谱分析的最小二乘支持向量机的模拟预测精度最高，率定期和检验期的模型效率系数分别高达89%和84%。说明采用SSA对资料进行预处理可以显著提高中长期径流预报的精度。
Abstract: To improve the accuracy of runoff prediction, Singular Spectrum Analysis (SSA) is applied to preprocess the original flow series and a new reconstructed series is obtained. The monthly inflow data of the Shui-buya Reservoir from 1951 to 2009 were selected as a case study. Seasonal Autoregressive (SAR) model, support vector machine (SVM) and least square support vector machine (LSSVM) are used to simulate and predict the original and reconstructed data series. The results show that SSA-LSSVM performs the best among these models, in which the model efficiency coefficients reach 89% and 84% during the verification and testing periods, respectively. It is shown that the accuracy of mid-long term runoff prediction can be significantly improved by using SSA.
文章引用：巴欢欢, 郭生练, 钟逸轩, 刘章君. SSA-LSSVM在中长期径流预测中的应用研究[J]. 水资源研究, 2016, 5(5): 423-433. https://dx.doi.org/10.12677/JWRR.2016.55049

参考文献

[1] 刘冀, 王本德, 袁晶瑄, 等. 基于相空间重构的支持向量机方法在径流中长期预报中应用[J]. 大连理工大学学报, 2008, 48(4): 591-595. LIU Ji, WANG Bende, YUAN Jingxuan, et al. Application of support vector machine based on phase-space reconstruction to medium-term and long-term runoff forecast. Journal of Dalian University of Technology, 2008, 48(4): 591-595. (in Chinese)
[2] 张卫国, 钟平安, 张玉兰, 等. 季节性支持向量机中长期径流预报模型[J]. 水力发电, 2014, 40(4): 17-21. ZHANG Weiguo, ZHONG Pingan, ZHANG Yulan, et al. A seasonal support vector machine mid-long term runoff forecast model. Water Power, 2014, 40(4): 17-21. (in Chinese)
[3] 崔东文. 多隐层BP神经网络模型在径流预测中的应用[J]. 水文, 2013, 33(1): 68-73. CUI Dongwen. Application of hidden multilayer BP neural network modelin runoffprediction. Journal of China Hydrology, 2013, 33(1): 68-73. (in Chinese)
[4] 周轶成, 焦国军. 基于最小二乘支持向量机的马营河中长期径流预测研究[J]. 甘肃水利水电技术, 2014, 50(12): 1-3. ZHOU Yicheng, JIAO Guojun. Study on Mayinghe medium and long term runoff forecastingbased on least square support vector machine. Gansu Water Resources and Hydropower Technology, 2014, 50(12): 1-3. (in Chinese)
[5] 李佳, 王黎, 马光文, 等. LS-SVM在径流预测中的应用[J]. 中国农村水利水电, 2008(5): 8-10. LI Jia, WANG Li, MA Guangwen, et al. Application of least squares support vector machines in runoff forecast. China Rural Water and Hydropower, 2008(5): 8-10. (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. http://dx.doi.org/10.1016/j.jhydrol.2011.01.017[CrossRef] 
[7] 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(9): 4-7. WANG Yun, GUO Shenglian and LI Xiang. Application of singular spectrum analysis method in mid-long term runoff predic-tion. Yangtze River, 2011, 42(9): 4-7. (in Chinese)
[8] WANG, Y., GUO, S., CHEN, H., et al. Comparative study of monthly inflow prediction methods for the Three Gorges Reservoir. Stochastic Environmental Research & Risk Assessment, 2014, 28(3): 555-570. http://dx.doi.org/10.1007/s00477-013-0772-4 [Google Scholar] [CrossRef] 
[9] CHAU, K W, WU, C L. A hybrid model coupled with singular spec-trum analysis for daily rainfall prediction. Journal of Hydroinformatics, 2010, 12(4): 458-473. http://dx.doi.org/10.2166/hydro.2010.032 [Google Scholar] [CrossRef] 
[10] 丁裕国, 江志红. 气象时间序列信号处理[M]. 北京: 气象出版社, 1998. DING Yuguo, JIANG Zhihong. Signal processing on meteorological time series. Beijing: China Meteorological Press, 1998. (in Chinese)
[11] 吴洪宝, 吴蕾. 气候变率诊断和预测方法[M]. 北京: 气象出版社, 2005. WU Hongbao, WU Lei. Climate change rate of diagnosis and prediction method. Beijing: China Meteorological Press, 2005. (in Chinese)
[12] SUYKENS, J. A. K., VANDEWALLE, J. Least squares support vector machine classifiers. Neural Processing Letters, 1999, 9(3): 293-300. http://dx.doi.org/10.1023/A:1018628609742 [Google Scholar] [CrossRef] 
[13] 邵骏, 袁鹏, 张文江, 等. 基于贝叶斯框架的LS-SVM中长期径流预报模型研究[J]. 水力发电学报, 2010, 29(5): 178-182. SHAO Jun, YUAN Peng, ZHANG Wenjiang, et al. Study of mid-long term runoff forecast based on LS-SVMin Bayesian evi-dence framework. Journal of Hydroelectric Engineering, 2010, 29(5): 178-182. (in Chinese)
[14] 林剑艺, 程春田. 支持向量机在中长期径流预报中的应用[J]. 水利学报, 2006, 37(6): 681-686. LIN Jianyi, CHENG Chuntian. Application of support vector machine method to long-term runoff forecast. Journal of Hydraulic Engineering, 2006, 37(6): 681-686. (in Chinese)
[15] 孙传文, 钟平安, 万新宇, 等. 考虑季节因子的支持向量机径流预测模型[J]. 中国农村水利水电, 2014(4): 101-104. SUN Chuanwen, ZHONG Pingan, WAN Xinyu, et al. Seasonal support vector machine model of the runoff forecast.China Rural Water and Hydropower, 2014(4): 101-104. (in Chinese)