针对长江上游干流主要站点月径流时间序列强非线性和非平稳特征,引入混沌理论和AdaBoost.RT集成极限学习机方法对其月径流时间序列进行分析和预测。首先,以流域径流非线性动力系统混沌特征参数辨识为切入点,研究并发现了流域内在特性作用下月径流时间序列动力响应的混沌现象,推求了月径流时间序列相空间重构的延迟时间和最佳嵌入维数,在此基础上,以重构相空间时间序列作为输入变量,引入基于自适应动态阈值的改进AdaBoost.RT算法改进极限学习机模型的学习性能,得到最佳的混沌集成学习月径流时间序列预测模型。实例研究结果表明,所提方法和模型能够显著提高单一极限学习机模型的泛化性和稳定性,从而获得更优越的预报性能。
Abstract
In view of the strong nonlinearity and non-stationarity of monthly runoff in the upper reaches of Yangtze River, a hybrid model integrating the chaos theory and an ensemble AdaBoost.RT extreme learning machine is proposed for monthly runoff analysis and prediction. Firstly, the chaotic characteristics of monthly runoff in watershed were researched and revealed based on parameter identification of the runoff system. The optimal delay time and embedding dimension of the monthly runoff time series are deduced. Secondly, with the time series of the reconstructed phase space matrix as input variables, an improved AdaBoost. RT algorithm based on self-adaptive dynamic threshold was incorporated to improve the performance of extreme learning machine. Finally, the optimal chaotic ensemble learning model for monthly runoff prediction was obtained. Results showed that the proposed model could evidently improve the generalization and stability of single extreme learning machine model, and thus achieve better prediction performance.
关键词
径流预报 /
长江上游 /
混沌动力特性 /
相空间重构 /
极限学习机 /
集成预测
Key words
runoff forecasting /
upper reaches of Yangtze River /
chaotic dynamic characteristics /
phase space reconstruction /
extreme learning machine /
integrated prediction
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 朱 双, 周建中, 孟长青,等. 基于灰色关联分析的模糊支持向量机方法在径流预报中的应用研究[J]. 水力发电学报, 2015, 34(6): 1-6.
[2] HENSE A. On the Possible Existence of a Strange Attractor for the Southern Oscillation[J]. Beitr. Physical Atmosphere,1987, 60(1):34-47.
[3] HU Z, ZHANG C, LUO G, et al. Characterizing Cross-scale Chaotic Behaviors of the Runoff Time Series in an Inland River of Central Asia[J]. Quaternary International, 2013, 311(9): 132-139.
[4] 王秀杰, 练继建, 费守明. 基于小波消噪的混沌神经网络径流预报模型[J]. 水力发电学报, 2008, 27(5): 37-40.
[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): 116-122.
[6] 郭晓亮, 王国利, 梁国华,等. 径流混沌时间序列的模糊支持向量机预测模型研究及其应用[J]. 水力发电学报, 2010, 29(3): 51-55.
[7] HONG M, WANG D, WANG Y, et al. Mid-and Long-term Runoff Predictions by an Improved phase-space Reconstruction Model[J]. Environmental Research, 2016, 148:560-573.
[8] TAORMINA R, CHAU K W. Data-driven Input Variable Selection for Rainfall-runoff Modeling Using Binary-coded Particle Swarm Optimization and Extreme Learning Machines[J]. Journal of Hydrology, 2015, 529:1617-1632.
[9] PENG T, ZHOU J, ZHANG C, et al. Streamflow Forecasting Using Empirical Wavelet Transform and Artificial Neural Networks[J]. Water, 2017, 9(6): 406.
[10]马细霞, 穆浩泽. 基于混沌分析的月径流序列耦合预测模型及其应用[J]. 水力发电学报, 2010, 29(6): 41-46.
[11]周建中, 张娟娟, 郭 俊,等.基于小波消噪的混沌神经网络月径流预报模型[J]. 水资源研究, 2012, 1(3): 65-71.
[12]OUYANG Q, LU W, XIN X, et al. Monthly Rainfall Forecasting Using EEMD-SVR Based on Phase-Space Reconstruction[J]. Water Resources Management, 2016, 30(7): 2311-2325.
[13]孙惠子, 粟晓玲, 昝大为. 基于最优加权组合模型的枯季径流预测研究[J]. 西北农林科技大学学报(自然科学版), 2011, 39(11): 201-208.
[14]肖 洁, 罗军刚, 解建仓,等. 变权组合预测模型在洪水预报中的应用[J]. 西北农林科技大学学报(自然科学版), 2013, 41(2): 215-221.
[15]FREUND Y, SCHAPIRE R E. Experiments with a New Boosting Algorithm[C]∥Proceedings of the Thirteenth International Conference on Machine Learning, Bari, Italy. July 3-6,1996:148-156.
[16]HUANG G B, ZHU Q Y, SIEW C K. Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks[C]∥Proceedings of the IEEE International Joint Conference on Neural Networks, Budapest, Hungary. July 25-29,2004:985-990.
[17]PACKARD N H, CRUTCHFIELD J P, FARMER J D, et al. Geometry from a Time Series[J]. Physical Review Letters, 1980, 45(9): 712.
[18]TAKENS F. Detecting Strange Attractors in Turbulence[M]. Heidelberg: Springer, 1981.
[19]SOLOMATINE D P, SHRESTHA D L. AdaBoost R T: A Boosting Algorithm for Regression Problems[C]∥Proceedings of the IEEE International Joint Conference on Neural Networks,Budapest, Hungary. July 25-29, 2004:1163-1168 .
[20]SHRESTHA D L, SOLOMATINE D P. Experiments with AdaBoost.RT, an Improved Boosting Scheme for Regression[J]. Neural Computation, 2006, 18(7): 1678-1710.
[21]TIAN H X, MAO Z Z. An Ensemble ELM Based on Modified AdaBoost.RT Algorithm for Predicting the Temperature of Molten Steel in Ladle Furnace[J]. IEEE Transactions on Automation Science & Engineering, 2010, 7(1):73-80.
基金
国家自然科学基金重大研究计划重点支持项目(91547208);国家自然科学基金面上项目(51579107);国家重点研发计划课题(2016YFC0402708, 2016YFC0401005)
PDF(5267 KB)
