Long-term prediction of solar and geomagnetic activity daily time series using singular spectrum analysis and fuzzy descriptor models

详细信息    查看全文

• 作者：Masoud Mirmomeni ; E. Kamaliha ; Masoud Shafiee ; Caro Lucas
• 关键词：Space weather ; geomagnetic disturbance ; solar activity indices ; prediction ; fuzzy descriptor models ; singular systems ; singular spectrum analysis ; GLoLiMoT
• 刊名：Earth, Planets and Space
• 出版年：2009
• 出版时间：September 2009
• 年：2009
• 卷：61
• 期：9
• 页码：1089-1101
• 全文大小：333KB
• 参考文献：Bellman, R., Adaptive Control Processes: A Guided Tour, Princeton University Press, 1961.
  Bothmer, V. and I. Daglis, Space Weather Physics and Effects, Springer Praxis Publishing, Chichester, UK, 2007.
  Brown, G. M., The peak of solar cycle 22: predictions in retrospect, Ann. Geophys., 10, 453-70, 1992.
  Brown, M. and C. Harris, Neurofuzzy Adaptive Modeling and Control, Prentice Hall, UK, 1995.
  Campbell, S. L., Singular Systems of Differential Equation, Pitman, London, 1980.
  Dai, L., Singular Control Systems, Springer, New York, 1989.CrossRef
  Dziurla, B. and R. W. Newcomb, The Drazien inverse and semi-state equations, in Proc. 4th Int. Symp. on Math. Theory of Networks and Systems. Delft, Netherland, pp. 283-89, 1979.
  Gholipour, A., A. Abbaspour, B. N. Araabi, and C. Lucas, Enhancements in the prediction of solar activity by locally linear model tree, paper presented at 22nd IASTED Int. Con. on Modeling, Identification, and Control, Innsbruck, Austria, 2003.
  Gholipour, A., C. Lucas, B. N. Araabi, and M. Shafiee, Solar activity forecast: spectral analysis and neurofuzzy prediction, J. Atmos. Sol.-Terr. Phys., 67, 595-03, 2005.CrossRef
  Gholipour, A., C. Lucas, B. N. Araabi, M. Mirmomeni, and M. Shafiee, Extracting the main patterns of natural time series for long-term neuro-fuzzy prediction, J. Neural Comput. Appl., 16(4-), 383-93, 2007.CrossRef
  Halfmann, C., O. Nelles, and H. Holzmann, Modeling and identification of the vehicle suspension characteristics using local linear model trees, in Proc. of IEEE, Int. Conf. on Control Applications, Khala-Coast island, Hawaii, USA, pp. 1484-489, 1999.
  Haykin, S. (editor), Unsupervised Neural networks: A Comprehensive Foundation, Macmillan, New York, 1994.
  Joselyn, J. A. et al., Panel achieves consensus prediction of solar cycle, Eos Trans. AGU, 78, 211-12, 1997.CrossRef
  Kang, J. L. and W. S. Tang, Minimum energy control of 2-D singular systems with constrained control, in Proc. of the 4th Int. Conference on Machine Learning and Cybernetics, August 18-1, Guangzhou, 2005.
  Karystinos, G. N. and A. Pados, On overfitting, generalization, and randomly expanded training sets, IEEE Trans. Neural Networks, 11(5), 1050-057, 2000.CrossRef
  Klir, G. J. and T. A. Folger, Fuzzy sets, uncertainty and information, Prentice-Hall, Englewood Cliffs, NJ, 1988.
  Leung, H., T. Lo, and S. Wang, Prediction of noisy chaotic time series using an optimal radial basis function neural network, IEEE Trans. Neural Networks, 12(5), 1163-172, 2001.CrossRef
  Lewis, Z. V., On the apparent randomness of substorm onsets, Geophys. Res. Lett., 18, 1627, 1991.CrossRef
  Lillekjendlie, B., D. Kugimutzis, and N. Christophersen, Chaotic time series, part II: System identification and prediction, Identification Control, 15, 225-43, 1994.CrossRef
  Ljung, L., System Identification: Theory for the User, New Jersey, Prentice-Hall, 1987.
  Lu, G. and D. W. C. Ho, Generalized quadratic stabilization for perturbated discrete-time singular systems with delayed state, in 4th Int. Conf. on Control and Automation (ICCA-3), June 10-2, Montreal, Canada, 2003.
  Lucas, C., A. Abbaspour, A. Gholipour, B. N. Araabi, and M. Fatourechi, Enhancing the performance of neurofuzzy predictors by emotional learning algorithm, Informatica, 27(2), 165-74, 2003.
  Luenberger, D. G., Dynamic equation in descriptor form, IEEE Trans. Auto. Contr., AC-22, 132-21, 1977.
  Meng, B. and J. F. Zhang, Reachability conditions for switched linear singular systems, IEEE Trans. Automatic Control, 51(3), 482-88, 2006.CrossRef
  Mirmomeni, M. and C. Lucas, Analyzing the variation of embedding dimension of solar and geomagnetic activity indices during geomagnetic storm time, Earth Planets Space, 61, 237-47, 2009.
  Mirmomeni, M. and M. Shafiee, State analysis of discrete-time singular nonlinear systems using a fuzzy neural network, in 13th Iranian Conference on Electrical Engineering (ICEE-5), Zanjan University, Zanjan, Iran, 2005a.
  Mirmomeni, M. and M. Shafiee, State analysis of time-invariant singular systems via Haar wavelet, in 13th Iranian Conference on Electrical Engineering (ICEE-5), Zanjan University, Zanjan, Iran, 2005b.
  Mirmomeni, M., M. Shafiee, C. Lucas, and B. N. Araabi, Introducing a new learning method for fuzzy descriptor systems with the aid of spectral analysis to forecast solar activity, J. Atmos. Sol.-Terr. Phys., 68, 2061-074, 2006.CrossRef
  Mirmomeni, M., C. Lucas, and B. Moshiri, Long term prediction of chaotic time series with the aid of neuro fuzzy models, spectral analysis and correlation analysis, IEEE Int. Joint Conference on Neural Networks, Orlando, Florida, USA, 2007.
  Nelles, O., Nonlinear System Identification, Springer, Berlin, 2001.CrossRef
  Newcomb, R. W., The semi-state description of nonlinear time-variable circuits, IEEE Trans. Circuits Systems, 28, 62-1, 1981.CrossRef
  Pandolfi, L., On the Regulator Problem for Line
• 作者单位：Masoud Mirmomeni (16)
  E. Kamaliha (26)
  Masoud Shafiee (36)
  Caro Lucas (16) (46)
  
  16. Control and Intelligent Processing Center of Excellence, School of Electrical and Computer Engineering, University College of Engineering, University of Tehran, Tehran, Iran
  26. Computer Engineering Department, Sharif University of Technology, Tehran, Iran
  36. Electrical Engineering Department, Amirkabir University of Technology, Tehran, Iran
  46. School of Cognitive Sciences, Institute for studies in theoretical Physics and Mathematics, Tehran, Iran
  
• 刊物类别：Earth Sciences, general; Geology; Geophysics/Geodesy;
• 刊物主题：Earth Sciences, general; Geology; Geophysics/Geodesy;
• 出版者：Springer Berlin Heidelberg
• ISSN：1880-5981

文摘

Of the various conditions that affect space weather, Sun-driven phenomena are the most dominant. Cyclic solar activity has a significant effect on the Earth, its climate, satellites, and space missions. In recent years, space weather hazards have become a major area of investigation, especially due to the advent of satellite technology. As such, the design of reliable alerting and warning systems is of utmost importance, and international collaboration is needed to develop accurate short-term and long-term prediction methodologies. Several methods have been proposed and implemented for the prediction of solar and geomagnetic activity indices, but problems in predicting the exact time and magnitude of such catastrophic events still remain. There are, however, descriptor systems that describe a wider class of systems, including physical models and non-dynamic constraints. It is well known that the descriptor system is much tighter than the state-space expression for representing real independent parametric perturbations. In addition, the fuzzy descriptor models as a generalization of the locally linear neurofuzzy models are general forms that can be trained by constructive intuitive learning algorithms. Here, we propose a combined model based on fuzzy descriptor models and singular spectrum analysis (SSA) (FD/SSA) to forecast a number of geomagnetic activity indices in a manner that optimizes a fuzzy descriptor model for each of the principal components obtained from singular spectrum analysis and recombines the predicted values so as to transform the geomagnetic activity time series into natural chaotic phenomena. The method has been applied to predict two solar and geomagnetic activity indices: geomagnetic aa and solar wind speed (SWS) of the solar wind index. The results demonstrate the higher power of the proposed method—compared to other methods—for predicting solar activity. Key words Space weather geomagnetic disturbance solar activity indices prediction fuzzy descriptor models singular systems singular spectrum analysis GLoLiMoT