Central england temperatures and solar activity: A Computational Intelligence approach

Two Computational Intelligence techniques, neural networks-based Multivariate Time Series Model Mining (MVTSMM) and Genetic Programming (GP), have been used to explore the possible relationship between solar activity and temperatures in Central England for the 1721 to 1967 period. Data driven analysis of multivariate, heterogeneous and incomplete time series are used in order to understand the extreme complexity of the climate machinery and to detect the possible relative contribution of influencing processes, like the Sun, whose decadal and centennial role in the climate is still debated. Experiments were carried out using each one of these techniques and their combination. Time-lag spectra obtained by means of MVTSMM seems to indicate time stamps of some of the relevant Earth-climate and solar variations on the temperature record. The equations provided by GP approximated analytically the relative contribution of particular solar activity time-lags. These preliminary results, even if they still are insufficient to support or discredit possible physical mechanisms, are interesting and encouraging to explore more in that direction.

[1]  Vassilios Petridis,et al.  Predictive Modular Neural Networks: Applications to Time Series , 1998 .

[2]  Fortunat Joos,et al.  Solar activity during the last 1000 yr inferred from radionuclide records , 2007 .

[3]  Nathan Intrator,et al.  Optimal ensemble averaging of neural networks , 1997 .

[4]  Francesco Carlo Morabito,et al.  Solar Activity Forecasting by Incorporating Prior Knowledge from Nonlinear Dynamics into Neural Networks , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[5]  Una-May O'Reilly,et al.  Genetic Programming II: Automatic Discovery of Reusable Programs. , 1994, Artificial Life.

[6]  Julio J. Valdés,et al.  Greenland Temperatures and Solar Activity: A Computational Intelligence Approach , 2007, 2007 International Joint Conference on Neural Networks.

[7]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[8]  John R. Koza,et al.  Genetic Programming III: Darwinian Invention & Problem Solving , 1999 .

[9]  G. Manley.  Central England temperatures: Monthly means 1659 to 1973 , 1974 .

[10]  Francesco Carlo Morabito,et al.  A New Technique for Solar Activity Forecasting using Recurrent Elman Networks , 2005, IEC.

[11]  D. Hathaway,et al.  Group Sunspot Numbers: Sunspot Cycle Characteristics , 2002 .

[12]  George E. P. Box,et al.  Time Series Analysis: Forecasting and Control , 1977 .

[13]  D. J. Gorney,et al.  A sunspot maximum prediction using a neural network , 1990 .

[14]  Kwok-wing Chau,et al.  A hybrid adaptive time-delay neural network model for multi-step-ahead prediction of sunspot activity , 2006 .

[15]  Douglas V. Hoyt,et al.  Group Sunspot Numbers: A New Solar Activity Reconstruction , 1998 .

[16]  Eric Y. Zhang,et al.  Predicting effects of climate fluctuations for water management by applying neural network , 1996 .

[17]  I. Usoskin,et al.  Lost sunspot cycle in the beginning of Dalton minimum: New evidence and consequences , 2002 .

[18]  B. Tinsley,et al.  The global atmospheric electric circuit and its effects on cloud microphysics , 2008 .

[19]  H. Svensmark,et al.  Cosmic ray decreases affect atmospheric aerosols and clouds , 2009 .

[20]  Cândida Ferreira,et al.  Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence , 2014, Studies in Computational Intelligence.

[21]  John R. Koza,et al.  Hierarchical Genetic Algorithms Operating on Populations of Computer Programs , 1989, IJCAI.

[22]  S. Solanki,et al.  Unusual activity of the Sun during recent decades compared to the previous 11,000 years , 2004, Nature.

[23]  Jeff Harrison,et al.  Applied Bayesian Forecasting and Time Series Analysis , 1994 .

[24]  Julio J. Valdés,et al.  Time dependent neural network models for detecting changes of state in complex processes: Applications in earth sciences and astronomy , 2006, Neural Networks.

[25]  D. Parker,et al.  Published online in Wiley InterScience (www.interscience.wiley.com). DOI: 10.1002/joc.1190 UNCERTAINTIES IN CENTRAL ENGLAND TEMPERATURE 1878–2003 AND SOME IMPROVEMENTS TO THE MAXIMUM AND MINIMUM SERIES , 2005 .

[26]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[27]  W. Herschel.  XIII. Observations tending to investigate the nature of the sun, in order to find the causes or symptoms of its variable emission of light and heat; with remarks on the use that may possibly be drawn from solar observations , 1801, Philosophical Transactions of the Royal Society of London.

[28]  John R. Koza.  Genetic Programming III - Darwinian Invention and Problem Solving , 1999, Evolutionary Computation.

[29]  Julio J. Valdés,et al.  Mining Multivariate Time Series Models with Soft-Computing Techniques: A Coarse-Grained Parallel Computing Approach , 2003, ICCSA.

[30]  T. Benner.  Central England temperatures: long‐term variability and teleconnections , 1999 .

[31]  P. Baffes,et al.  Sunspot prediction using neural networks , 1990 .

[32]  G. Reinsel.  Elements of Multivariate Time Series Analysis , 1995 .

[33]  D. Signorini,et al.  Neural networks , 1995, The Lancet.