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.