Greenland Temperatures and Solar Activity: A Computational Intelligence Approach

Download
  1. (PDF, 497 KB)
AuthorSearch for: ; Search for:
TypeArticle
ConferenceProceedings of the 2007 IEEE International Joint Conference on Neural Networks (IJCNN 2007), August 12-17, 2007., Orlando, Florida, USA
AbstractThe complexity of the earths climate and its relationship with solar activity are here approached by means of two computational intelligence techniques: Multivariate Time Series Model Mining (MVTSMM) and Genetic Programming (GP). They were applied to a temperature record (Delta O18/16), obtained from an ice core in Central Greenland, representative of the climate variations in the North Atlantic regions, and the International Sunspot Number series, as a proxy of solar activity, both covering the period from 1721 to 1983. Several experiments were conducted using these records jointly and separately with the purpose of characterize and reveal their time dependencies. Preliminary results show this mining approach is a valid and promising research line. The time-lag spectra obtained with MVTSMM seem to point out to time stamps of some of the most important Earth-climate and solar variations, as well as the contribution of solar activity and sunspot solar cycles along time. The GP provided equations which approximate the relative contribution of particular solar time-lags. Although suggestive, this research is at an early stage and the results are preliminary, emphasizing methodological aspects.
Publication date
LanguageEnglish
AffiliationNRC Institute for Information Technology; National Research Council Canada
Peer reviewedNo
NRC number49298
NPARC number5765439
Export citationExport as RIS
Report a correctionReport a correction
Record identifierd13fea8c-4241-487f-9c39-ea80f4dee29b
Record created2009-03-29
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)