Abstract
Various phenomena with solar origin and their mutual dependence must be studied in order to predict behaviors in solar – terrestrial system. Linear statistical methods prevalent in analyzing natural systems may not be able to detect nonlinear dependencies among solar and geomagnetic processes. When relations, whether linear or nonlinear, between indices and their changes over time are revealed, better predictions can be made through appropriate modeling techniques. Selection of nonredundant input variables to build suitable models for prediction of solar and geomagnetic activity is of utmost importance. Mutual information is a tool that is capable of capturing all dependencies for detecting nonlinear relations and selecting the best subset of input variables by means of an applicable algorithm that maximizes information about the output and minimizes the shared information between inputs. High generalization power and improved interpretability of the selected inputs are the consequences of this analysis.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Attia, A.-F., Abdel-Hamid, R., Quassim, M.: 2005, Solar Phys. 227, 177.
Bartels, J.: 1932, Terr. Magn. Atmos. Electr. 37, 1.
Battiti, R.: 1994, IEEE Trans. Neural Netw. 5, 537.
Baum, E.B., Haussler, D.: 1989, Neural Comput. 1, 151.
Benoudjit, N., Cools, E., Meurens, M., Verleysen, M.: 2004, Chemom. Intell. Lab. Syst. 70, 47.
Calvo, R.A., Ceccatto, H.A., Piacentini, R.D.: 1995, Astrophys. J. 444, 916.
Caruana, R., Freitag, D.: 1994, In: Cohen, W.W., Hirsh, H. (eds.) Proc. Int. Conf. Machine Learning (ICML-94), Morgan Kaufmann, San Francisco, 28.
Cover, T.M., Thomas, J.A.: 1990, Elements of Information Theory, Wiley, New York, 13.
Darbellay, G.: 1998, Institute of Information Theory and Automation (UTIA) Research Report No. 1889, Czech Academy of Science, Prague.
Das, S.: 2001, In: Brodley, C.E., Danyluk, A.P. (eds.) Proc. Int. Conf. Machine Learning (ICML-2001), Morgan Kaufmann, San Francisco, 74.
Dash, M., Liu, H.: 1997, Intell. Data Anal. 1, 131.
Dy, J.G., Brodley, C.E.: 2000, In: Langley, P. (ed.) Proc. Int. Conf. Machine Learning (ICML-2000), Morgan Kaufmann, San Francisco, 247.
Echer, E., Gonzales, W.D., Gonzalez, A.L.C., Prestes, A., Vieira, L.E.A., Dal Lago, A., Guarnieri, F.L., Schuch, N.J.: 2004, J. Atmos. Solar-Terr. Phys. 66, 1019.
Fayyad, U.M., Irani, K.B.: 1992, In: Swartout, W.R. (ed.) Proc. Natl. Conf. Artificial Intelligence (AAAI-92), AAAI Press/MIT Press, 104.
Geman, S., Bienenstock, E., Doursat, R.: 1992, Neural Comput. 4, 1.
Gholipour, A., Lucas, C., Araabi, B.N., Shafiee, M.: 2005, J. Atmos. Solar-Terr. Phys. 67, 595.
Granger, C.W.J., Lin, J.: 1994, J. Time Ser. Anal. 15, 371.
Gupta, M., Mishra, V.K., Mishra, A.P.: 2005, In: Acharya, B.S., Gupta, S., Jagedeesan, P., Jain, A., Karthikeyan, S., Morris, S., Tonwar, S. (eds.) Proc. 29th Int. Cosmic Ray Conf. 2, 147.
Guyon, I., Elisseeff, A.: 2003, J. Mach. Learn. Res. 3, 1157.
Jeong, J., Gore, J.C., Peterson, B.S.: 2001, Clin. Neurophysiol. 112, 827.
John, G.H., Kohavi, R., Pfleger, K.: 1994, In: Cohen, W.W., Hirsh, H. (eds.) Proc. Int. Conf. Machine Learning (ICML-94), Morgan Kaufmann, San Francisco, 121.
Kraskov, A., Stögbauer, H., Grassberger, P.: 2004, Phys. Rev. E 69, 066138.
Kudela, K., Storini, M., Hofer, M.Y., Belov, A.: 2000, Space Sci. Rev. 93, 153.
Kudela, K., Storini, M.: 2005, J. Atmos. Solar-Terr. Phys. 67, 907.
Kwak, N., Choi, C.H.: 2002, IEEE Trans. Neural Netw. 13, 143.
Liu, H., Setiono, R.: 1996, In: Saitta, L. (ed.) Proc. Int. Conf. Machine Learning (ICML-96), Morgan Kaufmann, San Francisco, 319.
Lundstedt, H.: 2005, Adv. Space Res. 36, 2516.
Mirmomeni, M., Shafiee, M., Lucas, C., Araabi, N.B.: 2006, J. Atmos. Solar-Terr. Phys. 68, 2061.
Mishra, A.P., Gupta, M., Mishra, V.K.: 2006, Solar Phys. 239, 475.
Nelles, O.: 2001, Nonlinear System Identification, Springer, Berlin, 341.
Reyhani, N., Hao, J., Ji, Y., Lendasse, A.: 2005, In: Verleysen, M. (ed.) Proc. European Symp. Artificial Neural Networks (ESANN2005), D-Side Publications, Brussels, 503.
Rossi, F., Lendasse, A., François, D., Wertz, V., Verleysen, M.: 2006, Chemom. Intell. Lab. Syst. 80, 215.
Schwarz, U., Kurths, J., Witt, A., Benz, A.O.: 1994, Space Sci. Rev. 68, 245.
Scott, D.W.: 1992, Multivariable Density Estimation: Theory, Practice, and Visualization, Wiley, New York, 47 and 125.
Shannon, C.E.: 1948, Bell Syst. Tech. J. 27, 379 and 623.
Siedlecki, W., Sklansky, J.: 1988, Int. J. Pattern Recogn. Artif. Intell. 2, 197.
Vassiliadis, D.: 2000, IEEE Trans. Plasma Sci. 28, 1944.
Wu, C.-C., Lepping, R.P.: 2006, Ann. Geophys. 24, 3383.
Xing, E., Jordan, M., Karp, R.: 2001, In: Brodley, C.E., Danyluk, A.P. (eds.) Proc. Int. Conf. Machine Learning (ICML-2001), Morgan Kaufmann, San Francisco, 601.
Yearmolaev, Y.I.: 2001, Cosmic Res. 39, 303.
Yu, L., Liu, H.: 2003, In: Fawcett, T., Mishra, N. (eds.) Proc. Int. Conf. Machine Leaning (ICML-03), AAAI Press, Menlo Park, 856.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rezaei Yousefi, M., Salehi Kasmaei, B., Vahabie, A. et al. Input Selection Based on Information Theory for Constructing Predictor Models of Solar and Geomagnetic Activity Indices. Sol Phys 258, 297–318 (2009). https://doi.org/10.1007/s11207-009-9418-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11207-009-9418-6