ANGEO Annales Geophysicae ANGEO Ann. Geophys. 1432-0576 Copernicus Publications Göttingen, Germany 10.5194/angeo-30-963-2012 Estimating the geoeffectiveness of halo CMEs from associated solar and IP parameters using neural networks Uwamahoro J. 1 2 McKinnell L. A. 2 3 Habarulema J. B. 2 Department of Mathematics and Physics, Kigali Institute of Education [KIE], P.O. Box 5039 – Kigali, Rwanda South African National Space Agency [SANSA], Space Science, 7200 Hermanus, South Africa Department of Physics and Electronics, Rhodes University, Grahamstown 6140, South Africa 12 06 2012 30 6 963 972 Copyright: © 2012 J. Uwamahoro et al. 2012 This work is licensed under the Creative Commons Attribution 3.0 Unported License. To view a copy of this licence, visit https://creativecommons.org/licenses/by/3.0/ This article is available from https://angeo.copernicus.org/articles/30/963/2012/angeo-30-963-2012.html The full text article is available as a PDF file from https://angeo.copernicus.org/articles/30/963/2012/angeo-30-963-2012.pdf

Estimating the geoeffectiveness of solar events is of significant importance for space weather modelling and prediction. This paper describes the development of a neural network-based model for estimating the probability occurrence of geomagnetic storms following halo coronal mass ejection (CME) and related interplanetary (IP) events. This model incorporates both solar and IP variable inputs that characterize geoeffective halo CMEs. Solar inputs include numeric values of the halo CME angular width (AW), the CME speed (<I>V</I><sub>cme</sub>), and the comprehensive flare index (cfi), which represents the flaring activity associated with halo CMEs. IP parameters used as inputs are the numeric peak values of the solar wind speed (<I>V</I><sub>sw</sub>) and the southward Z-component of the interplanetary magnetic field (IMF) or <I>B</I><sub>s</sub>. IP inputs were considered within a 5-day time window after a halo CME eruption. The neural network (NN) model training and testing data sets were constructed based on 1202 halo CMEs (both full and partial halo and their properties) observed between 1997 and 2006. The performance of the developed NN model was tested using a validation data set (not part of the training data set) covering the years 2000 and 2005. Under the condition of halo CME occurrence, this model could capture 100% of the subsequent intense geomagnetic storms (Dst &le; −100 nT). For moderate storms (−100 < Dst &le; −50), the model is successful up to 75%. This model's estimate of the storm occurrence rate from halo CMEs is estimated at a probability of 86%.

 References Bishop, C.&nbsp;M.: Neural Networks for Pattern Recognition, Oxford University Press Inc., New York, USA, 1995. Bruckner, G.&nbsp;E., Howard, R.&nbsp;A., Koomen, M.&nbsp;J., Korendyke, C.&nbsp;M., Michels, D.&nbsp;J., Moses, J.&nbsp;D., Socker, D.&nbsp;G., Dere, K.&nbsp;P., Lamy, P.&nbsp;L., Lleberia, A., Bout, M.&nbsp;V., Schwenn, R., Simnett, G.&nbsp;M., Bedford, D.&nbsp;K., and Eyles, C.&nbsp;J.: The Large Angle Spectroscopic Coronagraph, (LASCO), Solar Phys., 162, 357–402, 1995. Burton, R.&nbsp;K., McPherron, R.&nbsp;L., and Russell, C.&nbsp;T.: An empirical relationship between interplanetary conditions and Dst, J. Geophys. Res., 80, 4204–4214, 1975. Cane, H.&nbsp;V. and Richardson, I.&nbsp;G.: Interplanetary coronal mass ejections in the near-Earth solar wind during 1996–2002, J. Geophys. Res., 108, A4, <a href="http://dx.doi.org/10.1029/2002JA009817">https://doi.org/10.1029/2002JA009817</a>, 2003. Conway, A.&nbsp;J.: Time series, neural networks and the future of the Sun, New Astronomy Reviews, 42, 343–394, 1998. Cyr, O. C.&nbsp;S., Howard, R.&nbsp;A., Sheeley, N.&nbsp;R., Plunkett, S.&nbsp;P., Michels, D.&nbsp;J., Paswaters, S.&nbsp;E., Koomen, M.&nbsp;J., and Simnett, G.&nbsp;M.: Properties of coronal mass ejections: SOHO LASCO observations from January 1996 to June 1998, J. Geophys. Res., 105, 169–185, 2000. Dryer, M.: Multidimentional, magnetohydrodynamics simulation of solar-generated disturbances: Space weather forecasting of geomagnetic storms, AIAA Journal, 36, 365–370, 1998. Dryer, M., Smith, Z., Fry, C.&nbsp;D., Sun, W., Deehr, C.&nbsp;S., and Akasofu, S.&nbsp;I.: Real-Time shock arrival predictions during the Halloween 2003 epoch, Space Weather, 2, S09001, <a href="http://dx.doi.org/10.1029/2004SW000087">https://doi.org/10.1029/2004SW000087</a>, 2004. Echer, E., Gonzalez, W.&nbsp;D., Tsurutani, B.&nbsp;T., and Gonzalez, A. L.&nbsp;C.: Interplanetary conditions causing intense geomagnetic storms (${\rm Dst \leq -100$ nT) during solar cycle&nbsp;23 (1996–2006)}, J. Geophys. Res., 113, A05221, <a href="http://dx.doi.org/10.1029/2007JA012744">https://doi.org/10.1029/2007JA012744</a>, 2008. Fox, N. and Murdin, P.: Solar-Terrestrial Connection: Space Weather Predictions, Encyclopedia, Astronomy and Astrophysics, 2416, <a href="http://dx.doi.org/10.1888/0333750888/2416">https://doi.org/10.1888/0333750888/2416</a>, 2001. Gonzalez, W.&nbsp;D. and Tsurutani, B.&nbsp;T.: Criteria of interplanetary parameters causing intense magnetic storms (${\rm Dst < - 100$ nT)}, Planet Space Sci., 35, 1101–1109, 1987. Gonzalez, W.&nbsp;D., Joselyn, J.&nbsp;A., Kamide, Y., Kroehl, H.&nbsp;W., Tsurutani, B.&nbsp;T., Vasyliunas, V.&nbsp;M., and Rostoker, G.: What is a Geomagnetic storm?, J. Geophys. Res., 99, 5771–5792, 1994. Gonzalez, W.&nbsp;D., Lago, A.&nbsp;D., de&nbsp;Gonzalez, A. L.&nbsp;C., Vieira, L. E.&nbsp;A., and Tsurutani, B.&nbsp;T.: Prediction of peak-Dst from halo CME/magnetic cloud-speed observations, J. Atmos. Sol. Terr. Phys., 66, 161–165, 2004. Gopalswamy, N.: Coronal mass ejection and space weather, in: Climate and Weather of the Sun-Earth System (CAWSES): Selected papers from the 2007 Kyoto Symposium, edited by: Tsuda, T., Fujii, R., Shibata, K., and Geller, M.&nbsp;A., pp. 77–120, \textcopyright TERRAPUB, TOKYO, 2009. Gopalswamy, N., Yashiro, S., and Akiyama, S.: Geoeffectiveness of halo coronal mass ejections, J. Geophys. Res., 112, A06112, <a href="http://dx.doi.org/10.1029/2006JA012149">https://doi.org/10.1029/2006JA012149</a>, 2007. Hung, M.&nbsp;S., Hu, M.&nbsp;Y., Shanker, M.&nbsp;S., and Patuwo, B.&nbsp;E.: Estimating Posterior Probabilities In Classification Problems with Neural Networks, International Journal of Computational Intelligence and Organizations, 1, 49–60, 1996. Kamide, Y., Baumjohann, W., Gonzalez, W.&nbsp;D., Grande, M., Joselyn, J.&nbsp;A., McPheron, R.&nbsp;L., Phillips, J.&nbsp;L., Reeves, E. G.&nbsp;D., Rostoker, G., Sharma, A.&nbsp;S., Singer, H.&nbsp;J., and&nbsp;Vasyliunas, V.&nbsp;M. B. T.&nbsp;T.: Current understanding of magnetic storms: Storm-substorm relationships, J. Geophys. Res., 103, 705–728, 1998. Kim, R.&nbsp;S., Chao, K.&nbsp;S., Moon, Y.&nbsp;J., Dryer, M., Lee, J., Yi, Y., Kim, K.&nbsp;H., Wang, H., Park, Y.&nbsp;D., and Kim, Y.&nbsp;H.: An empirical model for prediction of geomagnetic storms using initially observed CME parameters at the Sun, J. Geophys. Res., 115, A12108, <a href="http://dx.doi.org/10.1029/2010JA015322">https://doi.org/10.1029/2010JA015322</a>, 2010. Loewe, C.&nbsp;A. and Prölss, G.&nbsp;W.: Classification and mean behaviour of magnetic storms, J. Geophys. Res., 102, 14209–14213, 1997. Lundstedt, H.: AI Techniques in Geomagnetic Storm Forecasting, in: Magnetic Storms, edited by: Tsurutani, B.&nbsp;T., Gonzalez, W.&nbsp;D., Kamide, Y., and Arballo, J.&nbsp;K., vol.&nbsp;98 of Geophys. Monograph series, pp. 243–252, AGU, Washington D.C., 1997. Lundstedt, H. and Wintoft, P.: Prediction of geomagnetic storms from solar wind data with the use of a neural network, Ann. Geophys., 12, 19–24, <a href="http://dx.doi.org/10.1007/s00585-994-0019-2">https://doi.org/10.1007/s00585-994-0019-2</a>, 1994. Lundstedt, H., Gleisner, H., and Wintoft, P.: Operational forecasts of the geomagnetic Dst index, Geophys. Res. Lett., 29, 2181, <a href="http://dx.doi.org/10.1029/2002GL016151">https://doi.org/10.1029/2002GL016151</a>, 2002. Lundstedt, H., Liszka, L., and Lundin, R.: Solar activity explored with new wavelet methods, Ann. Geophys., 23, 1505–1511, <a href="http://dx.doi.org/10.5194/angeo-23-1505-2005">https://doi.org/10.5194/angeo-23-1505-2005</a>, 2005. Macpherson, K.&nbsp;P., Conway, A.&nbsp;J., and Brown, J.&nbsp;C.: Prediction of solar and geomagnetic activity data using neural networks, J. Geophys. Res., 100, 735–744, 1995. McKinnell, L.&nbsp;A., Paradza, M.&nbsp;W., Cilliers, P.&nbsp;J., Abdu, M.&nbsp;A., and de&nbsp;Souza, J.&nbsp;R.: Predicting the probability occurrence of spread-F over Brazil using neural networks, Adv. Space Res., 46, 1047–1054, 2010. Messerotti, M., Zuccarello, F., Guglielmo, S.&nbsp;L., Bothmer, V., Lilensten, J., Noci, G., Storini, M., and Lundstedt, H.: Solar Weather Event Modelling and prediction, Space Sci. Rev., 147, 121–185, 2009. Pallocchia, G., Amata, E., Consolini, G., Marcucci, M. F., and Bertello, I.: Geomagnetic <i>D<sub>st</sub></i> index forecast based on IMF data only, Ann. Geophys., 24, 989–999, <a href="http://dx.doi.org/10.5194/angeo-24-989-2006">https://doi.org/10.5194/angeo-24-989-2006</a>, 2006. Richard, M.&nbsp;D. and Lippmann, R.&nbsp;P.: Neural Network Classifiers Estimate Bayesian a Posteriori Probabilities, Neural Computation, 3, 461–483, 1991. Richardson, I.&nbsp;G.: Major geomagnetic storms (${\rm Dst}\leq -100 $ nT) generated by corotating interactive regions, J. Geophys. Res., 111, A07S09, <a href="http://dx.doi.org/10.1029/2005JA011476">https://doi.org/10.1029/2005JA011476</a>, 2006. Richardson, I. and Cane, H.: Near-Earth Interplanetary Coronal Mass Ejections in 1996–2007, Tech. rep., Astrophysics Physics Laboratory, NASA Goddard Space Flight Center, Greenbelt, Maryland, USA, 2008. Richardson, I.&nbsp;G., Cane, H.&nbsp;V., and Cliver, E.&nbsp;W.: Sources of geomagnetic activity during nearly three solar cycles (1972–2000), J. Geophys. Res., 107, A8, <a href="http://dx.doi.org/10.1029/2001JA000504">https://doi.org/10.1029/2001JA000504</a>, 2002. Richardson, I.&nbsp;G., Webb, D.&nbsp;F., Zhang, J., Berdichersky, D.&nbsp;B., Biesecker, D.&nbsp;A., Kasper, J.&nbsp;C., Kataoka, R., Steinberg, J.&nbsp;T., Thompson, B.&nbsp;J., Wu, C.-C., and Zhukov, A.&nbsp;N.: Major geomagnetic storms ($Dst \leq -100$ nT) generated by corotating interactive regions, J. Geophys. Res., 111, A07S09, 2006. Schwenn, R., Dal Lago, A., Huttunen, E., and Gonzalez, W. D.: The association of coronal mass ejections with their effects near the Earth, Ann. Geophys., 23, 1033–1059, <a href="http://dx.doi.org/10.5194/angeo-23-1033-2005">https://doi.org/10.5194/angeo-23-1033-2005</a>, 2005. Siscoe, G. and Schwenn, R.: CME disturbance forecasting, Space Sc. Rev., 123, 453–470, 2006. Srivastava, N.: A logistic regression model for predicting the occurrence of intense geomagnetic storms, Ann. Geophys., 23, 2969–2974, <a href="http://dx.doi.org/10.5194/angeo-23-2969-2005">https://doi.org/10.5194/angeo-23-2969-2005</a>, 2005. Srivastava, N. and Venkatakrishnan, P.: Solar and interplanetary sources of geomagnetic storms during 1996-2002, J. Geophys. Res., 109, A10103, <a href="http://dx.doi.org/10.1029/2003JA010175">https://doi.org/10.1029/2003JA010175</a>, 2004. Stone, E.&nbsp;C., Frandsen, A.&nbsp;M., Mewaldt, R.&nbsp;A., Christian, E.&nbsp;R., Margolies, D., Ormes, J.&nbsp;F., and Snow, F.: The Advanced Composition Explorer, Space Sci. Rev., 86, 357–408, 1998. Uwamahoro, J., McKinnell, L.&nbsp;A., and Cilliers, P.&nbsp;J.: Forecasting solar cycle 24 using neural networks, J. Atmos. Solar-Terr. Phys., 71, 569–574, 2009. Valach, F., Revallo, M., Bochnicek, J., and Hejda, P.: Solar energetic particle flux enhancement as a predictor of geomagnetic activity in a neural network-based model, Space Weather, 7, S04004, <a href="http://dx.doi.org/10.1029/2008SW000421">https://doi.org/10.1029/2008SW000421</a>, 2009. Wang, Y.&nbsp;M., Ye, P.&nbsp;Z., Wang, S., Zhou, G.&nbsp;P., and Wang, J.&nbsp;X.: A statistical study on the geoeffectiveness of the Earth-directed coronal mass ejections from March 1997 to December 2000, J. Geophys. Res., 107, A11, <a href="http://dx.doi.org/10.1029/2002JA009244">https://doi.org/10.1029/2002JA009244</a>, 2002. Webb, D.&nbsp;F.: Coronal Mass Ejections: Origins, Evolution, and Role in Space Weather, IEEE Trans. plasma sc., 28, 1795–1806, 2000. Webb, D.&nbsp;F., Cliver, E.&nbsp;W., Crooker, N.&nbsp;U., st&nbsp;Cyr, O.&nbsp;C., and Thompson, B.&nbsp;J.: Relationship of halo coronal mass ejections, magnetic clouds and magnetic storms, J. Geophys. Res., 105, 7491–7508, 2000. Woolley, J.&nbsp;W., Agarwarl, P.&nbsp;K., and Baker, J.: Modeling and Prediction of Chaotic Systems with artificial neural networks, International Journal for Numerical Methods in Fluids, 63, 2117, <a href="http://dx.doi.org/10.1002/fld.2117">https://doi.org/10.1002/fld.2117</a>, 2010. Zell, A., Mamier, G.&nbsp;M., Vogt, M., Mach, N., Hübner, R., Döring, S., Herrmann, K.&nbsp;U., Soyez, T., Schmalzl, M., Sommer, T., Hatzigeorgiou, A., Posselt, D., Schreiner, T., Kett, B., Clemente, G., Wieland, J., and Gatter, J.: Stuttgart Neural Network Simulator (SNNS), User Manual, version 4.2, Universities of Stuttgart and Tübingen, Germany and the European Particle Research Lab, CERN, Geneva, Switzerland, 1998. Zhang, J., Richardson, I.&nbsp;G., Webb, D.&nbsp;F., Gopalswamy, N., Huttunen, E., Kasper, J.&nbsp;C., Nitta, N.&nbsp;V., Poomvises, W., Thompson, B.&nbsp;J., Wu, C.&nbsp;C., Yashiro, S., and Zhukov, A.&nbsp;N.: Solar and interplanetary sources of major geomagnetic storms (${\rm Dst \leq - 50 $ nT) during 1996–2005}, J. Geophys. Res., 112, A10102, <a href="http://dx.doi.org/10.1029/2007JA012321">https://doi.org/10.1029/2007JA012321</a>, 2007.