A neural network–based geosynchronous relativistic electron flux forecasting model

[1] A multilayer feed-forward neural network model has been developed to forecast >2 MeV electron flux at geosynchronous orbit. The model uses as input 10 consecutive days of historical electron flux values and 7 consecutive days of daily summed values of the planetary Kp index with two neurons in a single hidden layer. Development of the model is discussed in which the size of the training set interval and the retraining period are investigated. Problems associated with neuron saturation which limit the ability of the network to generalize are shown to be circumvented through a daily retraining regimen. The model performance is evaluated for the period 1998–2008 and compared with the results produced by the REFM model. The neural network model is demonstrated to perform quite well relative to the REFM model for this time period, producing mean prediction efficiencies for 6 month test intervals of 0.71, 0.49, and 0.31 for 1 day, 2 day, and 3 day forecasts, respectively.

[1]  Tsugunobu Nagai,et al.  “Space weather forecast”: Prediction of relativistic electron intensity at synchronous orbit , 1988 .

[2]  Y. Kamide,et al.  Mountains versus valleys: Semiannual variation of geomagnetic activity , 2000 .

[3]  G. Wrenn.  Conclusive evidence for internal dielectric charging anomalies on geosynchronous communications spacecraft , 1995 .

[4]  J. B. Blake,et al.  Effects of the solar wind on magnetospheric dynamics: Energetic electrons at the synchronous orbit , 2013 .

[5]  P. Filbert,et al.  Space Charging Currents and Their Effects on Spacecraft Systems , 1983, IEEE Transactions on Electrical Insulation.

[6]  M. Shea,et al.  Space weather: The effects on operations in space , 1998 .

[7]  Xinlin Li.  Variations of 0.7–6.0 MeV electrons at geosynchronous orbit as a function of solar wind , 2004 .

[8]  Daniel N. Baker,et al.  Correlation between the inner edge of outer radiation belt electrons and the innermost plasmapause location , 2006 .

[9]  Yoshizumi Miyoshi,et al.  Probabilistic space weather forecast of the relativistic electron flux enhancement at geosynchronous orbit , 2008 .

[10]  William H. Press,et al.  Numerical recipes in C , 2002 .

[11]  Daniel N. Baker,et al.  Quantitative prediction of radiation belt electrons at geostationary orbit based on solar wind measurements , 2001 .

[12]  Elijah Polak,et al.  Computational methods in optimization , 1971 .

[13]  P. Mayaud,et al.  Derivation, Meaning, and Use of Geomagnetic Indices , 1980 .

[14]  Drew Turner,et al.  Quantitative forecast of relativistic electron flux at geosynchronous orbit based on low‐energy electron flux , 2008 .

[15]  D. Baker,et al.  Adaptive linear prediction of radiation belt electrons using the Kalman filter , 2004 .

[16]  Brian J. Anderson,et al.  Data‐derived forecasting model for relativistic electron intensity at geosynchronous orbit , 2004 .

[17]  Harry C. Koons,et al.  A neural network model of the relativistic electron flux at geosynchronous orbit , 1991 .

[18]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[19]  Daniel N. Baker,et al.  Linear prediction filter analysis of relativistic electron properties at 6.6 RE , 1990 .

[20]  Sheldon Howard Jacobson,et al.  The Theory and Practice of Simulated Annealing , 2003, Handbook of Metaheuristics.

[21]  Lawrence. Davis,et al.  Handbook Of Genetic Algorithms , 1990 .

[22]  T. Nagai,et al.  Prediction of a geosynchronous electron environment with in situ magnetic field measurements , 1999 .

[23]  G. P. Ginet,et al.  Comparing geosynchronous relativistic electron prediction models , 2010 .