The use of sequential recurrent neural filters in forecasting the \(\mathbf D_{st}\) index for the strong magnetic storm of autumn 2003. (English) Zbl 1250.85002
Summary: Neural based geomagnetic forecasting literature has heavily relied upon non-sequential algorithms for estimation of model parameters. This paper proposes sequential Bayesian recurrent neural filters for online forecasting of the \(\mathbf D_{st}\) index. Online updating of the RNN parameters allows for newly arrived observations to be included into the model. The online RNN filters are compared to two (non-sequentially trained) models on a severe double storm that has so far been difficult to forecast. It is shown that the proposed models can significantly reduce forecast errors over non-sequentially trained recurrent neural models.
References:
| [1] | Axford, W. I.; Hines, C. O., A unifying theory of high-latitude geophysical phenomena and geomagnetic storms, Can. J. Phys., 39, 1433-1464 (1961) |
| [2] | Dungey, J. W., Interplanetary magnetic field and the auroral zones, Phys. Rev. Lett., 26, 47-48 (2000) |
| [3] | Gonzales, W. D.; Joselyn, J. A.; Kamide, Y.; Kroehl, H. W.; Rostoker, G.; Tsurutani, B. T.; Vasyliunas, V. M., What is a geomagnetic storm?, J. Geophys. Res., 99, 5771-5792 (1994) |
| [4] | Farrugia, C. J.; Freeman, M. P.; Burlaga, L. F.; Lepping, R. P.; Takahashi, K., The earth’s magnetosphere under continued forcing - Substorm activity during the passage of an interplanetary magnetic cloud, J. Geophys. Res., 98, 7657-7671 (1993) |
| [5] | Gosling, J. T.; McComas, D. J.; Phillips, J. L.; Bame, S. J., Geomagnetic activity associated with earth passage of interplanetary shock disturbances and coronal mass ejections, J. Geophys. Res., 96, 7831-7839 (1991) |
| [6] | Lundstedt, H., Neural networks and prediction of solar-terrestrial effects, Planet. Space Sci., 40, 457-464 (1992) |
| [7] | Lundstedt, H.; Wintoft, P., Prediction of geomagnetic storms from solar wind data with the use of a neural network, Ann Geophys., 12, 19-24 (1994) |
| [8] | Pallocchia, G.; Amata, E.; Consolini, G.; Marcucci, M. F.; Bertello, I., Geomagnetic Dst index forecast based on IMF data only, Ann. Geophys., 24, 989-999 (2006) |
| [9] | Puskorius, G. V.; Feldkamp, L. A., Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks, IEEE T Neural Networks., 5, 279-297 (1994) |
| [10] | Schottky, B.; Saad, D., Statistical mechanics of EKF learning in neural networks, J. Phys. A: Math Gen., 32, 1605-1621 (1999) · Zbl 0964.82044 |
| [11] | Williams, R. J.; Zipser, D., A learning algorithm for continuously running fully connected recurrent neural networks, Neural Computation, 1, 270-280 (1989) |
| [12] | Haykin, S., Kalman Filtering and Neural Networks (2001), John Wiley & Son: John Wiley & Son New York |
| [13] | Cernansky, M.; Benuskova, L., Simple recurrent network trained by RTRL and extended Kalman filter algorithms, Neural Network World, 13, 3, 223-234 (2003) |
| [14] | S. Julier, J. Uhlmann, A new extension of the Kalman filter to nonlinear systems. Signal Processing, Sensor Fusion, and Target Recognition VI, vol. 3068, 1997, pp. 182-193.; S. Julier, J. Uhlmann, A new extension of the Kalman filter to nonlinear systems. Signal Processing, Sensor Fusion, and Target Recognition VI, vol. 3068, 1997, pp. 182-193. |
| [15] | Lundstedt, H.; Gleisner, H.; Wintoft, P., Operational forecasts of the geomagnetic Dst index, Geophys. Res. Lett., 29 (2002), 34-1-34-4 |
| [16] | Amata, E.; Pallocchia, G.; Consolini, G.; Marcucci, M. F.; Bertello, I., Comparison between three algorithms for Dst predictions over the 2003-2005 period, Journal of Atmospheric and Solar-Terrestrial Physics, 70, 496-502 (2008) |
| [17] | Lund space weather center |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
