Neural net forecasting for geomagnetic activity
Authors:
- 7 December 1993
- journal article
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 20 (23) , 2707-2710
Abstract
We use neural nets to construct nonlinear models to forecast the AL index given solar wind and interplanetary magnetic field (IMF) data. We follow two approaches: 1) the state space reconstruction approach, which is a nonlinear generalization of autoregressive‐moving average models (ARMA) and 2) the nonlinear filter approach, which reduces to a moving average model (MA) in the linear limit. The database used here is that of Bargatze et al. [1985].Keywords
This publication has 19 references indexed in Scilit:
- The non‐linear response of the magnetosphere: 30 October 1978Geophysical Research Letters, 1993
- A nonlinear dynamical analogue model of geomagnetic activityJournal of Geophysical Research, 1992
- Nonlinear prediction of chaotic time seriesPhysica D: Nonlinear Phenomena, 1989
- IMF control of geomagnetic activityAdvances In Space Research, 1988
- Magnetospheric response to the IMF : Substorms.Journal of geomagnetism and geoelectricity, 1986
- Magnetospheric impulse response for many levels of geomagnetic activityJournal of Geophysical Research, 1985
- Solar wind control of auroral zone geomagnetic activityGeophysical Research Letters, 1981
- Geometry from a Time SeriesPhysical Review Letters, 1980
- Interplanetary energy flux associated with magnetospheric substormsPlanetary and Space Science, 1979
- Impulse response of geomagnetic indices to interplanetary magnetic field.Journal of geomagnetism and geoelectricity, 1979