Application of NARX neural network in storm-time SYM-H index prediction from IMF and solar wind data
Abstract
In this study the NARX neural network has been used for the first time to predict high-resolution magnetic storm index of SYM-H from solar wind (SW) and IMF parameters. In total 73 great storm events with IMF/SW data available from ACE satellite during 1998 to 2006 are used to establish the ANN model. Out of them, 67 are used to train the network and the other 6 samples for test. Additionally, the NARX prediction model is also validated using IMF/SW data from WIND satellite for 7 great storms during 1995-1997 and 2005, as well as for the July 2000 Bastille day storm and November 2001 superstorm using Geotail and OMNI data at 1AU. Five interplanetary parameters of IMF Bz, By and total B components along with proton density and velocity of solar wind are used as the original external inputs of the neural network to predict the SYM-H index about one hour or an even longer time ahead. For the 6 test storms registered by ACE including two super-storms with minimum SYM-H less than -200 nT, the correlation coefficient between observed and NARX network predicted SYM-H is 0.95 as a whole, even as high as 0.95 and 0.98 with average relative variance of 13.2 percent and 7.4 percent for the two super-storms, respectively. The prediction for the 7 storms with WIND data is also satisfactory, showing averaged correlation coefficient about 0.91 and RMSE of 14.2 nT. The newly developed NARX model shows much better capability than Elman network for SYM-H prediction, which can partly be attributed to a key feedback to the input layer from the output neuron with a suitable length (about 120 min). This feedback means that nearly real information of the ring current status is effectively brought to taking part in the prediction of SYM-H index by ANN. The proper history length of the output-feedback may mainly reflect on average the characteristic time of ring current decay which involves various decay mechanisms with ion lifetimes from tens of minutes to tens of hours. Besides, it is verified that this kind of model is also capable of providing satisfactory predictions of the SYM-H index 3 hours ahead from IMF/SW data with less physical parameters observed at L1 position, enhancing significantly the practicality of the model in space weather forecasting.
- Publication:
-
38th COSPAR Scientific Assembly
- Pub Date:
- 2010
- Bibcode:
- 2010cosp...38.4207C