Improving Forecasts of Geomagnetic Storms with Evolved Recurrent Neural Networks

Mirikitani, Derrick T.; Ouarbya, Lahcen; Tsui, Lisa and Martin, Eamonn. 2012. 'Improving Forecasts of Geomagnetic Storms with Evolved Recurrent Neural Networks'. In: IEEE 10th International Conference on Cybernetic Intelligent Systems (CIS). London, United Kingdom 1 - 2 September 2011. [Conference or Workshop Item]

[img]
Preview
Text
Improving_forecasts_of_geomagnetic_storms_with_evolved_recurrent_neural_networks.pdf - Accepted Version

Download (853kB) | Preview

Abstract or Description

Recurrent neural networks (RNNs) have been used for modeling the dynamics of the D st index. Researchers have experimented with various inputs to the model, and have found improvements in prediction accuracy using measurements of the interplanetary magnetic field (IMF) taken from the Advanced Composition Explorer satellite. The output of the model is the one hour ahead forecasted D st index. Previous models have used gradient information, usually gradient descent, for optimization of RNN parameters. This paper uses the IMF inputs (that have been found to work well) to the RNN and uses a Genetic algorithm for training the RNN. The proposed model is compared to a model used in operational forecasts which relies on solar wind data and IMF parameters, as well as a model which uses IMF data only. Both of the comparison models were trained with gradient descent. A series of geomagnetic storms that so far have been difficult to forecast are used to evaluate model performance. It is shown that the proposed evolutionary method of training the RNN outperforms both models which were trained by gradient descent.

Item Type:

Conference or Workshop Item (Paper)

Identification Number (DOI):

https://doi.org/10.1109/CIS.2011.6169133

Additional Information:

“© 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”

Keywords:

Storms, Lead, Context, Educational institutions

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
1 September 2011Published Online
15 March 2012Published

Event Location:

London, United Kingdom

Date range:

1 - 2 September 2011

Item ID:

6809

Date Deposited:

16 Apr 2012 12:35

Last Modified:

12 Jan 2022 18:07

URI:

https://research.gold.ac.uk/id/eprint/6809

View statistics for this item...

Edit Record Edit Record (login required)