Deep sequence-to-sequence neural networks for ionospheric activity map prediction

N. Cherrier, T. Castaings and A. Boulch

ICONIP, 2017

Best paper award finalist at ICONIP 2017

Abstract

The ability to predict the ionosphere activity is of interest for several applications such as satellite telecommunications or Global Navigation Satellite Systems (GNSS). A few studies have proposed models able to predict Total Electron Content (TEC) values of the ionosphere locally over measuring stations, but not worldwide for most of them. We propose a method using Deep Neural Networks (DNN) to predict a sequence of global TEC maps consecutive to an input sequence of past TEC maps, by combining Convolutional Neural Networks (CNNs) with convolutional Long Short-Term Memory (LSTM) networks. The numerical experiments show that the approach provides signi cant improvement over methods implemented for benchmarking and is competitive with state-of-the-art methods while providing global TEC predictions. The proposed architecture can be adapted to any sequence-to-sequence prediction problem.

Citation

@inproceedings{cherrier2017deep,
  title={Deep sequence-to-sequence neural networks for ionospheric activity map prediction},
  author={Cherrier, No{\"e}lie and Castaings, Thibaut and Boulch, Alexandre},
  booktitle={International Conference on Neural Information Processing},
  pages={545--555},
  year={2017},
  organization={Springer}
}