Title | Machine learning approaches for predicting the 10.7 cm radio flux from solar magnetogram data |
| |
Author | Valdés, J J; Nikolic, L; Tapping, K |
Source | 2019 International Joint Conference on Neural Networks (IJCNN), proceedings; N-19557, 2019 p. 1-8, https://doi.org/10.1109/IJCNN.2019.8852332 |
Image |  |
Year | 2019 |
Alt Series | Natural Resources Canada, Contribution Series 20180438 |
Publisher | IEEE |
Meeting | IJCNN 2019 - International Joint Conference on Neural Networks; Budapest; HU; July 14-19, 2019 |
Document | book |
Lang. | English |
Media | on-line; digital |
File format | pdf (Adobe® Reader®); html |
Subjects | geophysics; Science and Technology; Nature and Environment; solar variations; magnetic field; models; Methodology; Forecasting; machine learning |
Illustrations | sketch maps; time series; tables; 3-D images; plots |
Program | Public Safety Geoscience Northern Canada Geohazards Project |
Released | 2019 09 30 |
Abstract | Using solar magnetogram data, we explore potential of machine learning in space weather forecasting. In particular, unsupervised and supervised machine learning techniques are used to investigate the
structure of magnetograms for 2006-2018, and their relation with the 10.7 cm solar radio flux. The similarity structure of the magnetograms is characterized with perception-based state of the art measures (the MSSIM index) and it was found that the
data are contained in a space of intrinsically low dimension. The properties of these spaces were explored with methods preserving both local dissimilarity relationships, as well as conditional probability distributions within neighbourhoods. They
reveal a clear relation with the intensity of the 10.7 cm flux. The flux was modeled using data driven supervised approaches in the form of model trees and convolutional neural networks. Models were found that allow prediction of the 10.7 cm radio
flux with high accuracy. The results demonstrate significant potential which machine learning has in the space weather field. |
Summary | (Plain Language Summary, not published) Space weather refers to the dynamic conditions on the Sun and in the space environment, in particular, in the near-Earth environment, that can affect
critical infrastructure. NRCan operates the Canadian Space Weather Forecast Centre and conducts research into space weather effects on power systems, pipelines, radio communications and GNSS positioning to help Canadian industry understand and
mitigate the effects of space weather. In this work we investigate potential of using machine learning approaches to forecast space weather. Using solar magnetograms, we demonstrate forecast of the solar radio flux. |
GEOSCAN ID | 314537 |
|
|