Prediction and variation of the auroral oval boundary based on a deep learning model and space physical parameters

Han, Yiyuan; Han, Bing; Hu, Zejun; Gao, Xinbo; Zhang, Lixia; Yang, Huigen; Li, Bin

doi:https://doi.org/10.5194/npg-27-11-2020

Articles | Volume 27, issue 1

https://doi.org/10.5194/npg-27-11-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/npg-27-11-2020

© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 27, issue 1

Research article

|

03 Feb 2020

Research article |

| 03 Feb 2020

Prediction and variation of the auroral oval boundary based on a deep learning model and space physical parameters

Yiyuan Han, Bing Han, Zejun Hu, Xinbo Gao, Lixia Zhang, Huigen Yang, and Bin Li

Supplement

https://doi.org/10.5194/npg-27-11-2020-supplement

Data sets

One min and 5-min solar wind data sets at the Earth's bow shock nose J. King and N. Papitashvili http://omniweb.gsfc.nasa.gov/html/HROdocum.html

Disclaimer: The following material is being kept online for archival purposes C. Cattell, J. Dombeck, A. Keiling, J. Wygant, R. Bergmann, M. K. Hudson, and G. Parks https://pwg.gsfc.nasa.gov/polar/data_products.shtml#instruments

Short summary

We design a new non-linear model to construct an accurate relationship between auroral oval boundaries and 18 space physical parameters, and explore the influence of every single space physical parameter on auroral oval boundary in this paper. As a result, we found the combination of some space physical parameters can strengthen each other's influence on aurora oval boundary prediction, and this model can achieve the best performance when only partial space physical parameters are used as input.