Articles | Volume 27, issue 1
Nonlin. Processes Geophys., 27, 11–22, 2020
https://doi.org/10.5194/npg-27-11-2020
Nonlin. Processes Geophys., 27, 11–22, 2020
https://doi.org/10.5194/npg-27-11-2020

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 et al.

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

Download
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.