EGU22-8887
https://doi.org/10.5194/egusphere-egu22-8887
EGU General Assembly 2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

CME-learn: An interactive playground to benchmark CME databases for the time of arrival (ToA) prediction for using machine learning methods.

Ajay Tiwari1, Enrico Camporeale2,3, Dario Del Moro4, Raffaello Foldes5, Gianluca Napoletano4, Giancarlo de Gasperis4, and Jannis Teunissen1
Ajay Tiwari et al.
  • 1Centrum WIskunde and Informatica, Amsterdam, Netherlands (ajt@cwi.nl)
  • 2University of Colorado, Boulder
  • 3NOAA Space Weather Prediction Center
  • 4Università degli Studi di Roma "Tor Vergata"
  • 5University of L'Aquila

Coronal mass ejections are one of the most significant drivers of space weather. The ToA predictions along with the Arrival speed of the CMEs are one of the crucial pieces of information for preparing for the possible geomagnetic storms. Geomagnetic storms can have adverse effects on several key components of modern society e.g. communications and electrical grids. The development of many machine learning methods provides us with the opportunity to use these tools in space weather applications. There have been several studies using machine learning methods for ToA predictions. In this study, we present an interactive dashboard to apply several machine learning methods (regression models) to test on the several CME databases used in the community. We also use this opportunity to benchmark various CME databases for TOA and CME arrival speed predictions. We also welcome the community to use this interactive dashboard as a tool to learn about machine learning.

How to cite: Tiwari, A., Camporeale, E., Del Moro, D., Foldes, R., Napoletano, G., de Gasperis, G., and Teunissen, J.: CME-learn: An interactive playground to benchmark CME databases for the time of arrival (ToA) prediction for using machine learning methods., EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-8887, https://doi.org/10.5194/egusphere-egu22-8887, 2022.

Comments on the display material

to access the discussion