PREDSTORM AND SOLARWIND2GIC: FORECASTING OF SPACE WEATHER EFFECTS AND GICS WITH PYTHON

Rachel Louise Bailey, C Möstl, U. V. Amerstorfer, T. Amerstorfer, A. J. Weiss, J. Hinterreiter, M. A. Reiss, Dennis Albert

Publikation: KonferenzbeitragPoster

Abstract

PREDSTORM is a package developed as part of the project “Enhanced
lead time for geomagnetic storms”. The aim is to build a framework that
will provide a forecast of the solar wind at the L1 point using a
combination of empirical and machine learning methods. Among the
properties that can then be predicted from the L1 data are the
geomagnetic Dst index and the magnitudes of GICs in power grids.
Originalspracheenglisch
Seitenumfang1
PublikationsstatusVeröffentlicht - 2019
VeranstaltungMachine Learning in Heliophysics - The Royal Tropical Institute - Koninklijk Instituut voor de Tropen (KIT), Amsterdam, Niederlande
Dauer: 16 Sep 201920 Sep 2019
https://ml-helio.github.io/

Konferenz

KonferenzMachine Learning in Heliophysics
KurztitelML-Helio
LandNiederlande
OrtAmsterdam
Zeitraum16/09/1920/09/19
Internetadresse

ASJC Scopus subject areas

  • !!Earth and Planetary Sciences(all)

Treatment code (Nähere Zuordnung)

  • Application

Fingerprint Untersuchen Sie die Forschungsthemen von „PREDSTORM AND SOLARWIND2GIC: FORECASTING OF SPACE WEATHER EFFECTS AND GICS WITH PYTHON“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren