Probabilistic forecasting of the disturbance storm time index: An autoregressive Gaussian process approach
Open Access
- 5 August 2017
- journal article
- research article
- Published by American Geophysical Union (AGU) in Space Weather
- Vol. 15 (8) , 1004-1019
Abstract
We present a methodology for generating probabilistic predictions for theDisturbance Storm Time(Dst) geomagnetic activity index. We focus on theOne Step Aheadprediction task and use the OMNI hourly resolution data to build our models. Our proposed methodology is based on the technique ofGaussian Process Regression. Within this framework we develop two models;Gaussian Process Autoregressive(GP‐AR) andGaussian Process Autoregressive with eXogenous inputs(GP‐ARX). We also propose a criterion to aid model selection with respect to the order of autoregressive inputs. Finally, we test the performance of the GP‐AR and GP‐ARX models on a set of 63 geomagnetic storms between 1998 and 2006 and illustrate sample predictions with error bars for some of these events.Keywords
Funding Information
- National Science Foundation (AGS-1058456)
- National Aeronautics and Space Administration (NNX13AE12G, NNX15AJ01G, NNX16AC39G)
This publication has 43 references indexed in Scilit:
- Geomagnetic Dst index forecast based on IMF data onlyAnnales Geophysicae, 2006
- Influence of the solar wind dynamic pressure on the decay and injection of the ring currentJournal of Geophysical Research, 2003
- Computational analysis of the near‐Earth magnetospheric current system during two‐phase decay stormsJournal of Geophysical Research, 2001
- A study of the regularities in solar magnetic activity by singular spectral analysisAstronomy Letters, 2001
- Terrestrial magnetosphere as a nonlinear resonatorGeophysical Research Letters, 2001
- Determination of the effects of substorms on the storm‐time ring current using neural networksJournal of Geophysical Research, 2000
- An empirical phase space analysis of ring current dynamics: Solar wind control of injection and decayJournal of Geophysical Research, 2000
- Empirical polar cap potentialsJournal of Geophysical Research, 1997
- Identification of MIMO non-linear systems using a forward-regression orthogonal estimatorInternational Journal of Control, 1989
- Solar wind triggering of substorm expansion onset.Journal of geomagnetism and geoelectricity, 1986