Comparison of <i>Dst</i> forecast models for intense geomagnetic storms

Ji, Eun‐Young; Moon, Y.-J.; Gopalswamy, Ν.; Lee, Dong Hun

doi:10.1029/2011ja016872

Cited by 30 publications

(22 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nevertheless, based on the statistical analysis of these different ANN methods, our ANN+PSO method can be considered as a very accurate method. Still, a comparison can be made for some selected data sets; thus, we compared our method versus other six Dst forecast models for 1 h in advance (called B [ Burton et al , ], FL [ Fenrich and Luhmann , ], OM [ O'Brien and McPherron , ], TL [ Temerin and Li , ], W [ Wang et al , ], NM [ Boynton et al , ], and persistence P [ Witt and Malamud , ]) using 63 selected storms with Dst levels <−100 nT taken between 1998 and 2006, following the methodology and database proposed by Ji et al []. Then, we statistically compared these six methods using the correlation coefficient R , the root‐mean‐square error, RMSE, the difference in the minimum value of forecasted and measured Dst values |Δ Dst min |, and the absolute timing difference between the observed and measured Dst values |Δ t Dst | to test the accuracy and performance of these methods.…”

Section: Discussionmentioning

confidence: 99%

Forecasting the Dst index using a swarm‐optimized neural network

et al. 2017

View full text Add to dashboard Cite

A hybrid technique that combines an artificial neural network with a particle swarm optimization (ANN+PSO) was used to forecast the disturbance storm time (Dst) index from 1 to 6 h ahead. Our ANN was optimized by PSO to update ANN weights and to predict the short‐term Dst index using past values as input parameters. The database used contains 233,760 hourly data from 1 January 1990 to 31 August 2016, considering storms and quiet period, grouped into three data sets: learning set (with 116,880 hourly data points), validation set (with 58,440 data points), and testing set (with 58,440 data points). Several ANN topologies were studied, and the best architecture was determined by systematically adding neurons and evaluating the root‐mean‐square error (RMSE) and the correlation coefficient (R) during the training process. These results show that the hybrid algorithm is a powerful technique for forecasting the Dst index a short time in advance like t + 1 to t + 3, with RMSE from 3.5 nT to 7.5 nT, and R from 0.98 to 0.90. However, t + 4 to t + 6 predictions become slightly more uncertain, with RMSE from 8.8 nT to 10.9 nT, and R from 0.86 to 0.79. Additionally, an exhaustive analysis according to geomagnetic storm magnitude was conducted. In general, the results show that our hybrid algorithm can be correctly trained to forecast the Dst index with appropriate precision and that Dst past behavior significantly affects adequate training and predicting capabilities of the implemented ANN.

show abstract

Section: Discussionmentioning

confidence: 99%

Forecasting the Dst index using a swarm‐optimized neural network

et al. 2017

View full text Add to dashboard Cite

show abstract

“…At present, these types of models are in great demand, since they can give exact (though perhaps not always accurate) values at some time moments in a future. Ji et al (2012) compared the outputs from six Dst-index forecast models during intense geomagnetic storms, namely, Burton et al (1975), Fenrich and Luhmann (1998) ) also included Burton-type representations (Burton et al 1975;Murayama 1986), NARMAX model (Boynton et al 2011a), and Rice Dst model (Bala and Reiff 2012). All of the models showed very reasonable results, NARMAX model (Boynton et al 2011a) was specifically mentioned.…”

Section: Dst-index As a Storm Indicator Measure And Predictormentioning

confidence: 99%

Space Weather Effects Produced by the Ring Current Particles

2017

View full text Add to dashboard Cite

One of the definitions of space weather describes it as the time-varying space environment that may be hazardous to technological systems in space and/or on the ground and/or endanger human health or life. The ring current has its contributions to space weather effects, both in terms of particles, ions and electrons, which constitute it, and magnetic and electric fields produced and modified by it at the ground and in space. We address the main aspects of the space weather effects from the ring current starting with brief review of ring current discovery and physical processes and the Dst-index and predictions of the ring current and storm occurrence based on it. Special attention is paid to the effects on satellites produced by the ring current electrons. The ring current is responsible for several processes in the other inner magnetosphere populations, such as the plasmasphere and radiation belts which is also described. Finally, we discuss the ring current influence on the ionosphere and the generation of geomagnetically induced currents (GIC).

show abstract

“…After selecting the best performing GP‐AR and GP‐ARX models in the validation phase, we test and compare the performance of these models with the predictions generated from the persistence model

\overset{D}{true} st (t) = Dst (t - 1)

, on a set of 63 storm events occurring between 1998 and 2006 as given in Table , which is the same list of storm events as used in Ji et al [].…”

Section: Methodsmentioning

confidence: 99%

Probabilistic forecasting of the disturbance storm time index: An autoregressive Gaussian process approach

2017

View full text Add to dashboard Cite

We present a methodology for generating probabilistic predictions for the Disturbance Storm Time(Dst) geomagnetic activity index. We focus on the One Step Ahead prediction task and use the OMNI hourly resolution data to build our models. Our proposed methodology is based on the technique of Gaussian Process Regression. Within this framework we develop two models; Gaussian Process Autoregressive (GP‐AR) and Gaussian 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.

show abstract

Comparison of Dst forecast models for intense geomagnetic storms

Cited by 30 publications

References 44 publications

Forecasting the Dst index using a swarm‐optimized neural network

Forecasting the Dst index using a swarm‐optimized neural network

Space Weather Effects Produced by the Ring Current Particles

Probabilistic forecasting of the disturbance storm time index: An autoregressive Gaussian process approach

Contact Info

Product

Resources

About