Prediction of geomagnetic storms from solar wind data using Elman Recurrent Neural Networks

Wu, Jianguo; Lundstedt, H.

doi:10.1029/96gl00259

Cited by 120 publications

(93 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Geomagnetic disturbances are likely to be one of the largest sources of deviation between observed and modelled geomagnetic ®eld values. In recent years methods of predicting geomagnetic storms and substorms in near real-time from solar wind data using nonlinear ®lters (Vassiliadis et al, 1995) and neural networks (Lundstedt and Wintoft, 1994;Wu and Lundstedt, 1996;Weigel et al, 1999) have been developed. However, such predictions are limited to hours, or at best days, into the future and require observed solar wind data.…”

Section: Resultsmentioning

confidence: 99%

“…Arti®cial neural networks (ANNs) are a branch of AI methods which are proving particularly successful in solar-terrestrial time series prediction and pattern recognition; they appear to be especially e ective in modelling the time development of irregular processes (Koons and Gorney, 1991;Lundstedt, 1992;Gorney et al, 1993;Lundstedt and Wintoft, 1994;Williscroft and Poole, 1996;Wu and Lundstedt, 1996; Sutcli e, 1997; Weigel et al, 1999).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The development of a regional geomagnetic daily variation model using neural networks

Sutcliffe¹

2000

Ann. Geophys.

View full text Add to dashboard Cite

Abstract. Global and regional geomagnetic ®eld models give the components of the geomagnetic ®eld as functions of position and epoch; most utilise a polynomial or Fourier series to map the input variables to the geomagnetic ®eld values. The only temporal variation generally catered for in these models is the long term secular variation. However, there is an increasing need amongst certain users for models able to provide shorter term temporal variations, such as the geomagnetic daily variation. In this study, for the ®rst time, arti®cial neural networks (ANNs) are utilised to develop a geomagnetic daily variation model. The model developed is for the southern African region; however, the method used could be applied to any other region or even globally. Besides local time and latitude, input variables considered in the daily variation model are season, sunspot number, and degree of geomagnetic activity. The ANN modelling of the geomagnetic daily variation is found to give results very similar to those obtained by the synthesis of harmonic coe cients which have been computed by the more traditional harmonic analysis of the daily variation.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The development of a regional geomagnetic daily variation model using neural networks

Sutcliffe¹

2000

Ann. Geophys.

View full text Add to dashboard Cite

show abstract

“…The development of magnetic storms, including the energy content in the ring current and the coupling to the solar wind, has been successfully modeled in the past as a simple, nonlinear, input-output system, with solar wind VBz as the input and Dst as the output [Gonzalez et al, 1994;Valdivia et al, 1996;Wu and Lundstedt, 1996], where V is the x component of the solar wind velocity and Bz the z component of the solar wind magnetic field. We expect that a more complete understanding of the nonlinear behavior of the ring current could be reached after a more careful analysis of the evolution of its spatial structure, namely, its spariotemporal behavior.…”

Section: -0227/99 / 1999j A90015250900mentioning

confidence: 99%

Spatiotemporal activity of magnetic storms

Valdivia¹,

Vassiliadis²,

Klimas³

et al. 1999

J. Geophys. Res.

View full text Add to dashboard Cite

Abstract.We have constructed a data-derived model of the evolution of the spatial structure of the ring current geomagnetic signature during storms. A spatially dependent generalization of the Dessler-Parker-Skopke relation has been derived to explain the spatial structure in the midlatitude magnetic fluctuations (MLMF) as observed by ground magnetometers. Such a relation is used as a basis for constructing solar-wind-driven, data-derived models of the MLMF. The model includes a coupling to the solar wind as the energy driver and also includes a nonlocal coupling as an explanation of the inhomogeneity in the energy density that appears in the ring current during the main phase of a storm. Both linear and nonlinear models for the evolution of the spatial structure of the MLMF are constructed, and the nonlinear spatial model of the ring current produces better predictions than the linear one. This can be taken as an indication that during strong magnetic storms the ring current evolves in a nonlinear fashion. The spatial data used in the generation of the models are rotated to a frame "fixed" with the ring current, and presure effects were accounted through a kinematic relation. The techniques developed in this paper are very general and can be used to study other systems that show spatial structure, such as the high-latitude current system.

show abstract

“…The low-dimensional dynamical model is then applied to new SW time-series to predict the geomagnetic response. In another approach, neural networks are trained on historical SW data and geomagnetic indices and are then applied to new input SW time-series [e.g., Lundstedt, 1992;Hernandez et al, 1993;Wu and Lundstedt, 1996;Wu et al, 1998]. …”

Section: Introductionmentioning

confidence: 99%

Space Storms and Space Weather Hazards

Daglis¹

2001

View full text Add to dashboard Cite

Subject Terms Report Classification unclassified Classification of this page unclassified Classification of Abstract unclassified Limitation of Abstract UU Number of Pages 486REPORT DOCUMENTATION PAGE Public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington, VA 22202-4302, and to the Office of Management and Budget, -to review recent spacecraft measurements that have provided new insight into the dynamics and effects of space storms; -to review space weather hazards associated with space storms and pertinent to the operation of technological systems in space and on ground;-to discuss and assess methods of space weather forecasting, as well as national and international initiatives towards an efficient development of space climatology.Space weather, the invisible but nevertheless effective result of solar activity and solar-terrestrial coupling, has affected the operations of communication systems since the appearance of telegraph in the 19th century, though as an unknown trouble factor. Nowadays, the effects of space weather affect in various ways all communication modes, from cable to wireless to space-based systems. Moreover, space weather hazards include malfunction or even permanent damage of power distribution grids and of telecommunication, navigation and surveillance satellites, disturbances of over-the-horizon (OTH) radar, HF, VHF and UHF communications, surveying and navigation systems that use Global Positioning System (GPS) satellites, surveillance (optical and radar), and satellite tracking. Space weather influences on the Earth's weather and climate is still a developing topic. Little is known concerning the biological effects of space weather, especially regarding astronauts.This Institute could not be timelier. Space Weather, which has been defined as "conditions on the sun and in the solar wind, magnetosphere, ionosphere, and thermosphere that can influence the performance and reliability of space-and ground-based technological systems and can endanger human life", encompasses a broad range of phenomena impacting both space science and technology. The effects of Space Weather, while present throughout the solar cycle, gain particular prominence around the peak of the 11-year sunspot activity; the maximum of cycle 23 occurred in summer 2000.The fact that this ASI on Space Weather was held in Europe is particularly appropriate. European countries host a considerable repository of knowledge and world-class facilities in this field. Nevertheless, while Space Weather activities in c...

show abstract

Prediction of geomagnetic storms from solar wind data using Elman Recurrent Neural Networks

Cited by 120 publications

References 19 publications

The development of a regional geomagnetic daily variation model using neural networks

The development of a regional geomagnetic daily variation model using neural networks

Spatiotemporal activity of magnetic storms

Space Storms and Space Weather Hazards

Contact Info

Product

Resources

About