Real time Kp predictions from solar wind data using neural networks

Boberg, Fredrik; Wintoft, Peter; Lundstedt, H.

doi:10.1016/s1464-1917(00)00016-7

Cited by 70 publications

(95 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At present, we investigate the use of a purely observation-based analogue ensemble (AnEn) for statistical solar-wind forecasting, rather than in conjunction with a model. The concept of analogue or "similar day" forecasting has previously been investigated for specific space-weather uses, with pattern matching within discrete solar-wind events, specifically magnetic clouds (Chen, Cargill, and Palmadesso, 1997) and high-speed streams (Bussy-Virat and Ridley, 2016). More recently, Riley et al (2017) have demonstrated the potential of analogue forecasts through simple pattern matching for various solar-wind conditions.…”

Section: Introductionmentioning

confidence: 99%

“…Considering solar-wind parameters independently, and fixing the number of analogue periods at 50 and the period over which they are determined at 24 hours, they showed significant forecast skill for a few days lead time in solar-wind speed, density, and temperature, but only a few hours for the out-of-ecliptic magnetic-field component. Nonlinear approaches, particularly neural networks, which implicitly involve analogue-forecasting ideas, have been widely used for predicting Kp, one of the most widely used indices of geomagnetic disturbance (Detman and Joselyn, 1999;Boberg, Wintoft, and Lundstedt, 2000;Wing et al, 2005). These are typically used to assess the recent solar-wind conditions and give Kp forecasts with a lead time of about three hours (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Probabilistic Solar Wind and Geomagnetic Forecasting Using an Analogue Ensemble or “Similar Day” Approach

2017

View full text Add to dashboard Cite

Effective space-weather prediction and mitigation requires accurate forecasting of near-Earth solar-wind conditions. Numerical magnetohydrodynamic models of the solar wind, driven by remote solar observations, are gaining skill at forecasting the large-scale solar-wind features that give rise to near-Earth variations over days and weeks. There remains a need for accurate short-term (hours to days) solar-wind forecasts, however. In this study we investigate the analogue ensemble (AnEn), or "similar day", approach that was developed for atmospheric weather forecasting. The central premise of the AnEn is that past variations that are analogous or similar to current conditions can be used to provide a good estimate of future variations. By considering an ensemble of past analogues, the AnEn forecast is inherently probabilistic and provides a measure of the forecast uncertainty. We show that forecasts of solar-wind speed can be improved by considering both speed and density when determining past analogues, whereas forecasts of the out-of-ecliptic magnetic field [B N ] are improved by also considering the in-ecliptic magnetic-field components. In general, the best forecasts are found by considering only the previous 6 -12 hours of observations. Using these parameters, the AnEn provides a valuable probabilistic forecast for solar-wind speed, density, and in-ecliptic magnetic field over lead times from a few hours to around four days. For B N , which is central to space-weather disturbance, the AnEn only provides a valuable forecast out to around six to seven hours. As the inherent predictability of this parameter is low, this is still likely a marked improvement over other forecast methods. We also investigate the use of the AnEn in forecasting geomagnetic indices Dst and Kp. The AnEn provides a valuable probabilistic forecast of both indices out to around four days. We outline a number of future improvements to AnEn forecasts of near-Earth solar-wind and geomagnetic conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Probabilistic Solar Wind and Geomagnetic Forecasting Using an Analogue Ensemble or “Similar Day” Approach

2017

View full text Add to dashboard Cite

show abstract

“…Therefore, new opportunities to improve the scientific knowledge on the triggers of geomagnetic disturbances arise, leading to develop new forecasting tools based on solar observations. These solar-based tools (see e.g., Kim et al 2005;Gleisner & Watermann 2006a, 2006bRobbrecht & Berghmans 2006) are able to forecast in advance -one to three days depending on the solar wind speed -to those prediction schemes based on the knowledge of interplanetary parameters (see e.g., Boberg et al 2000;Gleisner & Lundstedt, 2001a, 2001bLundstedt et al 2002aLundstedt et al , 2002b. For practical applications the first can serve as a preliminary warning, which is then confirmed or cancelled by the latter.…”

Section: Response Of the Terrestrial Environment To Solar Activitymentioning

confidence: 99%

Geomagnetic response to solar and interplanetary disturbances

Sáiz

Cerrato

Cid

et al. 2013

J. Space Weather Space Clim.

View full text Add to dashboard Cite

The space weather discipline involves different physical scenarios, which are characterised by very different physical conditions, ranging from the Sun to the terrestrial magnetosphere and ionosphere. Thanks to the great modelling effort made during the last years, a few Sun-to-ionosphere/thermosphere physics-based numerical codes have been developed. However, the success of the prediction is still far from achieving the desirable results and much more progress is needed. Some aspects involved in this progress concern both the technical progress (developing and validating tools to forecast, selecting the optimal parameters as inputs for the tools, improving accuracy in prediction with short lead time, etc.) and the scientific development, i.e., deeper understanding of the energy transfer process from the solar wind to the coupled magnetosphere-ionosphere-thermosphere system. The purpose of this paper is to collect the most relevant results related to these topics obtained during the COST Action ES0803. In an end-to-end forecasting scheme that uses an artificial neural network, we show that the forecasting results improve when gathering certain parameters, such as X-ray solar flares, Type II and/or Type IV radio emission and solar energetic particles enhancements as inputs for the algorithm. Regarding the solar wind-magnetosphere-ionosphere interaction topic, the geomagnetic responses at high and low latitudes are considered separately. At low latitudes, we present new insights into temporal evolution of the ring current, as seen by Burton's equation, in both main and recovery phases of the storm. At high latitudes, the PCC index appears as an achievement in modelling the coupling between the upper atmosphere and the solar wind, with a great potential for forecasting purposes. We also address the important role of small-scale field-aligned currents in Joule heating of the ionosphere even under non-disturbed conditions. Our scientific results in the framework of the COST Action ES0803 cover the topics from the short-term solar-activity evolution, i.e., space weather, to the long-term evolution of relevant solar/heliospheric/magnetospheric parameters, i.e., space climate. On the timescales of the Hale and Gleissberg cycles (22-and 88-year cycle respectively) we can highlight that the trend of solar, heliospheric and geomagnetic parameters shows the solar origin of the widely discussed increase in geomagnetic activity in the last century.

show abstract

“…Takalo and Timonen, 1997;Gavrishchaka and Ganguli, 2001;Boberg et al, 2000;Lundstedt et al, 2002 Fig. 8 caption).…”

Section: Comparisons With Existing Geomagnetic Response Modelsmentioning

confidence: 99%

Specification of multiple geomagnetic responses to variable solar wind and IMF input

Fung

Shao²

2008

Ann. Geophys.

View full text Add to dashboard Cite

Abstract. This paper shows that the state of the magnetosphere, resulting from continuous but variable forcing of the solar wind and the interplanetary magnetic field (IMF), can be empirically specified by a magnetospheric state vector , consisting of a set of hourly-averaged magnetospheric driver and response parameters. It is demonstrated that there exists a correspondence between the magnetospheric driver and multiple geomagnetic response parameters. This parameter correspondence allows different magnetopsheric states to be specified by means of a look-up table, provided that the relative time lags between various driver (e.g. V sw , IMF) and response parameters (e.g. K p , D st , and AE) are taken into account. Using the magnetospheric state specifications, multiscale geomagnetic responses can then be simultaneously prescribed statistically from their corresponding driver parameters. Magnetospheric state specifications have been determined by using magnetospheric state parameter data taken in . Their validities have been tested by specifying the multi-geomagnetic responses over three representative intervals: (1) a magnetic cloud event, (2) a period of multiple storms, and (3) the years of 2001 and 2002. For all the intervals, we have found good correlation (with r>0.75) between the prescribed and observed geomagnetic indices at hourly resolution, and the magnetospheric state specifications are thus validated.

show abstract

Real time Kp predictions from solar wind data using neural networks

Cited by 70 publications

References 10 publications

Probabilistic Solar Wind and Geomagnetic Forecasting Using an Analogue Ensemble or “Similar Day” Approach

Probabilistic Solar Wind and Geomagnetic Forecasting Using an Analogue Ensemble or “Similar Day” Approach

Geomagnetic response to solar and interplanetary disturbances

Specification of multiple geomagnetic responses to variable solar wind and IMF input

Contact Info

Product

Resources

About