A neural network Dst index model driven by input time histories of the solar wind–magnetosphere interaction

Revallo, Miloš; Valach, Fridrich; Hejda, Pavel; Bochníček, Josef

doi:10.1016/j.jastp.2014.01.011

Cited by 27 publications

(33 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned in section 1, various models have been developed to forecast the Dst index (mainly for 1 h ahead) [Iyemori et al, 1979;Burton et al, 1975;Stepanova et al, 2005;Sharifi et al, 2006a;Wei et al, 2007;Revallo et al, 2014]. These methods are up to 90% accurate but the time of alert (∼1 h) is too short to prevent damage caused by geomagnetic storms [Khabarova, 2007].…”

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

“…It is evident that geomagnetic index prediction has served as a testbed for a plethora of machine learning techniques for the last 20 years. This short review is necessarily incomplete (for more related or similar works, see; Barkhatov et al, ; Dolenko et al, ; Gavrishchaka & Ganguli, , ; Gleisner & Lundstedt, ; Hernandez et al, ; Mirmomeni et al, ; Pallocchia et al, ; Revallo et al, ; ; Srivastava, ; Stepanova et al, ; Stepanova & Pérez, ; Takalo & Timonen, ; Watanabe et al, , ). The reader might feel overwhelmed by the quantity and the diversity of published work.…”

Section: Review Of Machine Learning In Space Weathermentioning

confidence: 99%

The Challenge of Machine Learning in Space Weather: Nowcasting and Forecasting

2019

View full text Add to dashboard Cite

The numerous recent breakthroughs in machine learning make imperative to carefully ponder how the scientific community can benefit from a technology that, although not necessarily new, is today living its golden age. This Grand Challenge review paper is focused on the present and future role of machine learning in Space Weather. The purpose is twofold. On one hand, we will discuss previous works that use machine learning for Space Weather forecasting, focusing in particular on the few areas that have seen most activity: the forecasting of geomagnetic indices, of relativistic electrons at geosynchronous orbits, of solar flares occurrence, of coronal mass ejection propagation time, and of solar wind speed. On the other hand, this paper serves as a gentle introduction to the field of machine learning tailored to the Space Weather community and as a pointer to a number of open challenges that we believe the community should undertake in the next decade. The recurring themes throughout the review are the need to shift our forecasting paradigm to a probabilistic approach focused on the reliable assessment of uncertainties, and the combination of physics-based and machine learning approaches, known as gray box. Plain Language SummaryIn the last decade, machine learning has achieved unforeseen results in industrial applications. In particular, the combination of massive data sets and computing with specialized processors (graphics processing units, or GPUs) can perform as well or better than humans in tasks like image classification and game playing. Space weather is a discipline that lives between academia and industry, given the relevant physical effects on satellites and power grids in a variety of applications, and the field therefore stands to benefit from the advances made in industrial applications. Today, machine learning poses both a challenge and an opportunity for the space weather community. The challenge is that the current data science revolution has not been fully embraced, possibly because space physicists remain skeptical of the gains achievable with machine learning. If the community can master the relevant technical skills, they should be able to appreciate what is possible within a few years time and what is possible within a decade. The clearest opportunity lies in creating space weather forecasting models that can respond in real time and that are built on both physics predictions and on observed data.

show abstract

“…For example, both Lundstedt and Wintoft (1994) and Bala et al (2009) used a time delay neural network algorithm while Wu and Lundstedt (1997) adopted the Elman neural network approach. Revallo et al (2014) also used the Elman neural network method but instead of feeding the solar wind values straight into the code, they filtered them first with a time-integrative function. As seen in the metrics column of Table 1, most of these approaches are very good at reproducing indices.…”

Section: Dst and Sym-hmentioning

confidence: 99%

“…Observed frequency and forecast probability close to unity slope Bala et al (2009) and Reiff (2012, 2014) Artificial neural network scheme 6-h lead-time: R-0.80, RMSE = 10.3 nT Rastätter et al (2013) Comparison of 30 different models against Dst PE, log spectral distance, R, modeling yield, and timing error Tobiska et al (2013) Dst prediction using the Anemomilos solar flare-Dst correlation method Now-mean: R = 0.995; 3-day forecast: R = 0.6 Revallo et al (2014) Neural network algorithm R = 0.74, PE = 0.44 Zhang and Moldwin (2015) Probabilistic forecast of SYM-H based on previous 12 hr of Dst values Cumulative probability distributions for ICME, SIR, and Alfvenic SW inputs Balan et al (2017) Severe Dst prediction scheme based on DVxBz threshold Nearly 100% success for Dst < À200 nT storms Space Weather qualitatively compared against the observed values. Another approach is with a set of coupled codes, such as the Space Weather Modeling Framework (SWMF, see Toth et al, 2012), that includes a magnetohydrodynamic model for the global magnetospheric structure, an inner magnetospheric drift physics model, and an ionospheric electrodynamics solver.…”

Section: 1029/2018sw002067mentioning

confidence: 99%

Model Evaluation Guidelines for Geomagnetic Index Predictions

et al. 2018

View full text Add to dashboard Cite

Geomagnetic indices are convenient quantities that distill the complicated physics of some region or aspect of near‐Earth space into a single parameter. Most of the best‐known indices are calculated from ground‐based magnetometer data sets, such as Dst, SYM‐H, Kp, AE, AL, and PC. Many models have been created that predict the values of these indices, often using solar wind measurements upstream from Earth as the input variables to the calculation. This document reviews the current state of models that predict geomagnetic indices and the methods used to assess their ability to reproduce the target index time series. These existing methods are synthesized into a baseline collection of metrics for benchmarking a new or updated geomagnetic index prediction model. These methods fall into two categories: (1) fit performance metrics such as root‐mean‐square error and mean absolute error that are applied to a time series comparison of model output and observations and (2) event detection performance metrics such as Heidke Skill Score and probability of detection that are derived from a contingency table that compares model and observation values exceeding (or not) a threshold value. A few examples of codes being used with this set of metrics are presented, and other aspects of metrics assessment best practices, limitations, and uncertainties are discussed, including several caveats to consider when using geomagnetic indices.

show abstract

A neural network Dst index model driven by input time histories of the solar wind–magnetosphere interaction

Cited by 27 publications

References 28 publications

Forecasting the Dst index using a swarm‐optimized neural network

Forecasting the Dst index using a swarm‐optimized neural network

The Challenge of Machine Learning in Space Weather: Nowcasting and Forecasting

Model Evaluation Guidelines for Geomagnetic Index Predictions

Contact Info

Product

Resources

About