Relevance vector machines as a tool for forecasting geomagnetic storms during years 1996–2007

Andriyas, Tushar; Andriyas, Sanyogita

doi:10.1016/j.jastp.2015.02.005

Cited by 17 publications

(9 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A direct comparison between the results obtained by the proposed methods and other methods reported in the literature (as presented in Table ) is complicated due to differences in databases and methodologies used in each study (Andriyas & Andriyas, ; Andrejková & Levický, ; Bala & Reiff, ; Barkhatov et al, ; Gleisner et al, ; Gruet et al, ; Jankovičová et al, ; Kugblenu et al, ; Lazzús et al, ; Lethy et al, ; Lotfi & Akbarzadeh‐T., ; Lundstedt & Wintoft, ; Lundstedt et al, ; Munsami, ; Ouarbya & Mirikitani, ; Ouarbya et al, ; Pallocchia et al, ; Revallo et al, ; Sharifi et al, ; Sharifi et al, ; Singh & Singh, ; Stepanova et al, ; Stepanova & Pérez, ; Stepanova et al, ; Vega‐Jorquera et al, ; Vörös & Jankovičová, ; Watanabe et al, ; ; Wei et al, ; Wu & Lundstedt, ; ; Xue & Gong, ). In addition, the ANN configurations contain deep variation such as the time steps of ahead prediction (i.e., output), input parameters, and the number of neurons in the hidden layer (see Table ).…”

Section: Discussionmentioning

confidence: 99%

“…This test compares six Dst forecast methods for 1 hour ahead (called, B ; Burton et al, ; FL ; Fenrich & Luhmann, ; OM ; O'Brien & McPherron, ; TL ; Temerin & Li, ; W ; Wang et al, ; and NM ; Boynton et al, ) employing 63 selected intense storms ( Dst <−100nT) between 1998 and 2006, and 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 this we added four other methods to forecast the Dst index 1‐h ahead, such as relevance vector machine (RVM) (Andriyas & Andriyas, ), gaussian process auto‐regressive (GP‐AR) (Chandorkar et al, ; ), gaussian process auto‐regressive with exogenous inputs (GP‐ARX) (Chandorkar et al, ; ), and persistence P. Figure presents an objective and quantitative comparison of these methods with our proposed method. Here, the selected skill scores provided a good measure for the performance assessment of each method, as is suggested by Rastätter et al ().…”

Section: Discussionmentioning

confidence: 99%

“…Comparison between the proposed ANN+PSO, ANN+GA, and ANN+PSO+GA methods and others available for forecasting the D s t index 1 h ahead (such as B Burton et al, ; FL ; Fenrich & Luhmann, ; OM ; O'Brien & McPherron, ; TL ; Temerin & Li, ; W ; Wang et al, ; NM ; Boynton et al, ; RVM ; Andriyas & Andriyas, ; GP‐AR ; Chandorkar et al, , ; GP‐ARX ; , , ; persistence P). ( a ) correlation coefficient R; ( b ) root mean square error RMSE; ( c ) difference in the minimum value of forecasted and measured Dst |ΔD s t m i n |; and ( d ) absolute timing difference between observed and measured Dst |Δ t D s t |.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Dst Index Forecast Based on Ground‐Level Data Aided by Bio‐Inspired Algorithms

et al. 2019

View full text Add to dashboard Cite

In this study, different hybridized techniques that combine an artificial neural network (ANN) with bio‐inspired optimization algorithms such as particle swarm optimization (PSO), genetic algorithm (GA), and a hybridized PSO+GA were applied to update the ANN connection weights and so forecast the disturbance storm time (Dst) index. The past values of Dst index time series were used as input parameters to forecast its variation from 1 to 6 hours ahead. The database collected considers 233,760 hourly data from 01 January 1990 to 31 August 2016, containing storms and quiet period, grouped into three data sets: learning set (116,880 hourly data points), validation set (58,440 data points), and testing set (58,440 data points). Several ANN configurations were studied and optimized during the training process by evaluating the root mean square error (RMSE) and the correlation coefficient (R). An analysis of the predictive capability of each method was made year per year, and according to the levels of the geomagnetic storm. Also, an additional test was applied to the proposed method using 17 intense geomagnetic storms reported during solar cycle 24, including the St. Patrick's Day storm of 2015. Results show that the hybridized ANN+PSO method can forecast the Dst index quite accurately from 1 to 3 h in advance (with RMSE≤5 nT and R≥0.9), while the ANN+PSO+GA method can forecast the Dst index quite accurately from 4 to 6 h ahead (RMSE≤7 nT and R≥0.8)

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Dst Index Forecast Based on Ground‐Level Data Aided by Bio‐Inspired Algorithms

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Supplemental Table S1 provides a succinct review of the application of NNs to the forecasting of Dst (Andriyas & Andriyas, 2015;Bala & Reiff, 2012;Gleisner, Lundstedt, & Wintoft, 1996;Jankovičová, Dolinskỳ, Valach, & Vörös, 2002;Kugblenu, Taguchi, & Okuzawa, 1999;Lazzús, Vega, Rojas, & Salfate, 2017;Munsami, 2000;Pallocchia, Amata, Consolini, Marcucci, & Bertello, 2006;Revallo, Valach, Hejda, & Bochníček, 2014;Sharifie, Lucas, & Araabi, 2006;Stepanova, Antonova, & Troshichev, 2005;Stepanova & Pérez, 2000;Wei, Zhu, Billings, & Balikhin, 2007;Wu & Lundstedt, 1996. These studies have applied a variety of architectures and data sources, but in generating forecasts for Dst, most have used the basic solar wind parameter measurements as well as prior values of Dst.…”

Section: Accepted Articlementioning

confidence: 99%

Probabilistic Geomagnetic Storm Forecasting via Deep Learning

Tasistro-Hart

Grayver

Kuvshinov

2021

Preprint

View full text Add to dashboard Cite

<p>By causing time variation in Earth's external magnetic field, geomagnetic storms can induce damaging currents in ground-based conducting infrastructure, such as power and communication lines.&#160; The physical link between solar activity and Earth's magnetosphere, while complicated, provides the basis for attempts to forecast geomagnetic storms. Fortunately, we have abundant observational data of both the solar disk and solar wind, which are ameable to the application of data-hungry neural networks to the forecasting problem. To date, almost all neural networks trained for geomagnetic storm forecasting have utilized solar wind observations from the Earth-Sun first Lagrangian point (L1) or closer and have generated deterministic output without uncertainty estimates. Furthermore, existing models generate forecasts for indices that are also sensitive to induced internal magnetic fields, complicating the forecasting problem with another layer of non-linearity. In this work, we present neural networks trained on observations from both the solar disk and the L1 point. Our architecture generates reliable probabilistic forecasts over Est, the external component of the disturbance storm time index, showing that neural networks can learn measures of confidence in their output.&#160;</p>

show abstract

“…All rights reserved. Supplemental Table S1 provides a succinct review of the application of NNs to the forecasting of Dst (Andriyas & Andriyas, 2015;Bala & Reiff, 2012;Gleisner, Lundstedt, & Wintoft, 1996;Jankovičová, Dolinskỳ, Valach, & Vörös, 2002;Kugblenu, Taguchi, & Okuzawa, 1999;Lazzús, Vega, Rojas, & Salfate, 2017;Munsami, 2000;Pallocchia, Amata, Consolini, Marcucci, & Bertello, 2006;Revallo, Valach, Hejda, & Bochníček, 2014;Sharifie, Lucas, & Araabi, 2006;Stepanova, Antonova, & Troshichev, 2005;Stepanova & Pérez, 2000;Wei, Zhu, Billings, & Balikhin, 2007;Wu & Lundstedt, 1996. These studies have applied a variety of architectures and data sources, but in generating forecasts for Dst, most have used the basic solar wind parameter measurements as well as prior values of Dst.…”

Section: Accepted Articlementioning

confidence: 99%