Recognition of Geomagnetic Storm Based on Neural Network Model Estimates of Dst Indices

Белов, А. В.; Гвишиани, А. Д.; Гетманов, В. Г.; Sololoviev, A. A.; Chinkin, V. E.; Yanke, V. G.; Yashin, I. I.

doi:10.1134/s106423072201004x

Cited by 3 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The NN architecture we have proposed in this paper, based on time series of matrix MH observations, exceeds in efficiency the approach described in [Belov et al, 2022;Getmanov et al, 2022b] and based on the formation of scalar time series of function values (3) from matrix MH observations. .…”

Section: Estimating Model Dst Indices and Gms Recognition Resultsmentioning

confidence: 99%

“…4. The experimental study has revealed that the proposed approach to the construction of DLNN, which is based on the use of time series consisting of MH observation matrices, is more effective than the approach described in [Belov et al, 2022;Getmanov et al, 2022a], which was based on the formation of scalar time series of average hourly MH observations from matrix MH observations. 5.…”

Section: Discussionmentioning

confidence: 98%

“…The former involves the formation of time series of S(T 0 n) from (3) from matrix MH observations. This solution [Belov et al, 2022;Getmanov et al, 2022a] can reduce computer requirements for NN implementation, but by decreasing the efficiency of GMS recognition. The second implies the direct use of time series of matrix MH observations, which requires high-performance computers capable of increasing the efficiency of GMS recognition for NN.…”

Section: Observations With the Uragan Muon Hodoscope And Gm Recogniti...mentioning

confidence: 99%

“…In [Belov et al, 2022;Getmanov et al, 2022a], an approach is described which consists in using scalar time series of MH observations and convolutional NN for analyzing GMS. Implementation of the proposed approach to GMS recognition using time series of matrix MH observations and deep learning NN aims to demonstrate its efficiency and possible future prospects.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Recognition of geomagnetic storms from time series of matrix observations with the muon hodoscope URAGAN using neural networks of deep learning

Getmanov,

Gvishiani,

Soloviev

et al. 2024

Solar-Terrestrial Physics

View full text Add to dashboard Cite

We solve the problem of recognizing geomagnetic storms from matrix time series of observations with the URAGAN muon hodoscope, using deep learning neural networks. A variant of the neural network software module is selected and its parameters are determined. Geomagnetic storms are recognized using binary classification procedures; a decision-making rule is formed. We estimate probabilities of correct and false recognitions. The recognition of geomagnetic storms is experimentally studied; for the assigned Dst threshold Yᴅ₀=–45 nT we obtain acceptable probabilities of correct and false recognitions, which amount to β=0.8212 and α=0.0047. We confirm the effectiveness and prospects of the proposed neural network approach.

show abstract

Section: Estimating Model Dst Indices and Gms Recognition Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 98%

Section: Observations With the Uragan Muon Hodoscope And Gm Recogniti...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations