High solar activity predictions through an artificial neural network

M. G. Orozco-Del-Castillo; J. C. Ortiz-Alemán; C. Couder-Castañeda; J. J. Hernández-Gómez; A. Solís-Santomé

doi:10.1142/S0129183117500759

High solar activity predictions through an artificial neural network

M. G. Orozco-Del-Castillo, J. C. Ortiz-Alemán, C. Couder-Castañeda, J. J. Hernández-Gómez, A. Solís-Santomé

Centro de Desarrollo Aeroespacial (CDA)

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

The effects of high-energy particles coming from the Sun on human health as well as in the integrity of outer space electronics make the prediction of periods of high solar activity (HSA) a task of significant importance. Since periodicities in solar indexes have been identified, long-term predictions can be achieved. In this paper, we present a method based on an artificial neural network to find a pattern in some harmonics which represent such periodicities. We used data from 1973 to 2010 to train the neural network, and different historical data for its validation. We also used the neural network along with a statistical analysis of its performance with known data to predict periods of HSA with different confidence intervals according to the three-sigma rule associated with solar cycles 24-26, which we found to occur before 2040.

Original language	English
Article number	1750075
Journal	International Journal of Modern Physics C
Volume	28
Issue number	6
DOIs	https://doi.org/10.1142/S0129183117500759
State	Published - 1 Jun 2017

Keywords

Artificial neural network (ANN)
ground level enhancement (GLE)
high solar activity (HSA)
pattern recognition
solar cycle prediction

Access to Document

10.1142/S0129183117500759

Cite this

@article{25703e6f756a43c38ba2067e99bcde3a,

title = "High solar activity predictions through an artificial neural network",

abstract = "The effects of high-energy particles coming from the Sun on human health as well as in the integrity of outer space electronics make the prediction of periods of high solar activity (HSA) a task of significant importance. Since periodicities in solar indexes have been identified, long-term predictions can be achieved. In this paper, we present a method based on an artificial neural network to find a pattern in some harmonics which represent such periodicities. We used data from 1973 to 2010 to train the neural network, and different historical data for its validation. We also used the neural network along with a statistical analysis of its performance with known data to predict periods of HSA with different confidence intervals according to the three-sigma rule associated with solar cycles 24-26, which we found to occur before 2040.",

keywords = "Artificial neural network (ANN), ground level enhancement (GLE), high solar activity (HSA), pattern recognition, solar cycle prediction",

author = "Orozco-Del-Castillo, {M. G.} and Ortiz-Alem{\'a}n, {J. C.} and C. Couder-Casta{\~n}eda and Hern{\'a}ndez-G{\'o}mez, {J. J.} and A. Sol{\'i}s-Santom{\'e}",

note = "Publisher Copyright: {\textcopyright} 2017 World Scientific Publishing Company.",

year = "2017",

month = jun,

day = "1",

doi = "10.1142/S0129183117500759",

language = "Ingl{\'e}s",

volume = "28",

journal = "International Journal of Modern Physics C",

issn = "0129-1831",

number = "6",

}

TY - JOUR

T1 - High solar activity predictions through an artificial neural network

AU - Orozco-Del-Castillo, M. G.

AU - Ortiz-Alemán, J. C.

AU - Couder-Castañeda, C.

AU - Hernández-Gómez, J. J.

AU - Solís-Santomé, A.

PY - 2017/6/1

Y1 - 2017/6/1

N2 - The effects of high-energy particles coming from the Sun on human health as well as in the integrity of outer space electronics make the prediction of periods of high solar activity (HSA) a task of significant importance. Since periodicities in solar indexes have been identified, long-term predictions can be achieved. In this paper, we present a method based on an artificial neural network to find a pattern in some harmonics which represent such periodicities. We used data from 1973 to 2010 to train the neural network, and different historical data for its validation. We also used the neural network along with a statistical analysis of its performance with known data to predict periods of HSA with different confidence intervals according to the three-sigma rule associated with solar cycles 24-26, which we found to occur before 2040.

AB - The effects of high-energy particles coming from the Sun on human health as well as in the integrity of outer space electronics make the prediction of periods of high solar activity (HSA) a task of significant importance. Since periodicities in solar indexes have been identified, long-term predictions can be achieved. In this paper, we present a method based on an artificial neural network to find a pattern in some harmonics which represent such periodicities. We used data from 1973 to 2010 to train the neural network, and different historical data for its validation. We also used the neural network along with a statistical analysis of its performance with known data to predict periods of HSA with different confidence intervals according to the three-sigma rule associated with solar cycles 24-26, which we found to occur before 2040.

KW - Artificial neural network (ANN)

KW - ground level enhancement (GLE)

KW - high solar activity (HSA)

KW - pattern recognition

KW - solar cycle prediction

UR - http://www.scopus.com/inward/record.url?scp=85021081736&partnerID=8YFLogxK

U2 - 10.1142/S0129183117500759

DO - 10.1142/S0129183117500759

M3 - Artículo

SN - 0129-1831

VL - 28

JO - International Journal of Modern Physics C

JF - International Journal of Modern Physics C

IS - 6

M1 - 1750075

ER -

High solar activity predictions through an artificial neural network

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this