Articles | Volume 40, issue 1
https://doi.org/10.5194/angeo-40-11-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/angeo-40-11-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Echo state network model for analyzing solar-wind effects on the AU and AL indices
The Institute of Statistical Mathematics, Tachikawa,
190–8562, Japan
Center for Data Assimilation Research and Applications,
Joint Support Center for Data Science Research, Tachikawa, Japan
School of Multidisciplinary Science, SOKENDAI, Hayama, Japan
Ryuho Kataoka
National Institute of Polar Research, Tachikawa, Japan
School of Multidisciplinary Science, SOKENDAI, Hayama, Japan
Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan
Related authors
Shin'ya Nakano, Ryuho Kataoka, Masahito Nosé, and Jesper W. Gjerloev
Ann. Geophys., 41, 529–539, https://doi.org/10.5194/angeo-41-529-2023, https://doi.org/10.5194/angeo-41-529-2023, 2023
Short summary
Short summary
Substorms are a phenomenon in the magnetosphere–ionosphere system, which are characterised by brightening of an auroral arc and enhancement of electric currents in the polar ionosphere. Since substorms are difficult to predict, this study treats a substorm occurrence as a stochastic phenomenon and represents the substorm occurrence rate with a machine learning model. We then analyse the response of substorm activity to solar wind conditions by feeding synthetic solar wind data into the model.
Shin'ya Nakano
Nonlin. Processes Geophys., 28, 93–109, https://doi.org/10.5194/npg-28-93-2021, https://doi.org/10.5194/npg-28-93-2021, 2021
Short summary
Short summary
The ensemble-based variational method is a method for solving nonlinear data assimilation problems by using an ensemble of multiple simulation results. Although this method is derived based on a linear approximation, highly uncertain problems, in which system nonlinearity is significant, can also be solved by applying this method iteratively. This paper reformulated this iterative algorithm to analyze its behavior in high-dimensional nonlinear problems and discuss the convergence.
Shin'ya Nakano, Kazue Suzuki, Kenji Kawamura, Frédéric Parrenin, and Tomoyuki Higuchi
Nonlin. Processes Geophys., 23, 31–44, https://doi.org/10.5194/npg-23-31-2016, https://doi.org/10.5194/npg-23-31-2016, 2016
Short summary
Short summary
This paper proposes a technique for dating an ice core. The proposed technique employs a hybrid method combining the sequential Monte Carlo method and the Markov chain Monte Carlo method, which is referred to as the particle Markov chain Monte Carlo method. The sequential Monte Carlo method, which is also known as the particle filter, is widely used for nonlinear time-series analysis. This paper demonstrates the usefulness of the approach in time-series analysis for dating an ice core.
Shin'ya Nakano, Ryuho Kataoka, Masahito Nosé, and Jesper W. Gjerloev
Ann. Geophys., 41, 529–539, https://doi.org/10.5194/angeo-41-529-2023, https://doi.org/10.5194/angeo-41-529-2023, 2023
Short summary
Short summary
Substorms are a phenomenon in the magnetosphere–ionosphere system, which are characterised by brightening of an auroral arc and enhancement of electric currents in the polar ionosphere. Since substorms are difficult to predict, this study treats a substorm occurrence as a stochastic phenomenon and represents the substorm occurrence rate with a machine learning model. We then analyse the response of substorm activity to solar wind conditions by feeding synthetic solar wind data into the model.
Shin'ya Nakano
Nonlin. Processes Geophys., 28, 93–109, https://doi.org/10.5194/npg-28-93-2021, https://doi.org/10.5194/npg-28-93-2021, 2021
Short summary
Short summary
The ensemble-based variational method is a method for solving nonlinear data assimilation problems by using an ensemble of multiple simulation results. Although this method is derived based on a linear approximation, highly uncertain problems, in which system nonlinearity is significant, can also be solved by applying this method iteratively. This paper reformulated this iterative algorithm to analyze its behavior in high-dimensional nonlinear problems and discuss the convergence.
Hiroko Miyahara, Ryuho Kataoka, Takehiko Mikami, Masumi Zaiki, Junpei Hirano, Minoru Yoshimura, Yasuyuki Aono, and Kiyomi Iwahashi
Ann. Geophys., 36, 633–640, https://doi.org/10.5194/angeo-36-633-2018, https://doi.org/10.5194/angeo-36-633-2018, 2018
Short summary
Short summary
Old diaries kept in Japan tell us a surprising fact. The 27-day solar rotational period in thunder and lightning activities had been persistent for the past 300 years. The intensity is found to be more prominent as solar activity increases. The physical mechanism of the Sun–Climate connection is yet uncertain, an important link surely exists between the solar activity and terrestrial climate even at a meteorological timescale.
Hiroko Miyahara, Yasuyuki Aono, and Ryuho Kataoka
Ann. Geophys., 35, 1195–1200, https://doi.org/10.5194/angeo-35-1195-2017, https://doi.org/10.5194/angeo-35-1195-2017, 2017
Short summary
Short summary
Solar activity and climate show correlations over a wide range of timescales. It is important to understand the behavior of the 27-day solar rotational period in lightning activities because it provides an opportunity to understand how the sun influences weather and climate. We analyzed lightning data extracted from diaries written in Kyoto, Japan from the mid-17th to the mid-18th century. Lightning shows the signal of the 27-day period; however, it disappeared during the Maunder Minimum.
Hiroko Miyahara, Chika Higuchi, Toshio Terasawa, Ryuho Kataoka, Mitsuteru Sato, and Yukihiro Takahashi
Ann. Geophys., 35, 583–588, https://doi.org/10.5194/angeo-35-583-2017, https://doi.org/10.5194/angeo-35-583-2017, 2017
Short summary
Short summary
Detailed analyses of the 27-day solar rotational period in cloud and lightning activities may help in untangling the process of solar influence on weather and climate. We analyzed the lightning data in Japan for AD 1989–2015 and found that the 27-day solar rotational period is seen in wide-area lightning activity. The signal was stronger at the maxima of solar decadal cycles. It was also found that the signal of the 27-day period migrates from the southwest to the northeast in Japan.
Shin'ya Nakano, Kazue Suzuki, Kenji Kawamura, Frédéric Parrenin, and Tomoyuki Higuchi
Nonlin. Processes Geophys., 23, 31–44, https://doi.org/10.5194/npg-23-31-2016, https://doi.org/10.5194/npg-23-31-2016, 2016
Short summary
Short summary
This paper proposes a technique for dating an ice core. The proposed technique employs a hybrid method combining the sequential Monte Carlo method and the Markov chain Monte Carlo method, which is referred to as the particle Markov chain Monte Carlo method. The sequential Monte Carlo method, which is also known as the particle filter, is widely used for nonlinear time-series analysis. This paper demonstrates the usefulness of the approach in time-series analysis for dating an ice core.
R. Kataoka, Y. Fukuda, H. A. Uchida, H. Yamada, Y. Miyoshi, Y. Ebihara, H. Dahlgren, and D. Hampton
Ann. Geophys., 34, 41–44, https://doi.org/10.5194/angeo-34-41-2016, https://doi.org/10.5194/angeo-34-41-2016, 2016
Short summary
Short summary
Stereoscopy of aurora was performed at the record fast sampling rate of 100 fps to measure the emission altitude of rapidly varying fine-scale structures. The new method unveiled that very different types of aurora appear in the same direction at different altitudes.
R. Kataoka, Y. Nakagawa, and T. Sato
Ann. Geophys., 33, 75–78, https://doi.org/10.5194/angeo-33-75-2015, https://doi.org/10.5194/angeo-33-75-2015, 2015
Short summary
Short summary
Using a new air-shower simulation driven by the proton flux data obtained from GOES satellites, we show the possibility of significant enhancement of the effective dose rate of up to 4.5 µSv/hr at a conventional flight altitude of 12 km during the largest solar proton event that did not cause a ground-level enhancement. As a result, a new GOES-driven model is proposed to give an estimate of the contribution from the isotropic component of the radiation dose in the stratosphere.
H. Fujiwara, S. Nozawa, Y. Ogawa, R. Kataoka, Y. Miyoshi, H. Jin, and H. Shinagawa
Ann. Geophys., 32, 831–839, https://doi.org/10.5194/angeo-32-831-2014, https://doi.org/10.5194/angeo-32-831-2014, 2014
R. Kataoka, Y. Miyoshi, K. Shigematsu, D. Hampton, Y. Mori, T. Kubo, A. Yamashita, M. Tanaka, T. Takahei, T. Nakai, H. Miyahara, and K. Shiokawa
Ann. Geophys., 31, 1543–1548, https://doi.org/10.5194/angeo-31-1543-2013, https://doi.org/10.5194/angeo-31-1543-2013, 2013
Related subject area
Subject: Magnetosphere & space plasma physics | Keywords: Storms and substorms
Probabilistic modelling of substorm occurrences with an echo state network
The record of the magnetic storm on 15 May 1921 in Stará Ďala (present-day Hurbanovo) and its compliance with the global picture of this extreme event
Seasonal features of geomagnetic activity: a study on the solar activity dependence
Polar substorm on 7 December 2015: preonset phenomena and features of auroral breakup
Response of the low- to mid-latitude ionosphere to the geomagnetic storm of September 2017
Influence of the Earth's ring current strength on Størmer's allowed and forbidden regions of charged particle motion
Dynamics of a geomagnetic storm on 7–10 September 2015 as observed by TWINS and simulated by CIMI
Shin'ya Nakano, Ryuho Kataoka, Masahito Nosé, and Jesper W. Gjerloev
Ann. Geophys., 41, 529–539, https://doi.org/10.5194/angeo-41-529-2023, https://doi.org/10.5194/angeo-41-529-2023, 2023
Short summary
Short summary
Substorms are a phenomenon in the magnetosphere–ionosphere system, which are characterised by brightening of an auroral arc and enhancement of electric currents in the polar ionosphere. Since substorms are difficult to predict, this study treats a substorm occurrence as a stochastic phenomenon and represents the substorm occurrence rate with a machine learning model. We then analyse the response of substorm activity to solar wind conditions by feeding synthetic solar wind data into the model.
Eduard Koči and Fridrich Valach
Ann. Geophys., 41, 355–368, https://doi.org/10.5194/angeo-41-355-2023, https://doi.org/10.5194/angeo-41-355-2023, 2023
Short summary
Short summary
We dealt with the most intense magnetic storm of the 20th century, which took place on 13–15 May 1921. It was also observed at Stará Ďala (present-day Hurbanovo). However, the record was not complete. We estimated the missing sensitivity scale values and presented the resulting digitized Stará Ďala’s data for 13–15 May 1921. The data were compared with the records from other observatories. The analysis suggests that the auroral oval got close to Stará Ďala in the morning hours on 15 May 1921.
Adriane Marques de Souza Franco, Rajkumar Hajra, Ezequiel Echer, and Mauricio José Alves Bolzan
Ann. Geophys., 39, 929–943, https://doi.org/10.5194/angeo-39-929-2021, https://doi.org/10.5194/angeo-39-929-2021, 2021
Short summary
Short summary
We used up-to-date substorms, HILDCAAs and geomagnetic storms of varying intensity along with all available geomagnetic indices during the space exploration era to explore the seasonal features of the geomagnetic activity and their drivers. As substorms, HILDCAAs and magnetic storms of varying intensity have varying solar/interplanetary drivers, such a study is important for acomplete understanding of the seasonal features of the geomagnetic response to the solar/interplanetary events.
Vladimir V. Safargaleev, Alexander E. Kozlovsky, and Valery M. Mitrofanov
Ann. Geophys., 38, 901–918, https://doi.org/10.5194/angeo-38-901-2020, https://doi.org/10.5194/angeo-38-901-2020, 2020
Short summary
Short summary
Comprehensive analysis of a moderate substorm was performed using optical observations inside the auroral oval and in the polar cap, combined with data from satellites, radars, and ground magnetometers. The onset took place near the poleward boundary of the auroral oval that is not typical for classical substorms. The data fit to the near-tail current disruption scenario of the substorm onset. The role of the 15 min oscillations in the IMF Bz component in the substorm initiation is discussed.
Nadia Imtiaz, Waqar Younas, and Majid Khan
Ann. Geophys., 38, 359–372, https://doi.org/10.5194/angeo-38-359-2020, https://doi.org/10.5194/angeo-38-359-2020, 2020
Short summary
Short summary
We study the impact of the geomagnetic storm of 7–9 September 2017 on the low- to mid-latitude ionosphere. The study is based on the analysis of data from the Global Positioning System (GPS) stations and magnetic observatories located at different longitudinal sectors corresponding to the Pacific, Asia, Africa and the Americas during the period 4–14 September 2017. The GPS data are used to derive the global, regional and vertical total electron content (vTEC) in the four selected regions.
Alexander S. Lavrukhin, Igor I. Alexeev, and Ilya V. Tyutin
Ann. Geophys., 37, 535–547, https://doi.org/10.5194/angeo-37-535-2019, https://doi.org/10.5194/angeo-37-535-2019, 2019
Short summary
Short summary
This paper concerns the question of whether the maximum Earth ring current strength exists and at which moment the ring current can start to break up, thus making a new mechanism of the ring current decrease during the magnetic storm. We study this effect using the Stormer theory of particle motion. After transition of critical strength, Stormer's inner trapping region opens up and the ring current charged particles get the opportunity to leave it, thus decreasing the current strength.
Joseph D. Perez, James Edmond, Shannon Hill, Hanyun Xu, Natalia Buzulukova, Mei-Ching Fok, Jerry Goldstein, David J. McComas, and Phil Valek
Ann. Geophys., 36, 1439–1456, https://doi.org/10.5194/angeo-36-1439-2018, https://doi.org/10.5194/angeo-36-1439-2018, 2018
Short summary
Short summary
Pressure and anisotropy profiles from trapped ions in the ring current as observed from energetic neutral atom images are compared to numerical simulations for the first time. The results show evidence for short time and spatially localized injections from the plasma sheet.
Cited articles
Allen, J. H. and Kroehl, H. W.: Spatial and temporal distributions of magnetic
effects of auroral electrojets as derived from AE indices, J. Geophys.
Res., 80, 3667–3677, 1975. a
Amariutei, O. A. and Ganushkina, N. Y.: On the prediction of the auroral westward electrojet index, Ann. Geophys., 30, 841–847, https://doi.org/10.5194/angeo-30-841-2012, 2012. a
Arnoldy, R. L.: Signature in the interplanetary medium for substorms, J.
Geophys. Res., 76, 5189–5201, 1971. a
Bala, R. and Reiff, P.: Improvements in short-term forecasting of geomagnetic
activity, Space Weather, 10, S06001, https://doi.org/10.1029/2012SW000779, 2012. a
Blunier, S., Toledo, B., Rogan, J., and Valdivia, J. A.: A nonlinear system
science approach to find the robust solar wind drivers of the multivariate
magnetosphere, Space Weather, 19, e2020SW002634,
https://doi.org/10.1029/2020SW002634, 2021. a, b, c, d
Boudouridis, A., Zesta, E., Lyons, L. R., Anderson, P. C., and Ridley, A. J.:
Temporal evolution of the transpolar potential after a sharp enhancement in
solar wind dynamic pressure, Geophys. Res. Lett., 35, L02101,
https://doi.org/10.1029/2007GL031766, 2008. a
Chattopadhyay, A., Hassanzadeh, P., and Subramanian, D.: Data-driven predictions of a multiscale Lorenz 96 chaotic system using machine-learning methods: reservoir computing, artificial neural network, and long short-term memory network, Nonlin. Processes Geophys., 27, 373–389, https://doi.org/10.5194/npg-27-373-2020, 2020. a
Chen, J. and Sharma, S.: Modeling and prediction of the magnetospheric
dynamics during intense geospace storms, J. Geophys. Res., 111, A4209,
https://doi.org/10.1029/2005JA011359, 2006. a
Clauer, C. R. and Kamide, Y.: DP 1 and DP 2 current systems for the March 22,
1979 substorms, J. Geophys. Res., 90, 1343–1354, 1985. a
Cliver, E. W., Kamide, Y., and Ling, A. G.: Mountain and valleys: Semiannual
variation of geomagnetic activity, J. Geophys. Res., 105, 2413–2424, 2000. a
Davis, T. N. and Sugiura, M.: Auroral electrojet activity index AE and its
universal time variations, J. Geophys. Res., 71, 785–801, 1966. a
Ebihara, Y., Tanaka, T., and Kamiyoshikawa, N.: New diagnosis for energy flow
from solar wind to ionosphere during substorm: Global MHD simulation, J.
Geophys. Res., 124, 360–378, https://doi.org/10.1029/2018JA026177, 2019. a, b
Gleisner, H. and Lundstedy, H.: Auroral electrojet predictions with dynamic
neural networks, J. Geophys. Res., 106, 24514–24549, 2001. a
Iijima, T. and Potemra, T. A.: The relationship between interplanetary
quantities and Birkeland current densities, Geophys. Res. Lett., 9,
442–445, 1982. a
Iyemori, T.: Storm-time magnetospheric currents inferred from mid-latitude
geomagnetic field variations, J. Geomag. Geoelectr., 42, 1249–1265, 1990. a
Iyemori, T. and Rao, D. R. K.: Decay of the Dst field of geomagnetic disturbance after substorm onset and its implication to storm-substorm relation, Ann. Geophys., 14, 608–618, https://doi.org/10.1007/s00585-996-0608-3, 1996. a
Jaeger, H. and Haas, H.: Harnessing nonlinearity: Predicting chaotic systems
and saving energy in wireless communication, Science, 304, 78–80,
https://doi.org/10.1126/science.1091277, 2004. a
Jaeger, H., Lukoševičius, M., Popovici, D., and Siewert, U.:
Optimization and applications of echo state networks with leaky-integrator
neurons, Neural Networks, 20, 335–352,
https://doi.org/10.1016/j.neunet.2007.04.016, 2007. a
Kepko, L., McPherron, R. L., Amm, O., Apatenkov, S., Baumjohann, W., Birn, J.,
Lester, M., Nakamura, R., Pulkkinen, T. I., and Sergeev, V.: Substorm
Current Wedge Revisited, Space Sci. Rev., 190, 1–46,
https://doi.org/10.1007/s11214-014-0124-9, 2015. a
King, J. H. and Papitashvili, N. E.: One min and 5-min solar wind data sets at the Earth's bow shock nose, NASA [data set], available at: https://omniweb.gsfc.nasa.gov/ow_min.html, last access: 11 January 2022. a
Korth, H., Anderson, B. J., and Waters, C. L.: Statistical analysis of the
dependence of large-scale Birkeland currents on solar wind parameters, Ann.
Geophys., 28, 515–530, https://doi.org/10.5194/angeo-28-515-2010, 2010. a
Lukoševičius, M.: A practical guide to applying echo state
networks, in: Neural networks: Tricks of the trade, edited by: Montavon,
G., Orr, G., and Müller, K., Springer, 659–686, 2012. a
Lukoševičius, M. and Jaeger, H.: Reservoir computing approaches to recurrent neural network training, Comput. Sci. Rev., 3, 127–149, https://doi.org/10.1016/j.cosrev.2009.03.005, 2009. a
Luo, B., Li, X., Temerin, M., and Liu, S.: Prediction of the AU, AL, and
AE indices using solar wind parameters, J. Geophys. Res., 118, 7683–7694,
https://doi.org/10.1002/2013JA019188, 2013. a, b, c, d
McPherron, R. L., Hsu, T.-S., and Chu, X.: An optimum solar wind coupling
function for the AL index, J. Geophys. Res., 120, 2494–2515,
https://doi.org/10.1002/2014JA020619, 2015. a, b
Nagata, D., Machida, S., Ohtani, S., Saito, Y., and Mukai, T.: Solar wind
control of plasma number density in the near-Earth plasma sheet, J. Geophys.
Res., 112, A09204, https://doi.org/10.1029/2007JA012284, 2007. a
Nakano, S.: Behavior of the iterative ensemble-based variational method in nonlinear problems, Nonlin. Processes Geophys., 28, 93–109, https://doi.org/10.5194/npg-28-93-2021, 2021. a
Nakano, S., Ueno, G., Ohtani, S., and Higuchi, T.: Impact of the solar wind
dynamic pressure on the Region 2 field-aligned currents, J. Geophys. Res.,
114, A02221, https://doi.org/10.1029/2008JA013674, 2009. a
Newell, P. T. and Gjerloev, J. W.: Evaluation of SuperMAG auroral electrojet
indices as indicators of substorms and auroral power, J. Geophys. Res., 116,
A12211, https://doi.org/10.1029/2011JA016779, 2011. a
Newell, P. T., Sotirelis, T., Liou, K., Meng, C.-I., and Rich, F. J.: A nearly
universal solar wind–magnetosphere coupling function inferred from 10
magnetospheric state variables, J. Geophys. Res., 112, A01206,
https://doi.org/10.1029/2006JA012015, 2007. a, b, c, d
Newell, P. T., Sotirelis, T., Liou, K., and Rich, F. J.: Pairs of solar
wind–magnetosphere coupling functions: Combining a merging term with a
viscous term works best, J. Geophys. Res., 113, A04218,
https://doi.org/10.1029/2007JA012825, 2008. a
Ober, D. M., Wilson, G. R., Burke, W. J., Maynard, N. C., and Siebert, K. D.:
Magnetohydrodynamic simulations of transient transpolar potential responses
to solar wind density changes, J. Geophys. Res., 112, A10212,
https://doi.org/10.1029/2006JA012169, 2007. a
Pallocchia, G., Amata, E., Consolini, G., Marcucci, M. F., and Bertello, I.:
AE index forecast at different time scales through an ANN algorithm based on
L1 IMF and plasma measurements, J. Atmos. Sol.-Terr. Phy., 70, 663–668,
2008. a
Sergeev, V. A., Sormakov, D. A., and Angelopoulos, V.: A missing variable in
solar wind–magnetosphere–ionosphere coupling studies, Geophys. Res. Lett.,
41, 8215–8220, https://doi.org/10.1002/2014GL062271, 2014. a
Sergeev, V. A., Dmitrieva, N. P., Stepanov, N. A., Sormakov, D. A.,
Angelopoulos, V., and Runov, V.: On the plasma sheet dependence on solar
wind and substorms and its role in magnetosphere–ionosphere coupling, Earth
Planets Space, 67, 133, https://doi.org/10.1186/s40623-015-0296-x, 2015. a
Takalo, J. and Timonen, J.: Neural network prediction of AE data, Geophys.
Res. Lett., 24, 2403–2406, 1997. a
Terasawa, T., Fujimoto, M., Mukai, T., Shinohara, I., Saito, Y., Yamamoto, T.,
Machida, S., Kokubun, S., Lazarus, A. J., Steinberg, J. T., and Lepping,
R. P.: Solar wind control of density and temperature in the near-Earth
plasma sheet: WIND/GEOTAIL collaboration, Geophys. Res. Lett., 24, 935–938,
1997. a
Tsurutani, B. T., Goldstein, B. E., Smith, E. J., Gonzalez, W. D., Tang, F.,
Akasofu, S. I., and Anderson, R. R.: The interplanetary and solar causes of
geomagnetic activity, Planet. Space Sci., 38, 109–126, 1990. a
Tsurutani, B. T., Gonzalez, W. D., Gonzalez, A. L. C., Tang, F., Arballo,
J. K., and Okada, M.: Interplanetary origin of geomagnetic activity in the
declining phase of the solar cycle, J. Geophys. Res., 100, 21717–21733,
1995. a
Wang, H., Lühr, H., Ma, S. Y., Weygand, J., Skoug, R. M., and Yin, F.: Field-aligned currents observed by CHAMP during the intense 2003 geomagnetic storm events, Ann. Geophys., 24, 311–324, https://doi.org/10.5194/angeo-24-311-2006, 2006. a
World Data Center for Geomagnetism, Kyoto: Mid-latitude geomagnetic indices ASY and SYM (Provisional), No. 10, Data Analysis Center for Geomagnetism and Space Magnetism, Graduate School of Science, Kyoto University [data set], available at: http://wdc.kugi.kyoto-u.ac.jp/wdc/Sec3.html (last access: 11 January 2022), 2000. a
World Data Center for Geomagnetism, Kyoto, Nosé, M., Iyemori, T.,
Sugiura, M., and Kamei, T.: Geomagnetic AE index, Data Analysis Center
for Geomagnetism and Space Magnetism, Graduate School of Science, Kyoto
University, https://doi.org/10.17593/15031-54800, 2015. a
Short summary
The relationships between auroral activity and the solar-wind conditions are modeled with a machine-learning technique. The impact of various solar-wind parameters on the auroral activity is then evaluated by putting artificial inputs into the trained machine-learning model. One of the notable findings is that the solar-wind density effect on the auroral activity is emphasized under high solar-wind speed and weak solar-wind magnetic field.
The relationships between auroral activity and the solar-wind conditions are modeled with a...