Geophysical Center RAS
Ufa, Russian Federation
Schmidt Institute of Physics of the Earth, RAS
Moscow, Russian Federation
Schmidt Institute of Physics of the Earth, RAS
Geophysical Center RAS
Moscow, Russian Federation
Space Research Institute of RAS
Ufa, Russian Federation
Ufa, Russian Federation
Ufa, Russian Federation
Apatity, Russian Federation
Apatity, Russian Federation
Despite the existing variety of approaches to monitoring space weather and geophysical parameters in the auroral oval region, the issue of effective prediction and diagnostics of auroras as a special state of the upper ionosphere at high latitudes remains virtually unresolved. In this paper, we explore the possibility of local diagnostics of auroras through mining of geomagnetic data from ground-based sources. We assess the significance of indicative variables and their statistical relationship. So, for example, the application of Bayesian inference to the data from the Lovozero geophysical station for 2012–2020 has shown that the dependence of a posteriori probability of observing auroras in the optical range on the state of geomagnetic parameters is logarithmic, and the degree of its significance is inversely proportional to the discrepancy between empirical data and approximating function. The accuracy of the approach to diagnostics of aurora presence based on the random forest method is at least 86 % when using several local predictors and ~80 % when using several global geomagnetic activity indices characterizing the geomagnetic field disturbance in the auroral zone. In conclusion, we discuss promising ways to improve the quality metrics of diagnostic models and their scope.
auroras, geomagnetic variations, geomagnetic data, ascaplots, machine learning, data mining, Bayesian inference, random forest
1. Baudot P., Tapia M., Bennequin D., Goaillard J.-M. Topological Information Data Analysis. Entropy. 2019, vol. 21, iss.9, p. 869. DOI:https://doi.org/10.3390/e21090869.
2. Breedveld M.J. Predicting the Auroral Oval Boundaries by Means of Polar Operational Environmental Satellite Particle Precipitation Data. Master Thesis. Arctic University of Norway. June 2020.
3. Gjerloev J.W. The SuperMAG data processing technique. J. Geophys. Res. 2012, vol. 117, iss. A9, p. A09213. DOI:https://doi.org/10.1029/2012JA017683.
4. Hand D.J., Till R.J. A simple generalization of the area under the ROC curve for multiple class classification problems. Machine Learning. 2001, vol. 45, rr. 171-186. DOI:https://doi.org/10.1023/A:1010920819831.
5. Jolliffe I.T. Principal Component Analysis. Ser.: Springer Series in Statistics, 2nd ed., Springer, NY, 2002, XXIX, 487 p.
6. Kuhn M., Johnson K. Feature Engineering and Selection: A Practical Approach for Predictive Models. CRC Press, 2019, 298 p.
7. Lebedinsky A.I. Synchronous auroral registration by all-sky camera C-180 and patrol spectrograph C-180-S. Ann. Intern. Geophys. Year. 1961, vol. XI.
8. Machol J.L., Green J.C., Redmon R.J., Viereck R.A., Newell P.T. Evaluation of OVATION as a forecast model for visible aurorae. Space Weather. 2012, vol. 10, iss. 3, p. S03005. DOI: 10.1029/ 2011SW000746.
9. Mantas C.J., Castellano J.G., Moral-García S., Abellán J. A comparison of random forest based algorithms: random credal random forest versus oblique random forest. Soft Somputing. 2019, vol. 23, rr. 10739-10754. DOI:https://doi.org/10.1007/s00500-018-3628-5.
10. Newell P.T., Gjerloev J.W. Substorm and magnetosphere characteristic scales inferred from the SuperMAG auroral electrojet indices. J. Geophys. Res. 2011, vol. 116, iss. A12, p. A12232. DOI:https://doi.org/10.1029/2011JA016936.
11. Newell P.T., Sotirelis T., Wing S. Seasonal variations in diffuse, monoenergetic, and broadband aurora, J. Geophys. Res. 2010, vol. 115, iss. A3, p. A03216. DOI:https://doi.org/10.1029/2009 JA014805.
12. Newell P.T., Liou K., Zhang Y., Sotirelis T., Paxton L.J., Mitchell E.J. OVATION Prime-2013: Extension of auroral precipitation model to higher disturbance levels. Space Weather. 2014, vol. 12, iss. 6, pp. 368-379. DOI: 10.1002/ 2014SW001056.
13. PGI Geophysical data. January, February, March 2015 / Ed. V. Vorobjev. Murmansk, Apatity: PGI KSC RAS. 2015.
14. Pilipenko V.A. Space weather impact on ground-based technological systems. Solar-Terr. Phys. 2021, vol. 7, iss. 3, pp. 68-104. DOI:https://doi.org/10.12737/stp-73202106.
15. Ptitsyna N.G., Tyasto M.I., Kasinsky V.V., Lyakhov N.N. Influence of space weather on technical systems: failures of railway equipment during geomagnetic storms. Solar-Terr. Phys. 2008, No. 12-2 (125), pp. 360. (In Russian).
16. Sigernes F., Holmen S. E., Biles D., Bjørklund H., Chen X., Dyrland M., Lorentzen D.A., Baddeley L., et al. Auroral all-sky camera calibration. Geoscientific Instrumentation, Methods and Data Systems. 2014, vol. 3, iss. 2, pp. 241-245. DOI:https://doi.org/10.5194/gi-3-241-2014.
17. Sokolova O.N., Sakharov Ya.A., Gritsutenko S.S., Korovkin N.V. Algorithm for analyzing the stability of power systems to geomagnetic storms. News of the Russian Academy of Sciences. Energy. 2019, no. 5, pp. 33-52. DOI: 10.1134/ S0002331019050145. (In Russian).
18. Soloviev A.A., Sidorov R.V., Oshchenko A.A., Zaitsev A.N. On the need for accurate monitoring of the geomagnetic field during directional drilling in the Russian Arctic. Izvestiya. Physics of the Solid Earth. 2022, vol. 58, pp. 420-434. DOI: 10.1134/ S1069351322020124.
19. Vorobev A., Soloviev A., Pilipenko V., Vorobeva G., Sakharov Y. An approach to diagnostics of geomagnetically induced currents based on ground magnetometers data. App. Sci. 2022a, vol. 12, iss. 3, pp. 1522. DOI:https://doi.org/10.3390/app12031522.
20. Vorobev A.V., Soloviev A.A., Pilipenko V.A., Vorobeva G.R. Interactive Computer model for aurora forecast and analysis. Solar-Terr. Phys. 2022b, vol. 8, no 2, pp. 84-90. DOI:https://doi.org/10.12737/stp-82202213.
21. Vorobjev V.G., Yagodkina O.I. Effect of magnetic activity on the global distribution of auroral precipitation zones. Geomagnetism and Aeronomy. 2005, vol. 45, pp. 438-444.
22. Witlox F. Gini Coefficient. International Encyclopedia of Geography: People, the Earth, Environment and Technology. 2017. DOI:https://doi.org/10.1002/9781118786352.wbieg0855.
23. Yagodkina O.I., Vorobyov V.G., Shekunova E.S. Observations of auroras over the Kola Peninsula. Proc. Kola Scientific Center of the Russian Academy of Sciences. 2019, vol. 10, no. 8-5, pp. 43-55. DOI:https://doi.org/10.25702/KSC.2307-5252.2019.10.8. (In Russian).
24. Yasyukevich Y., Astafyeva E., Padokhin A. Ivanova V., Syrovatskii S., Podlesnyi A. The 6 September 2017 X-class solar flares and their impacts on the ionosphere, GNSS, and HF radio wave propagation. Space Weather. 2018, vol. 16, iss. 8, pp. 1013-1027. DOI: 10.1029/ 2018SW001932.
25. Yasyukevich Y., Vasilyev R., Ratovsky K. Small-scale ionospheric irregularities of auroral origin at mid-latitudes during the 22 June 2015 magnetic storm and their effect on GPS positioning. Remote Sensing. 2020, vol. 12, no 10, p. 1579. DOI:https://doi.org/10.3390/rs12101579.
26. Zakharov V.I., Chernyshov A.A., Miloh V., Jin Ya. Influence of the ionosphere on the parameters of GPS navigation signals during a geomagnetic substorm. Space Res. 2020, vol. 60, no. 6, pp. 769-782. DOI:https://doi.org/10.7868/S0023420616010143. (In Russian).
