Abstract
Geomagnetic storms resulting from solar disturbances impact telecommunication and satellite systems. Satellites are positioned at Lagrange point L1 to monitor these disturbances and give warning 30 min to 1 h ahead. As propagation delay from L1 to Earth depends on various factors, estimating the delay using the assumption of ballistic propagation can result in greater uncertainty. In this study, we aim to reduce the uncertainty in the propagation delay by using machine-learning (ML) models. Solar-wind velocity components (\(V_{ \mathrm{x}}\), \(V_{\mathrm{y}}\), \(V_{\mathrm{z}}\)), the position of Advanced Composition Explorer (ACE) at all three coordinates (\(r_{\mathrm{x}}\), \(r_{\mathrm{y}}\), \(r_{\mathrm{z}}\)), and the Earth’s dipole tilt angle at the time of the disturbances are taken as input parameters. The target is the time taken by the disturbances to reach from L1 to the magnetosphere. The study involves a comparison of eight ML models that are trained across three different speed ranges of solar-wind disturbances. For low and very high-speed solar wind, the vector-delay method fares better than the flat-plane propagation method and ML models. Ridge regression performs consistently better at all three speed ranges in ML models. For high-speed solar wind, boosting models perform well with an error of around 3.8 min better than the vector-delay model. Studying the best-performing models through variable-importance measures, the velocity component \(V_{\mathrm{x}}\) is identified as the most important feature for the estimation and aligns well with the flat-plane propagation method. Additionally, for slow solar-wind disturbances, the position of ACE is seen as the second most important feature in ridge regression, while high-speed disturbances emphasize the importance of other vector components of solar-wind speed over the ACE position. This work improves our understanding of the propagation delay of different solar-wind speed and showcases the potential of ML in space weather prediction.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data Availability
No datasets were generated or analysed during the current study.
References
Awad, M., Khanna, R.: 2015, Support Vector Regression 67, Apress, Berkeley, 978. DOI.
Baniecki, H., Kretowicz, W., Piatyszek, P., Wisniewski, J., Biecek, P.: 2021, Dalex: responsible machine learning with interactive explainability and fairness in python. J. Mach. Learn. Res. 22, 1.
Baumann, C., McCloskey, A.E.: 2021, Timing of the solar wind propagation delay between L1 and Earth based on machine learning. J. Space Weather Space Clim. 11, 41. DOI. ADS.
Blanchard, G.T., Bankston, D.: 2002, Improved interplanetary magnetic field propagation timing by correction of the phase front orientation using two spacecraft. J. Geophys. Res. Space Phys. 107, SSH 6. DOI.
Burlaga, L.F., Ogilvie, K.W.: 1969, Causes of sudden commencements and sudden impulses. J. Geophys. Res. 74, 2815. DOI. ADS.
Cameron, T., Jackel, B.: 2016, Quantitative evaluation of solar wind time-shifting methods. Space Weather 14, 973. DOI.
Cameron, T.G., Jackel, B.: 2019, Using a numerical MHD model to improve solar wind time shifting. Space Weather 17, 662. DOI.
Cash, M.D., Witters Hicks, S., Biesecker, D.A., Reinard, A.A., de Koning, C.A., Weimer, D.R.: 2016, Validation of an operational product to determine L1 to Earth propagation time delays. Space Weather 14, 93. DOI.
Collier, M.R., Slavin, J.A., Lepping, R.P., Szabo, A., Ogilvie, K.: 1998, Timing accuracy for the simple planar propagation of magnetic field structures in the solar wind. Geophys. Res. Lett. 25, 2509. DOI.
Crooker, N.U., Siscoe, G.L., Russell, C.T., Smith, E.J.: 1982, Factors controlling degree of correlation between ISEE 1 and ISEE 3 interplanetary magnetic field measurements. J. Geophys. Res. Space Phys. 87, 2224. DOI.
Eggington, J.W.B., Eastwood, J.P., Mejnertsen, L., Desai, R.T., Chittenden, J.P.: 2020, Dipole tilt effect on magnetopause reconnection and the steady-state magnetosphere-ionosphere system: global MHD simulations. J. Geophys. Res. Space Phys. 125, e2019JA027510. DOI.
Friedman, J.H.: 2002, Stochastic gradient boosting. Comput. Stat. Data Anal. 38, 367. DOI. Nonlinear Methods and Data Mining.
Fujita, S.: 2019, Response of the magnetosphere–ionosphere system to sudden changes in solar wind dynamic pressure. Rev. Mod. Plasma Phys. 3, 2. DOI.
Gosling, J.T., Asbridge, J.R., Bame, S.J., Hundhausen, A.J., Strong, I.B.: 1967, Discontinuities in the solar wind associated with sudden geomagnetic impulses and storm commencements. J. Geophys. Res. 72, 3357. DOI.
Ho, T.K.: 1995, Random decision forests. In: Proc. 3rd Int. Conf. Doc. Anal. Recogn. 1, 278. DOI.
Horbury, T.S., Burgess, D., Fränz, M., Owen, C.J.: 2001, Prediction of Earth arrival times of interplanetary southward magnetic field turnings. J. Geophys. Res. Space Phys. 106, 30001. DOI.
Joselyn, J.A., Tsurutani, B.T.: 1990, Geomagnetic sudden impulses and storm sudden commencements: a note on terminology. Eos Trans. AGU 71, 1808. DOI.
Karl Laundal, K., Reistad, J., Smith, A., Hovland, A.: 2020. Dipole.
Kelly, T.J., Crooker, N.U., Siscoe, G.L., Russell, C.T., Smith, E.J.: 1986, On the use of a sunward libration-point-orbiting spacecraft as an interplanetary magnetic field monitor for magnetospheric studies. J. Geophys. Res. Space Phys. 91, 5629. DOI.
Lavraud, B., Thomsen, M.F., Borovsky, J.E., Denton, M.H., Pulkkinen, T.I.: 2006, Magnetosphere preconditioning under northward IMF: Evidence from the study of coronal mass ejection and corotating interaction region geoeffectiveness. J. Geophys. Res. Space Phys. 111. DOI.
Lepping, R.P., Behannon, K.W.: 1980, Magnetic field directional discontinuities: 1. Minimum variance errors. J. Geophys. Res. Space Phys. 85, 4695. DOI.
Liu, Z.-Q., Lu, J.Y., Kabin, K., Yang, Y.F., Zhao, M.X., Cao, X.: 2012, Dipole tilt control of the magnetopause for southward IMF from global magnetohydrodynamic simulations. J. Geophys. Res. Space Phys. 117. DOI.
Lu, J.Y., Liu, Z.-Q., Kabin, K., Jing, H., Zhao, M.X., Wang, Y.: 2013, The IMF dependence of the magnetopause from global MHD simulations. J. Geophys. Res. Space Phys. 118, 3113. DOI.
Mailyan, B., Munteanu, C., Haaland, S.: 2008, What is the best method to calculate the solar wind propagation delay? Ann. Geophys. 26. DOI.
Maynard, N.C., Burke, W.J., Sandholt, P.E., Moen, J., Ober, D.M., Lester, M., Weimer, D.R., Egeland, A.: 2001, Observations of simultaneous effects of merging in both hemispheres. J. Geophys. Res. 106, 24551. DOI. ADS.
McComas, D.J., Bame, S.J., Barker, P., Feldman, W.C., Phillips, J.L., Riley, P., Griffee, J.W.: 1998, Solar Wind Electron Proton Alpha Monitor (SWEPAM) for the advanced composition explorer. Space Sci. Rev. 86, 563. DOI.
McDonald, G.C.: 2009, Ridge regression. WIREs Comput. Stat. 1, 93. DOI.
Milan, S.E., Carter, J.A., Bower, G.E., Fleetham, A.L., Anderson, B.J.: 2022, Influence of off-Sun-Earth line distance on the accuracy of L1 solar wind monitoring. J. Geophys. Res. Space Phys. 127, e2021JA030212. DOI.
Munteanu, C., Haaland, S., Mailyan, B., Echim, M., Mursula, K.: 2013, Propagation delay of solar wind discontinuities: comparing different methods and evaluating the effect of wavelet denoising. J. Geophys. Res. Space Phys. 118, 3985. DOI.
Nishida, A., Cahill, J., Laurence, J.: 1964, Sudden impulses in the magnetosphere observed by explorer 12. J. Geophys. Res. 69, 2243. DOI. ADS.
O’Brien, C., Walsh, B.M., Zou, Y., Tasnim, S., Zhang, H., Sibeck, D.G.: 2023, PRIME: a probabilistic neural network approach to solar wind propagation from L1. Front. Astron. Space Sci. 10. DOI.
Popescu, M.-C., Balas, V.E., Perescu-Popescu, L., Mastorakis, N.: 2009, Multilayer perceptron and neural networks. WSEAS Trans. Circuits Syst. 8, 579.
Pulkkinen, A., Rastätter, L.: 2009, Minimum variance analysis-based propagation of the solar wind observations: Application to real-time global magnetohydrodynamic simulations. Space Weather 7. DOI.
Ridley, A.J.: 2000, Estimations of the uncertainty in timing the relationship between magnetospheric and solar wind processes. J. Atmos. Solar-Terr. Phys. 62, 757. DOI.
Ridley, A.J., Lu, G., Clauer, C.R., Papitashvili, V.O.: 1998, A statistical study of the ionospheric convection response to changing interplanetary magnetic field conditions using the assimilative mapping of ionospheric electrodynamics technique. J. Geophys. Res. Space Phys. 103, 4023. DOI.
Russell, C.T., Siscoe, G.L., Smith, E.J.: 1980, Comparison of ISEE-1 and −3 interplanetary magnetic field observations. Geophys. Res. Lett. 7, 381. DOI.
Schwartz, S.J.: 1998, Analysis methods for multi-spacecraft data. ISSI Sci. Rep. Ser. 1, 249.
Sonnerup, B.U.Ö., Scheible, M.: 1998, Minimum and maximum variance analysis. ISSI Sci. Rep. Ser. 1, 185. ADS.
Tsurutani, B., Baker, D.: 1979, Substorm warnings: an ISEE-3 real time data system. Eos Trans. AGU 60, 701. DOI.
Weimer, D.R., King, J.H.: 2008, Improved calculations of interplanetary magnetic field phase front angles and propagation time delays. J. Geophys. Res. Space Phys. 113. DOI.
Weimer, D.R., Ober, D.M., Maynard, N.C., Burke, W.J., Collier, M.R., McComas, D.J., Ness, N.F., Smith, C.W.: 2002, Variable time delays in the propagation of the interplanetary magnetic field. J. Geophys. Res. Space Phys. 107, 1210. DOI. ADS.
Weimer, D.R., Ober, D.M., Maynard, N.C., Collier, M.R., McComas, D.J., Ness, N.F., Smith, C.W., Watermann, J.: 2003, Predicting interplanetary magnetic field (IMF) propagation delay times using the minimum variance technique. J. Geophys. Res. Space Phys. 108. DOI.
Zhu, C.B., Zhang, H., Ge, Y.S., Pu, Z.Y., Liu, W.L., Wan, W.X., Liu, L.B., Chen, Y.D., Le, H.J., Wang, Y.F.: 2015, Dipole tilt angle effect on magnetic reconnection locations on the magnetopause. J. Geophys. Res. Space Phys. 120, 5344. DOI.
Acknowledgements
We thank the anonymous reviewer for the constructive comments and suggestions, which greatly improved the readability and quality of the paper. We express gratitude for the availability of ACE data, generously provided by the ACE Science Center at Caltech (www.srl.caltech.edu/ACE). This paper uses data from the Heliospheric Shock Database, generated and maintained at the University of Helsinki to determine the shock list.
Author information
Authors and Affiliations
Contributions
Saurabh Das and Hemapriya Raju conceptualized the idea. Hemapriya Raju contributed to the model development, analysis of the results, it’s interpretation, and the initial drafting of the manuscript. Saurabh Das provided supervision throughout the manuscript. Both the authors contributed to refining the final version of the manuscript and reviewed it.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Raju, H., Das, S. Comparative Analysis of Various Machine-Learning Models for Solar-Wind Propagation-Delay Estimation. Sol Phys 299, 95 (2024). https://doi.org/10.1007/s11207-024-02339-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11207-024-02339-2