skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Title: A Deep Learning‐Based Approach to Forecast the Onset of Magnetic Substorms
Abstract The auroral substorm has been extensively studied over the last six decades. However, our understanding of its driving mechanisms is still limited and so is our ability to accurately forecast its onset. In this study, we present the first deep learning‐based approach to predict the onset of a magnetic substorm, defined as the signature of the auroral electrojets in ground magnetometer measurements. Specifically, we use a time history of solar wind speed (Vx), proton number density, and interplanetary magnetic field (IMF) components as inputs to forecast the occurrence probability of an onset over the next 1 hr. The model has been trained and tested on a data set derived from the SuperMAG list of magnetic substorm onsets and can correctly identify substorms ∼75% of the time. In contrast, an earlier prediction algorithm correctly identifies ∼21% of the substorms in the same data set. Our model's ability to forecast substorm onsets based on solar wind and IMF inputs prior to the actual onset time, and the trend observed in IMFBzprior to onset together suggest that a majority of the substorms may not be externally triggered by northward turnings of IMF. Furthermore, we find that IMFBzandVxhave the most significant influence on model performance. Finally, principal component analysis shows a significant degree of overlap in the solar wind and IMF parameters prior to both substorm and nonsubstorm intervals, suggesting that solar wind and IMF alone may not be sufficient to forecast all substorms, and preconditioning of the magnetotail may be an important factor.  more » « less
Award ID(s):
1822056 1839509
PAR ID:
10456287
Author(s) / Creator(s):
 ;  ;  ;  ;  
Publisher / Repository:
DOI PREFIX: 10.1029
Date Published:
Journal Name:
Space Weather
Volume:
17
Issue:
11
ISSN:
1542-7390
Page Range / eLocation ID:
p. 1534-1552
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract We analyze three substorms that occur on (1) 9 March 2008 05:14 UT, (2) 26 February 2008 04:05 UT, and (3) 26 February 2008 04:55 UT. Using ACE solar wind velocity and interplanetary magnetic fieldBzvalues, we calculate the rectified (southwardBz) solar wind voltage propagated to the magnetosphere. The solar wind conditions for the two events were vastly different, 300 kV for 9 March 2008 substorm, compared to 50 kV for 26 February 2008. The voltage is input to a nonlinear physics‐based model of the magnetosphere called WINDMI. The output is the westward auroral electrojet current which is proportional to the auroral electrojet (AL) index from World Data Center for Geomagnetism Kyoto and the SuperMAG auroral electrojet index (SML). Substorm onset times are obtained from the superMAG substorm database, Pu et al. (2010,https://doi.org/10.1029/2009JA014217), Lui (2011,https://doi.org/10.1029/2010JA016078) and synchronized to Time History of Events and Macroscale Interactions during Substorms satellite data. The timing of onset, model parameters, and intermediate state space variables are analyzed. The model onsets occurred about 5 to 10 min earlier than the reported onsets. Onsets occurred when the geotail current in the WINDMI model reached a critical threshold of 6.2 MA for the 9 March 2008 event, while, in contrast, a critical threshold of 2.1 MA was obtained for the two 26 February 2008 events. The model estimates 1.99 PJ of total energy transfer during the 9 March 2008 event, with 0.95 PJ deposited in the ionosphere. The smaller events on 26 February 2008 resulted in a total energy transfer of 0.37 PJ according to the model, with 0.095 PJ deposited in the ionosphere. 
    more » « less
  2. Abstract We study the effects of the east‐west (y) component of the interplanetary magnetic field (IMF) on the occurrence of substorms by analyzing 16,743 magnetic substorm events identified with the SuperMAGSMLindex from 1995 to 2016. It is found, surprisingly, that substorm occurrence rates depend highly on the sign of IMFBy, with, on average, ~1/3 more substorms for IMFBy> 0 than for IMFBy< 0. We attribute this asymmetry to the enhanced convection (e.g., more energy in the tail) under IMFBy> 0 conditions. A superposed epoch analysis of the IMF indicates that the average IMFByprior to onset is positive but becomes less positive ~15 min prior to the onset, indicating that the release of the stress associated with a clockwise twisted magnetotail may be an important onset trigger. We conjecture that an asymmetry in the dayside merging efficiency may be the cause. 
    more » « less
  3. Abstract The extreme substorm event on 5 April 2010 (THEMIS AL = −2,700 nT, called supersubstorm) was investigated to examine its driving processes, the aurora current system responsible for the supersubstorm, and the magnetosphere‐ionosphere‐thermosphere (M‐I‐T) responses. An interplanetary shock created shock aurora, but the shock was not a direct driver of the supersubstorm onset. Instead, the shock with a large southward IMF strengthened the growth phase with substantially larger ionosphere currents, more rapid equatorward motion of the auroral oval, larger ionosphere conductance, and more elevated magnetotail pressure than those for the growth phase of classical substorms. The auroral brightening at the supersubstorm onset was small, but the expansion phase had multistep enhancements of unusually large auroral brightenings and electrojets. The largest activity was an extremely large poleward boundary intensification (PBI) and subsequent auroral streamer, which started ~20 min after the substorm auroral onset during a steady southward IMFBzand elevated dynamic pressure. Those were associated with a substorm current wedge (SCW), plasma sheet flow, relativistic particle injection and precipitation down to the D‐region, total electron content (TEC), conductance, and neutral wind in the thermosphere, all of which were unusually large compared to classical substorms. The SCW did not extend over the entire nightside auroral activity but was localized azimuthally to a few 100 km in the ionosphere around the PBI and streamer. These results reveal the importance of localized magnetotail reconnection for releasing large energy accumulation that can affect geosynchronous satellites and produce the extreme M‐I‐T responses. 
    more » « less
  4. Abstract We model lower band chorus observations from the DEMETER satellite using daily and hourly autoregressive‐moving average transfer function (ARMAX) equations. ARMAX models can account for serial autocorrelation between observations that are measured close together in time and can be used to predict a response variable based on its past behavior without the need for recent data. Unstable distributions of radiation belt source electrons (tens of keV) and the substorm activity (SMEd from the SuperMAG array) that is thought to inject these electrons were both statistically significant explanatory variables in a daily ARMAX model describing chorus. Predictions from this model correlated well with observations in a hold‐out test data set (validation correlation of 0.675). Source electron flux was most influential when observations came from the same day or the day before the chorus measurement, with effects decaying rapidly over time. Substorms were more influential when they occurred on previous days, presumably due to their injecting source electrons from the plasma sheet. A daily ARMAX model with interplanetary magnetic field (IMF)|B|, IMFBz, and solar wind pressure as inputs instead of those given above was somewhat less predictive of chorus (r=0.611). An hourly ARMAX model with only solar wind and IMF inputs was even less successful, with a validation correlation of 0.502. 
    more » « less
  5. Abstract Substorm‐type evolution of the Earth's magnetosphere is investigated by mining more than two decades (1995–2017) of spaceborne magnetometer data from multiple missions including the first two years (2016‐2017) of the Magnetospheric MultiScale mission. This investigation reveals interesting features of plasma evolution distinct from ideal magnetohydrodynamics (MHD) behavior: X‐lines, thin current sheets, and regions with the tailward gradient of the equatorial magnetic fieldBz. X‐lines are found to form mainly beyond 20RE, but for strong driving, with the solar wind electric field exceeding ∼5mV/m, they may come closer. For substorms with weaker driving, X‐lines may be preceded by redistribution of the magnetic flux in the tailwardBzgradient regions, similar to the magnetic flux release instability discovered earlier in PIC and MHD simulations as a precursor mechanism of the reconnection onset. Current sheets in the growth phase may be as thin as 0.2RE, comparable to the thermal ions gyroradius, and at the same time, as long as 15RE. Such an aspect ratio is inconsistent with the isotropic force balance for observed magnetic field configurations. These findings can help resolve kinetic mechanisms of substorm dipolarizations and adjust kinetic generalizations of global MHD models of the magnetosphere. They can also guide and complement microscale analysis of nonideal effects. 
    more » « less