skip to main content


Title: Probabilistic Forecasting of Ground Magnetic Perturbation Spikes at Mid‐Latitude Stations
Abstract

The prediction of large fluctuations in the ground magnetic field (dB/dt) is essential for preventing damage from Geomagnetically Induced Currents. Directly forecasting these fluctuations has proven difficult, but accurately determining the risk of extreme events can allow for the worst of the damage to be prevented. Here we trained Convolutional Neural Network models for eight mid‐latitude magnetometers to predict the probability thatdB/dtwill exceed the 99th percentile threshold 30–60 min in the future. Two model frameworks were compared, a model trained using solar wind data from the Advanced Composition Explorer (ACE) satellite, and another model trained on both ACE and SuperMAG ground magnetometer data. The models were compared to examine if the addition of current ground magnetometer data significantly improved the forecasts ofdB/dtin the future prediction window. A bootstrapping method was employed using a random split of the training and validation data to provide a measure of uncertainty in model predictions. The models were evaluated on the ground truth data during eight geomagnetic storms and a suite of evaluation metrics are presented. The models were also compared to a persistence model to ensure that the model using both datasets did not over‐rely ondB/dtvalues in making its predictions. Overall, we find that the models using both the solar wind and ground magnetometer data had better metric scores than the solar wind only and persistence models, and was able to capture more spatially localized variations in thedB/dtthreshold crossings.

 
more » « less
Award ID(s):
1920965
NSF-PAR ID:
10419815
Author(s) / Creator(s):
 ;  ;  ;  ;  ;  ;  ;  
Publisher / Repository:
DOI PREFIX: 10.1029
Date Published:
Journal Name:
Space Weather
Volume:
21
Issue:
6
ISSN:
1542-7390
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. During periods of rapidly changing geomagnetic conditions electric fields form within the Earth’s surface and induce currents known as geomagnetically induced currents (GICs), which interact with unprotected electrical systems our society relies on. In this study, we train multi-variate Long-Short Term Memory neural networks to predict magnitude of north-south component of the geomagnetic field (| B N |) at multiple ground magnetometer stations across Alaska provided by the SuperMAG database with a future goal of predicting geomagnetic field disturbances. Each neural network is driven by solar wind and interplanetary magnetic field inputs from the NASA OMNI database spanning from 2000–2015 and is fine tuned for each station to maximize the effectiveness in predicting | B N |. The neural networks are then compared against multivariate linear regression models driven with the same inputs at each station using Heidke skill scores with thresholds at the 50, 75, 85, and 99 percentiles for | B N |. The neural network models show significant increases over the linear regression models for | B N | thresholds. We also calculate the Heidke skill scores for d| B N |/dt by deriving d| B N |/dt from | B N | predictions. However, neural network models do not show clear outperformance compared to the linear regression models. To retain the sign information and thus predict B N instead of | B N |, a secondary so-called polarity model is utilized. The polarity model is run in tandem with the neural networks predicting geomagnetic field in a coupled model approach and results in a high correlation between predicted and observed values for all stations. We find this model a promising starting point for a machine learned geomagnetic field model to be expanded upon through increased output time history and fast turnaround times. 
    more » « less
  2. Abstract

    Prediction of geomagnetically induced currents (GICs) plays a critical role in the gestalt of space weather forecasting and risk assessment, giving power companies time to enact mitigation strategies that could avoid a catastrophic collapse of the power grid caused by, for example, the impact of an Earth‐directed coronal mass ejection. Sun‐to‐mud prediction of the surface magnetic field (and/or its time derivative) is a long‐standing goal for both first‐principles and data‐driven models. Here, we quantify the upper limits of peak GIC predictability as a function of how much magnetic field information is accurately predictable. Using the United States as a testbed, our results suggest that accurate characterization of temporal scales up to around 30 mHz keeps relative peak GIC errors below 10across the regions considered. We also found that forecasting if GIC will exceed a specified threshold over the next 30 min is feasible with an accurate prediction of peak dB/dt magnitude. This is supported by reasonable out‐of‐sample performance across several forecast metrics (0.4–0.8 POD, POFD0.05,1–5 forecast ratio,0.4–0.8 Heidke skill score), and favorable performance relative to a persistence model across all but the most extreme data intervals. We also find that the subsurface conductivity may influence peak GIC predictability. Overall, our results highlight the range of temporal scales in the surface magnetic field that are important for estimation of peak GIC and, in the context of peak dB/dt magnitude prediction, provide an upper bound on expected GIC predictability across a wide range of magnitudes.

     
    more » « less
  3. 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
  4. Abstract In this manuscript we develop a deep learning algorithm to improve estimation of rates of progression and prediction of future patterns of visual field loss in glaucoma. A generalized variational auto-encoder (VAE) was trained to learn a low-dimensional representation of standard automated perimetry (SAP) visual fields using 29,161 fields from 3,832 patients. The VAE was trained on a 90% sample of the data, with randomization at the patient level. Using the remaining 10%, rates of progression and predictions were generated, with comparisons to SAP mean deviation (MD) rates and point-wise (PW) regression predictions, respectively. The longitudinal rate of change through the VAE latent space (e.g., with eight dimensions) detected a significantly higher proportion of progression than MD at two (25% vs. 9%) and four (35% vs 15%) years from baseline. Early on, VAE improved prediction over PW, with significantly smaller mean absolute error in predicting the 4 th , 6 th and 8 th visits from the first three (e.g., visit eight: VAE8: 5.14 dB vs. PW: 8.07 dB; P < 0.001). A deep VAE can be used for assessing both rates and trajectories of progression in glaucoma, with the additional benefit of being a generative technique capable of predicting future patterns of visual field damage. 
    more » « less
  5. Abstract

    Geomagnetic indices are convenient quantities that distill the complicated physics of some region or aspect of near‐Earth space into a single parameter. Most of the best‐known indices are calculated from ground‐based magnetometer data sets, such as Dst, SYM‐H, Kp, AE, AL, and PC. Many models have been created that predict the values of these indices, often using solar wind measurements upstream from Earth as the input variables to the calculation. This document reviews the current state of models that predict geomagnetic indices and the methods used to assess their ability to reproduce the target index time series. These existing methods are synthesized into a baseline collection of metrics for benchmarking a new or updated geomagnetic index prediction model. These methods fall into two categories: (1) fit performance metrics such as root‐mean‐square error and mean absolute error that are applied to a time series comparison of model output and observations and (2) event detection performance metrics such as Heidke Skill Score and probability of detection that are derived from a contingency table that compares model and observation values exceeding (or not) a threshold value. A few examples of codes being used with this set of metrics are presented, and other aspects of metrics assessment best practices, limitations, and uncertainties are discussed, including several caveats to consider when using geomagnetic indices.

     
    more » « less