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.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Multi-Variate LSTM Prediction of Alaska Magnetometer Chain Utilizing a Coupled Model Approach
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
Award ID(s):
1920965
PAR ID:
10334986
Author(s) / Creator(s):
; ; ; ; ; ; ;
Date Published:
Journal Name:
Frontiers in Astronomy and Space Sciences
Volume:
9
ISSN:
2296-987X
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Space Weather)
    Abstract Regression models (LEEMYR: Low Energy Electron MLT geosYnchronous orbit Regression) predict hourly 4.1–30 keV electron flux at geostationary orbit (GOES‐16) using solar wind, IMF, and geomagnetic index parameters. Multiplicative interaction and polynomial terms describe synergistic and nonlinear effects. We reduce predictors to an optimal set using stepwise regression, resulting in models with validation comparable to a neural network. Models predict 1, 3, 6, 12, and 24 hr into the future. Validation correlations are as high as 0.78 (4.1 and 11 keV, 1 hr prediction) and Heidke Skill scores (HSS) up to 0.66. A 3 hr ahead prediction is more practical, with slightly lower validation correlation (0.75) and HSS (0.61). The addition of location (MLT: magnetic local time) as a covariate, including multiplicative interaction terms, accounts for location‐dependent flux differences and variation of parameter influence, and allows prediction over the full orbit. Adding a substorm index (SME) provides minimal increase in validation correlation (0.81) showing that other parameters are good proxies for an unavailable real time substorm index. Prediction intervals on individual values provide more accurate assessments of model quality than confidence intervals on the mean values. An inverse N‐weighted least squares approach is impractical as it increases false positive warnings. Physical interpretations are not possible as spurious correlations due to common cycles are not removed. However,SME, Bz, Kp, and Dst are the highest correlates of electron flux, with solar wind velocity, density, and pressure, and IMF magnitude being less well correlated. 
    more » « less
  2. ; ; ; ; ; ; ; (, Space Weather)
    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
  3. ; ; ; ; ; (, Journal of Geophysical Research: Space Physics)
    Abstract During periods of increased geomagnetic activity, perturbations within the terrestrial magnetosphere are known to induce currents within conducting materials, at the surface of Earth through rapid changes in the local magnetic field over time (dB/dt). These currents are known as geomagnetically induced currents and have potentially detrimental effects on ground based infrastructure. In this study we undertake case studies of five geomagnetic storms, analyzing a total of 19 days of 1‐s SuperMAG data in order to better understand the magnetic local time (MLT) distribution, size, and occurrence of “spikes” indB/dt, with 131,447 spikes indB/dtexceeding 5 nT/s identified during these intervals. These spikes were concentrated in clusters over three MLT sectors: two previously identified pre‐midnight and dawn region hot‐spots, and a third, lower‐density population centered around 12 MLT (noon). The noon spike cluster was observed to be associated with pressure pulse impacts, however, due to incomplete magnetometer station coverage, this population is not observed for all investigated storms. The magnitude of spikes indB/dtare determined to be greatest within these three “hot‐spot” locations. These spike occurrences were then compared with field‐aligned current (FAC) data, provided by the Active Magnetospheric Planetary Electrodynamic Response Experiment. Spikes are most likely to be co‐located with upward FACs (56%) rather than downward FACs (30%) or no FACs (14%). 
    more » « less
  4. ; ; (, Journal of Geophysical Research: Space Physics)
    Abstract The occurrence of small‐scale and intense ionospheric currents that can contribute to geomagnetically induced currents have recently been discovered. A difficulty in their characterization is that their signatures are often only observed at single widely spaced (typically 200–400 km) ground geomagnetic stations. These small‐scale structures motivate the examination of the maximum station separation required to fully characterize these small‐scale signatures. We analyze distributions of correlation coefficients between closely spaced mid‐latitude and auroral zone ground magnetometer stations spanning day to month long intervals to assess the separation distance at which geomagnetic signatures appear in only one station. Distributions were analyzed using periods that included low and high geomagnetic activity. We used data from pairs of magnetometer stations across North America within 200 km of each other, all of which were separated primarily latitudinally. Results show that while measurements remain largely similar up to separations of 200 km, large and frequent differences appear starting at around 130 km separation. Larger differences and lower correlations are observed during high geomagnetic activity, while low geomagnetic activity leads to frequent high correlation even past 200 km separation. Small but identifiable differences can appear in magnetometer data from stations as close as 35 km during high geomagnetic activity. We recommend future magnetometer array deployment in the auroral and sub‐auroral zone to have separations of 100–150 km. This enables the monitoring of large scale effects of geomagnetic storms, better temporal and spatial resolution of substorms, and observations of small‐scale current signatures. 
    more » « less
  5. ; (, The Journal of Creative Behavior)
    Abstract The current study addresses gaps in our understanding of the relationship between creative cognition, intelligence (IQ), and executive functioning (EF). Undergraduate students completed an IQ test, verbal and figural divergent thinking (DT) tests, and a self‐assessment of EF, across four study sessions. Participant data (N = 199) were analyzed using linear regression and PROCESS moderation models. Results demonstrated that EF interacts with IQ to predict figural and verbal DT in distinct ways, with different patterns emerging from different methods of scoring DT. Using traditional DT scoring,Gf(but notGc) significantly moderated the relationship between EF and scores on both verbal and figural DT tasks. Low EF was associated with diminished DT scores for those with lowGfscores, unrelated for those with relatively higherGf, and enhanced scores for those with the highestGf. Using originality ratio scores, low EF was associated with diminished originality in verbal DT responses for those with low IQ (bothGfandGc), unrelated for those with relatively higher IQ, and enhanced originality for those with the highestGc(but notGf) scores. Thus, there are several nuances in the way that EF interacts with IQ to predict DT. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email