Search for: All records

Abstract We introduce a new framework called Machine Learning (ML) based Auroral Ionospheric electrodynamics Model (ML‐AIM). ML‐AIM solves a current continuity equation by utilizing the ML model of Field Aligned Currents of Kunduri et al. (2020,https://doi.org/10.1029/2020JA027908), the FAC‐derived auroral conductance model of Robinson et al. (2020,https://doi.org/10.1029/2020JA028008), and the solar irradiance conductance model of Moen and Brekke (1993,https://doi.org/10.1029/92gl02109). The ML‐AIM inputs are 60‐min time histories of solar wind plasma, interplanetary magnetic fields (IMF), and geomagnetic indices, and its outputs are ionospheric electric potential, electric fields, Pedersen/Hall currents, and Joule Heating. We conduct two ML‐AIM simulations for a weak geomagnetic activity interval on 14 May 2013 and a geomagnetic storm on 7–8 September 2017. ML‐AIM produces physically accurate ionospheric potential patterns such as the two‐cell convection pattern and the enhancement of electric potentials during active times. The cross polar cap potentials (Φ_PC) from ML‐AIM, the Weimer (2005,https://doi.org/10.1029/2004ja010884) model, and the Super Dual Auroral Radar Network (SuperDARN) data‐assimilated potentials, are compared to the ones from 3204 polar crossings of the Defense Meteorological Satellite Program F17 satellite, showing better performance of ML‐AIM than others. ML‐AIM is unique and innovative because it predicts ionospheric responses to the time‐varying solar wind and geomagnetic conditions, while the other traditional empirical models like Weimer (2005,https://doi.org/10.1029/2004ja010884) designed to provide a quasi‐static ionospheric condition under quasi‐steady solar wind/IMF conditions. Plans are underway to improve ML‐AIM performance by including a fully ML network of models of aurora precipitation and ionospheric conductance, targeting its characterization of geomagnetically active times. 

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. 

Abstract One of the most significant observations associated with a sharp enhancement in solar wind dynamic pressure,, is the poleward expansion of the auroral oval and the closing of the polar cap. The polar cap shrinking over a wide range of magnetic local times (MLTs), in connection with an observed increase in ionospheric convection and the transpolar potential, led to the conclusion that the nightside reconnection rate is significantly enhanced after a pressure front impact. However, this enhanced tail reconnection has never been directly measured. We demonstrate the effect of a solar wind dynamic pressure front on the polar cap closure, and for the first time, measure the enhanced reconnection rate in the magnetotail, for a case occurring during southward background Interplanetary Magnetic Field (IMF) conditions. We use Polar Ultra‐Violet Imager (UVI) measurements to detect the location of the open‐closed field line boundary, and combine them with Assimilative Mapping of Ionospheric Electrodynamics (AMIE) potentials to calculate the ionospheric electric field along the polar cap boundary, and thus evaluate the variation of the dayside/nightside reconnection rates. We find a strong response of the polar cap boundary at all available MLTs, exhibiting a significant reduction of the open flux content. We also observe an immediate response of the dayside reconnection rate, plus a phased response, delayed by ∼15–20 min, of the nightside reconnection rate. Finally, we provide comparison of the observations with the results of the Open Geospace General Circulation Model (OpenGGCM), elucidating significant agreements and disagreements. 

Abstract The LEXI and SMILE missions will provide soft X‐ray images of the Earth's magnetosheath and cusps after their anticipated launch in 2023 and 2024, respectively. The IBEX mission showed the potential of an Energetic Neutral Atom (ENA) instrument to image dayside magnetosheath and cusps, albeit over the long hours required to raster an image with a single pixel imager. Thus, it is timely to discuss the two imaging techniques and relevant science topics. We simulate soft X‐ray and low‐ENA images that might be observed by a virtual spacecraft during two interesting solar wind scenarios: a southward turning of the interplanetary magnetic field and a sudden enhancement of the solar wind dynamic pressure. We employ the OpenGGCM global magnetohydrodynamics model and a simple exospheric neutral density model for these calculations. Both the magnetosheath and the cusps generate strong soft X‐rays and ENA signals that can be used to extract the locations and motions of the bow shock and magnetopause. Magnetopause erosion corresponds closely to the enhancement of dayside reconnection rate obtained from the OpenGGCM model, indicating that images can be used to understand global‐scale magnetopause reconnection. When dayside imagers are installed with high‐ENA inner‐magnetosphere and FUV/UV aurora imagers, we can trace the solar wind energy flow from the bow shock to the magnetosphere and then to the ionosphere in a self‐standing manner without relying upon other observatories. Soft X‐ray and/or ENA imagers can also unveil the dayside exosphere density structure and its response to space weather. 

Abstract Whistler mode chorus waves can scatter plasma sheet electrons into the loss cone and produce the Earth's diffuse aurora. Van Allen Probes observed plasma sheet electron injections and intense chorus waves on 24 November 2012. We use quasilinear theory to calculate the precipitating electron fluxes, demonstrating that the chorus waves could lead to high differential energy fluxes of precipitating electrons with characteristic energies of 10–30 keV. Using this method, we calculate the precipitating electron flux from 2012 to 2019 when the Van Allen Probes were near the magnetic equator and perform global surveys of electron precipitation under different geomagnetic conditions. The most significant electron precipitation due to chorus is found from the nightside to dawn sectors over 4 < L < 6.5. The average total precipitating energy flux is enhanced during disturbed conditions, with time‐averaged values reaching ~3–10 erg/cm²/s whenAE ≥ 500 nT. 

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. 

With the availability of data and computational technologies in the modern world, machine learning (ML) has emerged as a preferred methodology for data analysis and prediction. While ML holds great promise, the results from such models are not fully unreliable due to the challenges introduced by uncertainty. An ML model generates an optimal solution based on its training data. However, if the uncertainty in the data and the model parameters are not considered, such optimal solutions have a high risk of failure in actual world deployment. This paper surveys the different approaches used in ML to quantify uncertainty. The paper also exhibits the implications of quantifying uncertainty when using ML by performing two case studies with space physics in focus. The first case study consists of the classification of auroral images in predefined labels. In the second case study, the horizontal component of the perturbed magnetic field measured at the Earth’s surface was predicted for the study of Geomagnetically Induced Currents (GICs) by training the model using time series data. In both cases, a Bayesian Neural Network (BNN) was trained to generate predictions, along with epistemic and aleatoric uncertainties. Finally, the pros and cons of both Gaussian Process Regression (GPR) models and Bayesian Deep Learning (DL) are weighed. The paper also provides recommendations for the models that need exploration, focusing on space weather prediction.