Search for: All records

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.

 

Forecasting ground magnetic field perturbations has been a long-standing goal of the space weather community. The availability of ground magnetic field data and its potential to be used in geomagnetically induced current studies, such as risk assessment, have resulted in several forecasting efforts over the past few decades. One particular community effort was the Geospace Environment Modeling (GEM) challenge of ground magnetic field perturbations that evaluated the predictive capacity of several empirical and first principles models at both mid- and high-latitudes in order to choose an operative model. In this work, we use three different deep learning models-a feed-forward neural network, a long short-term memory recurrent network and a convolutional neural network-to forecast the horizontal component of the ground magnetic field rate of change ( dB H / dt ) over 6 different ground magnetometer stations and to compare as directly as possible with the original GEM challenge. We find that, in general, the models are able to perform at similar levels to those obtained in the original challenge, although the performance depends heavily on the particular storm being evaluated. We then discuss the limitations of such a comparison on the basis that the original challenge was not designed with machine learning algorithms in mind. 

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. 

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. 

Abstract. Terrestrial ecliptic dayside observations of the exospheric Lyman-α column intensity between 3–15 Earth radii (RE) by UVIS/HDAC (UVIS – ultraviolet imaging spectrograph; HDAC – hydrogen-deuterium absorptioncell) Lyman-α photometer at CASSINI have been analyzed to derive the neutral exospheric H-density profile at the Earth's ecliptic dayside in this radial range. The data were measured during CASSINI's swing-by maneuver at the Earth on 18 August 1999 and are published by Werner et al. (2004). In this study the dayside HDAC Lyman-α observations published by Werner et al. (2004) are compared to calculated Lyman-α intensities based on the 3D H-density model derived from TWINS (Two Wide-angle Imaging Neutral-atom Spectrometers) Lyman-α observations between 2008–2010 (Zoennchen et al., 2015). It was found that both Lyman-α profiles show a very similar radial dependence in particular between 3–8 RE. Between 3.0–5.5 RE impact distance Lyman-α observations of both TWINS and UVIS/HDAC exist at the ecliptic dayside. In this overlapping region the cross-calibration of the HDAC profile against the calculated TWINS profile was done, assuming that the exosphere there was similar for both due to comparable space weather conditions. As a result of the cross-calibration the conversion factor between counts per second and rayleigh, fc=3.285 counts s−1 R−1, is determined for these HDAC observations. Using this factor the radial H-density profile for the Earth's ecliptic dayside was derived from the UVIS/HDAC observations, which constrained the neutral H density there at 10 RE to a value of 35 cm−3. Furthermore, a faster radial H-density decrease was found at distances above 8 RE (≈r-3) compared to the lower distances of 3–7 RE (≈r-2.37). This increased loss of neutral H above 8 RE might indicate a higher rate of H ionization in the vicinity of the magnetopause at 9–11 RE (near subsolar point) and beyond, because of increasing charge exchange interactions of exospheric H atoms with solar wind ions outside the magnetosphere. 

Dayside transients, such as hot flow anomalies, foreshock bubbles, magnetosheath jets, flux transfer events, and surface waves, are frequently observed upstream from the bow shock, in the magnetosheath, and at the magnetopause. They play a significant role in the solar wind-magnetosphere-ionosphere coupling. Foreshock transient phenomena, associated with variations in the solar wind dynamic pressure, deform the magnetopause, and in turn generates field-aligned currents (FACs) connected to the auroral ionosphere. Solar wind dynamic pressure variations and transient phenomena at the dayside magnetopause drive magnetospheric ultra low frequency (ULF) waves, which can play an important role in the dynamics of Earth’s radiation belts. These transient phenomena and their geoeffects have been investigated using coordinated in-situ spacecraft observations, spacecraft-borne imagers, ground-based observations, and numerical simulations. Cluster, THEMIS, Geotail, and MMS multi-mission observations allow us to track the motion and time evolution of transient phenomena at different spatial and temporal scales in detail, whereas ground-based experiments can observe the ionospheric projections of transient magnetopause phenomena such as waves on the magnetopause driven by hot flow anomalies or flux transfer events produced by bursty reconnection across their full longitudinal and latitudinal extent. Magnetohydrodynamics (MHD), hybrid, and particle-in-cell (PIC) simulations are powerful tools to simulate the dayside transient phenomena. This paper provides a comprehensive review of the present understanding of dayside transient phenomena at Earth and other planets, their geoeffects, and outstanding questions.

 

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.