Search for: All records

Abstract Solar wind particles interact with the Earth's magnetic field and can cause rapid changes in the magnetic field on the ground. This can result in Geomagnetically Induced Currents capable of causing significant damage to infrastructure, making it vital to predict when and where the fluctuations will occur so the impact can be limited. The fluctuations can occur on both a large and highly localized scale, further complicating precise predictions. Machine learning (ML) techniques have emerged as an effective method of predicting space weather phenomena, with their largest complication being their lack of explainability. Here we seek to use such ML methods, combined with a model explainability technique called SHapley Additive exPlanation to both predict and times of extreme localization. Using L1 solar wind data and magnetometer data from SuperMAG, we train two different types of models, one predicting extreme and one predicting large Region‐to‐Specific Difference (RSD). We are seeking to forecast the maximum of RSD and within a rolling 60‐min window, beginning 30 min in the future. The models perform well across a variety of latitudes and Magnetic Local times. While traditional drivers of space weather ( and ) are important drivers of the ML models, other not often examined parameters (particularly ) exhibit non‐uniform spatial and latitudinal dependencies which cannot be attributed to correlation with more influential parameters. Additionally, the inertia of the internal geomagnetic field on a regional scale exhibits a more nuanced behavior compared to previous studies on individual magnetometer stations. 

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. 

Geomagnetically induced currents (GICs) pose a significant space weather hazard, driven by geomagnetic field variation due to the coupling of the solar wind to the magnetosphere-ionosphere system. Extensive research has been dedicated to understanding ground-level geomagnetic field perturbations as a GIC proxy. Still, the non-uniform aspect of geomagnetic fluctuations make it difficult to fully characterize the ground-level magnetic field across large regions of the globe. Here, we focus on localized geomagnetic disturbances (LGMDs) in the North American region and specify the degree to which these disturbances are localized. Employing the electrodynamics-informed Spherical Elementary Current Systems (SECS) method, we spatially interpolate magnetic field perturbations between ground-based magnetometer stations. In this way, we represent the ground magnetic field as a series of heatmaps at high temporal and spatial resolution. We leverage heatmaps from storm time during solar cycle 24 to automatically identify LGMDs. We build a statistical picture of the frequency with which LGMDs occur, their scale sizes, and their latitude-longitude aspect ratios. Additionally, we use an information theory approach to quantify the dependence of these three attributes on the phase of the solar cycle. We find no clear influence of the solar cycle on any of the three attributes. We offer some avenues toward explaining why LGMDs might behave broadly the same whether they arise during solar maximum or solar minimum. 

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.