Global Geomagnetic Perturbation Forecasting Using Deep Learning

  title={Global Geomagnetic Perturbation Forecasting Using Deep Learning},
  author={Vishal Upendran and Panagiotis Tigas and Banafsheh Ferdousi and T{\'e}o Bloch and Mark C. M. Cheung and Siddha Ganju and Asti Bhatt and Ryan Mcgranaghan and Yarin Gal},
  journal={Space Weather},
Geomagnetically Induced Currents (GICs) arise from spatio‐temporal changes to Earth's magnetic field, which arise from the interaction of the solar wind with Earth's magnetosphere, and drive catastrophic destruction to our technologically dependent society. Hence, computational models to forecast GICs globally with large forecast horizon, high spatial resolution and temporal cadence are of increasing importance to perform prompt necessary mitigation. Since GIC data is proprietary, the time… 
On the Considerations of Using Near Real Time Data for Space Weather Hazard Forecasting
Space weather represents a severe threat to ground‐based infrastructure, satellites and communications. Accurately forecasting when such threats are likely (e.g., when we may see large induced


Comparison of Deep Learning Techniques to Model Connections Between Solar Wind and Ground Magnetic Perturbations
Geomagnetically induced currents (GIC) can drive power outages and damage power grid components while also affecting pipelines and train systems. Developing the ability to predict local GICs is
Solar Wind Prediction Using Deep Learning
Emanating from the base of the Sun's corona, the solar wind fills the interplanetary medium with a magnetized stream of charged particles whose interaction with the Earth's magnetosphere has space
Solar wind driven empirical forecast models of the time derivative of the ground magnetic field
Empirical models are developed to provide 10–30-min forecasts of the magnitude of the time derivative of local horizontal ground geomagnetic field (|d B h /d t |) over Europe. The models are driven
An empirical model of ground‐level geomagnetic perturbations
A new empirical model for predicting ground‐level geomagnetic perturbations has been developed. This model is based on global measurements of the magnetic field at multiple stations in the Northern
Ground geomagnetic field and GIC response to March 17, 2015, storm
The St. Patrick’s Day geomagnetic storm on March 17, 2015, has been chosen by the space community for synergetic analysis to build a more comprehensive picture of the storm’s origin and evolution.
Statistical maps of geomagnetic perturbations as a function of the interplanetary magnetic field
[1] Mappings of geomagnetic perturbations are shown for different combinations of the solar wind velocity, interplanetary magnetic field (IMF), and dipole tilt angle (season). Average maps were
A Gray‐Box Model for a Probabilistic Estimate of Regional Ground Magnetic Perturbations: Enhancing the NOAA Operational Geospace Model With Machine Learning
A novel algorithm is presented that predicts the probability that the time derivative of the horizontal component of the ground magnetic field dB/dt exceeds a specified threshold at a given location, and it is shown that the ML‐enhanced algorithm consistently improves all the metrics considered.
Sensitivity of geomagnetically induced currents to varying auroral electrojet and conductivity models
  • C. Beggan
  • Geology, Physics
    Earth, Planets and Space
  • 2015
Geomagnetically induced currents (GIC) are created by the interaction of rapid changes in the magnitude of the magnetic field with the conductive subsurface of the Earth. The changing magnetic field
Exploring predictive performance: A reanalysis of the geospace model transition challenge
The Pulkkinen et al. (2013) study evaluated the ability of five different geospace models to predict surface dB/dt as a function of upstream solar drivers. This was an important step in the
A Study of Intense Local dB/dt Variations During Two Geomagnetic Storms
Interactions between the solar wind and the Earth's magnetosphere manifest many important space weather phenomena. In this paper, magnetosphere‐ionosphere drivers of intense dB/dt produced during