Abstract
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 important to protecting infrastructure and limiting the impact of geomagnetic storms on public safety and the economy. While GIC data is not readily available, variations in the magnetic field, dB=dt, measured by ground magnetometers can be used as a proxy for GICs.We are developing a set of neural networks to predict the horizontal component of the magnetic field, BH, from which dBH=dt is calculated. We apply two techniques for time series analysis to study the connection of solar wind and interplanetary magnetic field properties obtained from the OMNI dataset to the ground magnetic field perturbations. The analysis techniques include a feed-forward artificial neural network (ANN) and a long-short term memory (LSTM) neural network. Here we present a comparison of both models performance when predicting the BH component of the Ottawa (OTT) ground magnetometer for the year 2011 and 2015 and then when attempting to reconstruct the time series of BH for two geomagnetic storms that occurred on 5 August 2011 and 17 March 2015.
Highlights
Induced currents (GICs) are one of the most significant space weather effects due to their potential to damage the power grid and can cause widespread, long-term power outages
In this study we present a comparison of models using a feed-forward artificial neural network (ANN) with a builtin time dependence and a long short-term memory (LSTM) neural network to predict the ground magnetic field north and east components at the mid-latitude ground magnetometer station located in Ottawa (OTT)
These 2 years were selected for testing because they include storms from the Pulkkinen-Welling validation set for ground magnetic perturbations (Pulkkinen et al, 2013; Welling et al, 2018)
Summary
Induced currents (GICs) are one of the most significant space weather effects due to their potential to damage the power grid and can cause widespread, long-term power outages. Lotz and Cilliers (2015) developed a neural network based model using solar wind and IMF inputs and dB/dt measurements at a Southern hemisphere mid-latitude station as outputs They developed separate models for the north and east components of the geomagnetic field and found that fluctuations in the eastward component are more dependent on the interplanetary magnetic field (IMF) Bz. Similar to Wintoft et al (2015), they found reasonable predictions of the timing of intense fluctuations, with less accuracy as the storm evolved. We use solar wind and interplanetary magnetic field (IMF) data obtained from the OMNIWeb dataset available through NASA’s Space Physics Data Facility from 1995 through 2010 for the purpose of training and validation of the models, and from 2011 and 2015 for testing These 2 years were selected for testing because they include storms from the Pulkkinen-Welling validation set for ground magnetic perturbations (Pulkkinen et al, 2013; Welling et al, 2018). We emphasize that large variations are most likely to result in significant GIC events
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
