AUTHOR=Blandin Matthew , Connor Hyunju K. , Öztürk Doğacan S. , Keesee Amy M. , Pinto Victor , Mahmud Md Shaad , Ngwira Chigomezyo , Priyadarshi Shishir 

TITLE=Multi-Variate LSTM Prediction of Alaska Magnetometer Chain Utilizing a Coupled Model Approach

JOURNAL=Frontiers in Astronomy and Space Sciences

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/astronomy-and-space-sciences/articles/10.3389/fspas.2022.846291

DOI=10.3389/fspas.2022.846291

ISSN=2296-987X

ABSTRACT=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 geomagnetic field strength at multiple ground magnetometer stations across Alaska provided by the SuperMAG database with an uptime 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 the magnitude of the north-south component (|$B_N$|). 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|. Linear regression models show consistent low values ( <0.5 ) for these thresholds while the neural networks indicate significant performance increases with average skill score values exceeding 0.5. To retain the full form of the geomagnetic field, a secondary so-called polarity model is utilized to predict the
direction. The polarity model is run in tandem with the neural networks predicting
geomagnetic field in an ensemble approach and results in a high correlation between
predicted and observed values at the College, Alaska magnetometer station (CMO). 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.