A Gray‐Box Model for a Probabilistic Estimate of Regional Ground Magnetic Perturbations: Enhancing the NOAA Operational Geospace Model With Machine Learning. Issue 11 (31st October 2020)

• Record Type: Journal Article
• Authors: Camporeale, E.; Cash, M. D.; Singer, H. J.; Balch, C. C.; Huang, Z.; Toth, G.
• Is Part Of: Journal of geophysical research. Volume 125:Issue 11(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-10-31
• Subjects: geomagnetically induced currents -- Geospace model -- forecasting -- machine learning; Magnetospheric physics -- Periodicals; Space environment -- Periodicals; Cosmic physics -- Periodicals; Planets -- Atmospheres -- Periodicals; Heliosphere (Astrophysics) -- Periodicals; Geophysics -- Periodicals; 523.01
• DOI: 10.1029/2019JA027684
• Languages: English
• ISSNs: 2169-9380

Abstract

Abstract: We present a novel algorithm that predicts the probability that the time derivative of the horizontal component of the ground magnetic field d B / d t exceeds a specified threshold at a given location. This quantity provides important information that is physically relevant to geomagnetically induced currents (GICs), which are electric currents associated with sudden changes in the Earth's magnetic field due to space weather events. The model follows a "gray‐box" approach by combining the output of a physics‐based model with machine learning. Specifically, we combine the University of Michigan's Geospace model that is operational at the National Oceanic and Atmospheric Administration (NOAA) Space Weather Prediction Center, with a boosted ensemble of classification trees. We discuss the problem of recalibrating the output of the decision tree to obtain reliable probabilities. The performance of the model is assessed by typical metrics for probabilistic forecasts: Probability of Detection and False Detection, True Skill Statistic, Heidke Skill Score, and Receiver Operating Characteristic curve. We show that the ML‐enhanced algorithm consistently improves all the metrics considered. Key Points: We present a new model to forecast the maximum value of d B / d t over 20‐min intervals at specific locations The model enhances the output of the physics‐based Geospace model with a machine learning technique The model provides a probabilistic forecast of exceeding a predefined threshold at a given location