Multi‐Hour‐Ahead Dst Index Prediction Using Multi‐Fidelity Boosted Neural Networks

Abstract

The Disturbance storm time (Dst) is a geomagnetic index related to the perturbation of the geomagnetic field at low latitudes (Burton et al., 1975;Rostoker, 1972). Currently, Dst is defined by using geomagnetic field measurements from four equatorial ground magnetometers: Hermanus, Honolulu, San Juan and Kakioka (Sugiura & Kamei, 1991). Dst has been widely used for monitoring geomagnetic storms, which pose one of the most severe space weather risks to our space-borne and ground-based electronic instruments, such as global navigation satellite systems and radio transmission systems (Z. Li et al., 2021;Wan et al., 2021).A short-term prediction of Dst is produced operationally at the NOAA Space Weather Prediction Center by means of a physics-based model (the Space Weather Modeling Framework developed at the University of Michigan, (Tóth et al., 2005)). A longer lead-time operational Dst forecast is provided by Space Environment Technologies, using the Anemomilos model (Tobiska et al., 2013). Dst is also used as an essential input for forecasting thermosphere mass density and ionospheric parameters, and to parameterize several empirical models. The following is a non-exhaustive list of models that use Dst as one of their inputs: O'Brien and Moldwin ( 2003) empirically estimate the location of the plasmapause; Agapitov et al. (2015) derive a statistical model for the lower band chorus distribution; S. Li et al. (2016) estimate the ionospheric global electron content storm-time response; Boardsen et al. (2000) derive an empirical model of the high-latitude magnetopause; and, Zhao et al. (2018) derive a model of radiation belt electron pitch-angle distributions.A large amount of literature has been devoted to Dst prediction, notably using empirical and machine learning techniques (Camporeale, 2019). Lundstedt et al. (2002) first attempted to implement a multi-layer perception neural network to forecast Dst 1 hour ahead using interplanetary magnetic field (IMF) data. Several researchers presented models to extend the Dst forecast up to 6 hr in advance (Bala & Reiff, 2012;Lazzús et al., 2017;Saiz et al., 2008). A Gaussian Process model was introduced by Chandorkar et al. (2017) and combined with a long short-term memory (LSTM) architecture in Gruet et al. (2018) to provide probabilistic predictions up to 6 hours in advance. An ensemble learning algorithm was applied by Xu et al. (2020) for the same purpose. Laperre et al. (2020) evaluated the performance of a LSTM model based on a Dynamical Time Warping metric as the cost function.

Forecasting Geoffective Events from Solar Wind Data and Evaluating the Most Predictive Features through Machine Learning Approaches

“…We pointed out that when SYM-H is not used as a feature, the performances are low: this is due to the fact that when a geomagnetic storm is in place, then the SYM-H is below −50 nT, and such information helps the network to learn that if in the previous hour the SYM-H is below −50 nT, the probability that it is below this threshold in the next hour is high. Further, we made the comparison with a simple persistence model (as in Hu et al 2023), and the performance in terms of TSS are comparable with the ones obtained by the LSTM model when the SYM-H is included as an additional feature (the persistence model provides a mean TSS on the same test sets about 0.8361 ± 0.028). However, it should be noted that the persistence model can basically predict whether in the next hour the Earth's magnetosphere will still be perturbed (SYM-H < −50 nT), that is, it is able to ascertain the presence of the recovery phase once the geomagnetic storm has already started.…”

The Response of Ionospheric Currents to External Drivers Investigated Using a Neural Network‐Based Model

“…Training the model with imbalanced EIC data, the mean square error (MSE) and a focal loss (L4) are utilized as loss functions to be minimized, for comparatively studying the improvement of the imbalanced regression by different loss functions. Many other machine learning models dealt with the imbalance problem by manually selecting only extreme events to improve the performance, for example, (Hu et al., 2023; Ren et al., 2023). We avoid providing such a priori knowledge to the predictive model, such that our model is robust to provide continuous predictions/forecasts in the real operational environment.…”

A Framework for Evaluating Geomagnetic Indices Forecasting Models

“…Geomagnetic indices such as Dst, Kp, SYM‐H, and others, are essential for understanding geomagnetic conditions, but their study often requires additional data sources. Depending on the focus of the research, this may include solar imagery (Hu et al., 2022), solar wind parameters (Shprits et al., 2019), and other measurements to enhance the forecasting and analysis models (Hu et al., 2023). The development of the models is inherently dependent on the availability of these supplementary data.…”