An official website of the United States government
Abstract We present a transformer model, named DeepHalo, to predict the occurrence of halo coronal mass ejections (CMEs). Our model takes as input an active region (AR) and a profile, where the profile contains a time series of data samples in the AR that are collected 24 hr before the beginning of a day, and predicts whether the AR would produce a halo CME during that day. Each data sample contains physical parameters, or features, derived from photospheric vector magnetic field data taken by the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory. We survey and match CME events in the Space Weather Database Of Notification, Knowledge, Information and the Large Angle and Spectrometric Coronagraph CME Catalog, and we compile a list of CMEs, including halo CMEs and nonhalo CMEs, associated with ARs in the period between 2010 November and 2023 August. We use the information gathered above to build the labels (positive vs. negative) of the data samples and profiles at hand, where the labels are needed for machine learning. Experimental results show that DeepHalo with a true skill statistic (TSS) score of 0.907 outperforms a closely related long short-term memory network with a TSS score of 0.821. To our knowledge, this is the first time that the transformer model has been used for halo CME prediction.
more »
« less
Prediction of Geoeffective CMEs Using SOHO Images and Deep Learning
Abstract The application of machine learning to the study of coronal mass ejections (CMEs) and their impacts on Earth has seen significant growth recently. Understanding and forecasting CME geoeffectiveness are crucial for protecting infrastructure in space and ensuring the resilience of technological systems on Earth. Here we present GeoCME, a deep-learning framework designed to predict, deterministically or probabilistically, whether a CME event that arrives at Earth will cause a geomagnetic storm. A geomagnetic storm is defined as a disturbance of the Earth’s magnetosphere during which the minimum Dst index value is less than −50 nT. GeoCME is trained on observations from the instruments including LASCO C2, EIT, and MDI on board the Solar and Heliospheric Observatory (SOHO), focusing on a dataset that includes 136 halo/partial halo CMEs in Solar Cycle 23. Using ensemble and transfer learning techniques, GeoCME is capable of extracting features hidden in the SOHO observations and making predictions based on the learned features. Our experimental results demonstrate the good performance of GeoCME, achieving a Matthew’s correlation coefficient of 0.807 and a true skill statistics score of 0.714 when the tool is used as a deterministic prediction model. When the tool is used as a probabilistic forecasting model, it achieves a Brier score of 0.094 and a Brier skill score of 0.493. These results are promising, showing that the proposed GeoCME can help enhance our understanding of CME-triggered solar-terrestrial interactions.
more »
« less
- PAR ID:
- 10575005
- Publisher / Repository:
- Solar Physics
- Date Published:
- Journal Name:
- Solar Physics
- Volume:
- 299
- Issue:
- 11
- ISSN:
- 0038-0938
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Geomagnetic storms are an important aspect of space weather and can result in significant impacts on space- and ground-based assets. The majority of strong storms are associated with the passage of interplanetary coronal mass ejections (ICMEs) in the near-Earth environment. In many cases, these ICMEs can be traced back unambiguously to a specific coronal mass ejection (CME) and solar activity on the frontside of the Sun. Hence, predicting the arrival of ICMEs at Earth from routine observations of CMEs and solar activity currently makes a major contribution to the forecasting of geomagnetic storms. However, it is clear that some ICMEs, which may also cause enhanced geomagnetic activity, cannot be traced back to an observed CME, or, if the CME is identified, its origin may be elusive or ambiguous in coronal images. Such CMEs have been termed “stealth CMEs”. In this review, we focus on these “problem” geomagnetic storms in the sense that the solar/CME precursors are enigmatic and stealthy. We start by reviewing evidence for stealth CMEs discussed in past studies. We then identify several moderate to strong geomagnetic storms (minimum Dst$$< -50$$ nT) in solar cycle 24 for which the related solar sources and/or CMEs are unclear and apparently stealthy. We discuss the solar and in situ circumstances of these events and identify several scenarios that may account for their elusive solar signatures. These range from observational limitations (e.g., a coronagraph near Earth may not detect an incoming CME if it is diffuse and not wide enough) to the possibility that there is a class of mass ejections from the Sun that have only weak or hard-to-observe coronal signatures. In particular, some of these sources are only clearly revealed by considering the evolution of coronal structures over longer time intervals than is usually considered. We also review a variety of numerical modelling approaches that attempt to advance our understanding of the origins and consequences of stealthy solar eruptions with geoeffective potential. Specifically, we discuss magnetofrictional modelling of the energisation of stealth CME source regions and magnetohydrodynamic modelling of the physical processes that generate stealth CME or CME-like eruptions, typically from higher altitudes in the solar corona than CMEs from active regions or extended filament channels.more » « less
-
The Sun constantly releases radiation and plasma into the heliosphere. Sporadically, the Sun launches solar eruptions such as flares and coronal mass ejections (CMEs). CMEs carry away a huge amount of mass and magnetic flux with them. An Earth-directed CME can cause serious consequences to the human system. It can destroy power grids/pipelines, satellites, and communications. Therefore, accurately monitoring and predicting CMEs is important to minimize damages to the human system. In this study we propose an ensemble learning approach, named CMETNet, for predicting the arrival time of CMEs from the Sun to the Earth. We collect and integrate eruptive events from two solar cycles, #23 and #24, from 1996 to 2021 with a total of 363 geoeffective CMEs. The data used for making predictions include CME features, solar wind parameters and CME images obtained from the SOHO/LASCO C2 coronagraph. Our ensemble learning framework comprises regression algorithms for numerical data analysis and a convolutional neural network for image processing. Experimental results show that CMETNet performs better than existing machine learning methods reported in the literature, with a Pearson product-moment correlation coefficient of 0.83 and a mean absolute error of 9.75 h.more » « less
-
Abstract We present observations and modeling results of the propagation and impact at Earth of a high-latitude, extended filament channel eruption that commenced on 2015 July 9. The coronal mass ejection (CME) that resulted from the filament eruption was associated with a moderate disturbance at Earth. This event could be classified as a so-called “problem storm” because it lacked the usual solar signatures that are characteristic of large, energetic, Earth-directed CMEs that often result in significant geoeffective impacts. We use solar observations to constrain the initial parameters and therefore to model the propagation of the 2015 July 9 eruption from the solar corona up to Earth using 3D magnetohydrodynamic heliospheric simulations with three different configurations of the modeled CME. We find the best match between observed and modeled arrival at Earth for the simulation run that features a toroidal flux rope structure of the CME ejecta, but caution that different approaches may be more or less useful depending on the CME–observer geometry when evaluating the space weather impact of eruptions that are extreme in terms of their large size and high degree of asymmetry. We discuss our results in the context of both advancing our understanding of the physics of CME evolution and future improvements to space weather forecasting.more » « less
-
Abstract Forecasting the arrival time of Earth‐directed coronal mass ejections (CMEs) via physics‐based simulations is an essential but challenging task in space weather research due to the complexity of the underlying physics and limited remote and in situ observations of these events. Data assimilation techniques can assist in constraining free model parameters and reduce the uncertainty in subsequent model predictions. In this study, we show that CME simulations conducted with the Space Weather Modeling Framework (SWMF) can be assimilated with SOHO LASCO white‐light (WL) observations and solar wind observations at L1 prior to the CME eruption to improve the prediction of CME arrival time. The L1 observations are used to constrain the model of the solar wind background into which the CME is launched. Average speed of CME shock front over propagation angles are extracted from both synthetic WL images from the Alfvén Wave Solar atmosphere Model (AWSoM) and the WL observations. We observe a strong rank correlation between the average WL speed and CME arrival time, with the Spearman's rank correlation coefficients larger than 0.90 for three events occurring during different phases of the solar cycle. This enables us to develop a Bayesian framework to filter ensemble simulations using WL observations, which is found to reduce the mean absolute error of CME arrival time prediction from about 13.4 to 5.1 hr. The results show the potential of assimilating readily available L1 and WL observations within hours of the CME eruption to construct optimal ensembles of Sun‐to‐Earth CME simulations.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1007/s11207-024-02385-w
