Machine learning is nowadays the methodology of choice for flare forecasting and supervised techniques, in both their traditional and deep versions, are becoming the most frequently used ones for prediction in this area of space weather. Yet, machine learning has not been able so far to realize an operating warning system for flaring storms and the scientific literature of the last decade suggests that its performances in the prediction of intense solar flares are not optimal.
The main difficulties related to forecasting solar flaring storms are probably two. First, most methods are conceived to provide probabilistic predictions and not to send binary yes/no indications on the consecutive occurrence of flares along an extended time range. Second, flaring storms are typically characterized by the explosion of high energy events, which are seldom recorded in the databases of space missions; as a consequence, supervised methods are trained on very imbalanced historical sets, which makes them particularly ineffective for the forecasting of intense flares.
Yet, in this study we show that supervised machine learning could be utilized in a way to send timely warnings about the most violent and most unexpected flaring event of the last decade, and even to predict with some accuracy the energy budget daily released by magnetic reconnection during the whole time course of the storm. Further, we show that the combination of sparsity-enhancing machine learning and feature ranking could allow the identification of the prominent role that energy played as an Active Region property in the forecasting process.
In the early days of 2017 September, an exceptionally energetic solar active region AR12673 aroused great interest in the solar physics community. It produced four X class flares, more than 20 CMEs and an intense geomagnetic storm, for which the peak value of the Dst index reached up to -142nT at 2017 September 8 02:00 UT. In this work, we check the interplanetary and solar source of this intense geomagnetic storm. We find that this geomagnetic storm was mainly caused by a shock-ICME complex structure, which was formed by a shock driven by the 2017 September 6 CME propagating into a previous I…
Cosmic Ray Inter-Station Correlation Variations as Precursors of Geomagnetic Storms: A Statistical Study and Multi-Parameter Early Warning Framework
College of Physics and Optoelectronic Engineering, Ocean University of China（中国海洋大学物理与光电工程学院）；Engineering Research Center of Advanced Marine Physical Instruments and Equipment of Ministry of Education（教育部先进海洋物理仪器装备工程研究中心）；Qingdao Key Laboratory of Advanced Optoelectronics（青岛先进光电学重点实验室）
Coronal mass ejections (CMEs) are the primary sources of intense disturbances at Earth, where their geo-effectiveness is largely determined by their dynamic pressure and internal magnetic field, which can be significantly altered during interactions with other CMEs in interplanetary space. We analyse three successive CMEs that erupted from the Sun during September 4-6, 2017, investigating the role of CME-CME interactions as source of the associated intense geomagnetic storm (Dst_min=-142 nT on September 7). To quantify the impact of interactions on the (geo-)effectiveness of individual CMEs, w…
Dim red aurora at low magnetic latitudes is a visual and recognized manifestation of geomagnetic storms. The great low-latitude auroral displays seen throughout East Asia on 16-18 September 1770 are considered to manifest one of the greatest storms. Recently found 111 historical documents in East Asia attest that these low-latitude auroral displays were succeeding for almost 9 nights during 10-19 September 1770 in the lowest magnetic latitude areas (< 30°). This suggests that the duration of the great magnetic storm is much longer than usual. Sunspot drawings from 1770 reveals the fact that su…
The Carrington storm (September 1/2, 1859) is one of the largest magnetic storms ever observed and it has caused global auroral displays in low-latitude areas, together with a series of multiple magnetic storms during August 28 and September 4, 1859. In this study, we revisit contemporary auroral observation records to extract information on their elevation angle, color, and direction to investigate this stormy interval in detail. We first examine their equatorward boundary of "auroral emission with multiple colors" based on descriptions of elevation angle and color. We find that their locatio…
On 2012 September 30 - October 1 the Earth underwent a two-step geomagnetic storm. We examine the Sun-to-Earth characteristics of the coronal mass ejections (CMEs) responsible for the geomagnetic storm with combined heliospheric imaging and in situ observations. The first CME, which occurred on 2012 September 25, is a slow event and shows an acceleration followed by a nearly invariant speed in the whole Sun-Earth space. The second event, launched from the Sun on 2012 September 27, exhibits a quick acceleration, then a rapid deceleration and finally a nearly constant speed, a typical Sun-to-Ear…
The origin of hard X-rays and gamma-rays emitted from the solar atmosphere during occulted solar flares is still debated. The hard X-ray emissions could come from flaring loop tops rising above the limb or Coronal Mass Ejections (CME) shock waves, two by-products of energetic solar storms. For the shock scenario to work, accelerated particles must be released on magnetic field lines rooted on the visible disk and precipitate. We present a new Monte Carlo code that computes particle acceleration at shocks propagating along large coronal magnetic loops. A first implementation of the model is car…
Technical University of Cluj-Napoca（克卢日-纳波卡技术大学）；High Altitude Observatory, National Center for Atmospheric Research（美国国家大气研究中心高空天文台）；Astronomical Institute of the Romanian Academy（罗马尼亚科学院天文研究所）
Coronal mass ejections (CMEs) are the most geoeffective space weather phenomena, being associated with large geomagnetic storms, having the potential to cause disturbances to telecommunication, satellite network disruptions, power grid damages and failures. Thus, considering these storms' potential effects on human activities, accurate forecasts of the geoeffectiveness of CMEs are paramount. This work focuses on experimenting with different machine learning methods trained on white-light coronagraph datasets of close to sun CMEs, to estimate whether such a newly erupting ejection has the poten…
Cosmic-Ray-Constrained LSTM Model for Geomagnetic Storm Prediction
College of Physics and Optoelectronic Engineering, Ocean University of China（中国海洋大学物理与光电工程学院）；School of Mathematics and Computer Science, Yunnan Minzu University（云南民族大学数学与计算机科学学院）；College of Automation, Nanjing University of Information Science and Technology（南京信息工程大学自动化学院）；State Key Laboratory of Solar Activity and Space Weather, National Astronomical Observatories, Chinese Academy of Sciences（中国科学院国家天文台太阳活动与空间天气国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）
INAF - Osservatorio Astrofisico di Torino（意大利国家天体物理研究所-都灵天体物理天文台）
Operational flare forecasting aims at providing predictions that can be used to make decisions, typically at a daily scale, about the space weather impacts of flare occurrence. This study shows that video-based deep learning can be used for operational purposes when the training and validation sets used for the network optimization are generated while accounting for the periodicity of the solar cycle. Specifically, the paper describes an algorithm that can be applied to build up sets of active regions that are balanced according to the flare class rates associated to a specific cycle phase. Th…
Here we report evidence of a large solar filament eruption on 2013, September 29. This smooth eruption, which passed without any previous flare, formed after a two-ribbon flare and a coronal mass ejection towards Earth. The coronal mass ejection generated a moderate geomagnetic storm on 2013, October 2 with very serious localized effects. The whole event passed unnoticed to flare-warning systems. We have conducted multi-wavelength analyses of the Solar Dynamics Observatory through Atmospheric Imaging Assembly (AIA) and Helioseismic and Magnetic Imager (HMI) data. The AIA data on 304, 193, 211,…
