arXiv subjects

Manolis K. Georgoulis

Publications and source records attributed to Manolis K. Georgoulis.

At least 19 recordsLinked to original sources

arXiv2026

Brightenings AnD Polarity Inversion Tracking (BADPIT) method for studying solar active region evolution before major solar flares

This study investigates the relationship between extreme ultraviolet (EUV) transient brightenings (TBs) and the onset of GOES X-class solar flares in active regions (ARs). We introduce the Brightenings AnD Polarity Inversion Tracking (BADPIT) method that detects TBs across multiple SDO/AIA channels. To identify TBs, we impose two independent thresholds: a 3-(sigma) intensity-based criterion and a power-law divergence approach. We apply the BADPIT method to datasets of a flaring and a non-flaring AR for 24 hours as a pathfinder to a comprehensive statistical study for a complete performance verification: the flare-productive AR 11429 and the quiescent AR 13186, both sharing a similar Hale sunspot classification. Preliminary results are encouraging: significantly more TBs are detected in the flaring AR, with up to five times more 3-(sigma) thresholded TBs, while power-law thresholded events were frequent only in the flaring AR and mostly absent in the non-flaring AR. We find that both the power-law threshold method and the 3-(sigma) method can be useful diagnostic tools for distinguishing between imminent flaring or not, several hours before the onset of major solar flares.

astro-ph.SR↗

arXiv2026

Predicting Associations between Solar Flares and Coronal Mass Ejections Using SDO/HMI Magnetograms and a Hybrid Neural Network

Solar eruptions, including flares and coronal mass ejections (CMEs), have a significant impact on Earth. Some flares are associated with CMEs, and some flares are not. The association between flares and CMEs is not always obvious. In this study, we propose a new deep learning method, specifically a hybrid neural network (HNN) that combines a vision transformer with long short-term memory, to predict associations between flares and CMEs. HNN finds spatio-temporal patterns in the time series of line-of-sight magnetograms of solar active regions (ARs) collected by the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory and uses the patterns to predict whether a flare projected to occur within the next 24 hours will be eruptive (i.e., CME-associated) or confined (i.e., not CME-associated). Our experimental results demonstrate the good performance of the HNN method. Furthermore, the results show that magnetic flux cancellation in polarity inversion line regions may well play a role in triggering flare-associated CMEs, a finding consistent with literature.

astro-ph.SR↗

arXiv2025

Enhancing Explainability in Solar Energetic Particle Event Prediction: A Global Feature Mapping Approach

Solar energetic particle (SEP) events, as one of the most prominent manifestations of solar activity, can generate severe hazardous radiation when accelerated by solar flares or shock waves formed aside from coronal mass ejections (CMEs). However, most existing data-driven methods used for SEP predictions are operated as black-box models, making it challenging for solar physicists to interpret the results and understand the underlying physical causes of such events rather than just obtain a prediction. To address this challenge, we propose a novel framework that integrates global explanations and ad-hoc feature mapping to enhance model transparency and provide deeper insights into the decision-making process. We validate our approach using a dataset of 341 SEP events, including 244 significant (>=10 MeV) proton events exceeding the Space Weather Prediction Center S1 threshold, spanning solar cycles 22, 23, and 24. Furthermore, we present an explainability-focused case study of major SEP events, demonstrating how our method improves explainability and facilitates a more physics-informed understanding of SEP event prediction.

cs.LG↗

arXiv2025

A Multimodal Tiered Magnetic Polarity Inversion Features Dataset for Space Weather Forecasting

This article presents a publicly available, multimodal, tiered magnetic polarity inversion lines (MPILs) dataset extracted from the Solar Dynamics Observatory's (SDO) Helioseismic and Magnetic Imager (HMI) Active Region Patches (SDO/HMI HARP) between May 2010 and April 2025. The dataset comprises four distinct tiers, each generated by running our detection methodology with four different magnetic field strength thresholds to capture nuanced variations in MPIL features at multiple levels of detail. In total, we provide 6,695 HARP series mapped using the Lambert Cylindrical Equal Area (CEA) projection at a 12-minute cadence. This tiered approach ensures that each tier captures specific sensitivities to polarity changes, enabling researchers to tailor their analyses to a range of scientific and operational objectives. In each threshold tier, we offer six binary MPIL masks associated with heliophysics and space weather forecasting, including MPIL, Region of Polarity Inversion (RoPI), positive and negative polarity regions, unsigned polarity regions, and MPIL convex hulls. Furthermore, structured metadata in the form of multivariate time series is included, allowing users to track and analyze MPIL properties over time.

astro-ph.SR↗

arXiv2025

Solar Alfvenic Pulses and Mesoscale Solar Wind

Large-scale solar ejections are well understood, but the extent to which small-scale solar features directly influence the solar wind remains an open question, primarily due to the challenges of tracing these small-scale ejections and their impact. Here, we measure the fine-scale motions of network bright points along a coronal hole boundary in high-resolution H-alpha images from the 1.6m Goode Solar Telescope at Big Bear Solar Observatory to quantify the agitation of open flux tubes into generating Alfvenic pulses. We combine the motion, magnetic flux, and activity duration of the flux tubes to estimate the energy content carried by individual Alfvenic pulses, which is ~10+25 erg, adequately higher than the energies ~10+23 erg estimated for the magnetic switchbacks observed by the Parker Solar Probe (PSP). This implies the possibility that the surface-generated Alfvenic pulses could reach the solar wind with sufficient energy to generate switchbacks, even though some of then are expected to be reflected back in the stratified solar atmosphere. Alfvenic pulses further reproduce for the first time other properties of switchbacks, including the filling factor above ~8% at granular and supergranular scales, which correspond best to the lower end of the mesoscale structure. This quantitative result for solar energy output in the form of Alfvenic pulses through magnetic funnels provides a crucial clue to the ongoing debate about the dynamic cycle of energy exchange between the Sun and the mesoscale solar wind that has been raised, but has not been adequately addressed, by PSP near-Sun observations.

astro-ph.SR↗

arXiv2025

How the CME on 21 April 2023 Triggered the First Severe Geomagnetic Storm of Solar Cycle 25

The first severe (G4) geomagnetic storm of Solar Cycle 25 occurred on 23-24 April 2023, following the arrival of a Coronal Mass Ejection (CME) on 23 April. The characteristics of this CME, measured from coronagraphs (speed and mass), did not indicate that it would trigger such an intense geomagnetic storm. In this work, our aim is to understand why this CME led to such a geoeffective outcome. Our analysis spans from the source active region to the corona and inner heliosphere through 1 au using multiwavelength, multi-viewpoint remote sensing observations and in situ data. We find that rotation and possibly deflection of the CME resulted in an axial magnetic field nearly parallel to the ecliptic plane during the Earth encounter, which might explain the storm's severity. Additionally, we find that imaging away from the Sun-Earth line is crucial in hindcasting the CME Time-of-Arrival at Earth. The position (0.39 au) and detailed images from the SoloHI telescope onboard the Solar Orbiter mission, in combination with SOHO and STEREO images, helped decisively with the three-dimensional (3D) reconstruction of the CME.

astro-ph.SR↗

arXiv2024

Generative Simulations of The Solar Corona Evolution With Denoising Diffusion : Proof of Concept

The solar magnetized corona is responsible for various manifestations with a space weather impact, such as flares, coronal mass ejections (CMEs) and, naturally, the solar wind. Modeling the corona's dynamics and evolution is therefore critical for improving our ability to predict space weather In this work, we demonstrate that generative deep learning methods, such as Denoising Diffusion Probabilistic Models (DDPM), can be successfully applied to simulate future evolutions of the corona as observed in Extreme Ultraviolet (EUV) wavelengths. Our model takes a 12-hour video of an Active Region (AR) as input and simulate the potential evolution of the AR over the subsequent 12 hours, with a time-resolution of two hours. We propose a light UNet backbone architecture adapted to our problem by adding 1D temporal convolutions after each classical 2D spatial ones, and spatio-temporal attention in the bottleneck part. The model not only produce visually realistic outputs but also captures the inherent stochasticity of the system's evolution. Notably, the simulations enable the generation of reliable confidence intervals for key predictive metrics such as the EUV peak flux and fluence of the ARs, paving the way for probabilistic and interpretable space weather forecasting. Future studies will focus on shorter forecasting horizons with increased spatial and temporal resolution, aiming at reducing the uncertainty of the simulations and providing practical applications for space weather forecasting. The code used for this study is available at the following link: https://github.com/gfrancisco20/video_diffusion

astro-ph.SR↗

arXiv2024

Case studies on pre-eruptive X-class flares using R-value in the lower solar atmosphere

The R-value is a measure of the strength of photospheric magnetic Polarity Inversion Lines (PILs) in Active Regions (ARs). This work investigates the possibility of a relation between R-value variations and the occurrence of X-class flares in ARs, not in the solar photosphere, as usual, but above it in regions, closer to where flares occur. The modus operandi is to extrapolate the Solar Dynamic Observatory's (SDO) Helioseismic and Magnetic Imager (HMI) magnetogram data up to a height of 3.24 Mm above the photosphere and then compute the R-value based on the extrapolated magnetic field. Recent studies have shown that certain flare-predictive parameters such as the horizontal gradient of the vertical magnetic field and magnetic helicity may improve flare prediction lead times significantly if studied at a specific height range above the photosphere, called the Optimal Height Range (OHR). Here we define the OHR as a collection of heights where a sudden but sustained increase in R-value is found. For the eight case studies discussed in this paper, our results indicate that it is possible for OHRs to exist in the low solar atmosphere (between 0.36 - 3.24 Mm), where R-value spikes occur 48-68 hrs before the first X-class flare of an emerging AR. The temporal evolution of R-value before the first X-class flare for an emerging AR is also found to be distinct from that of non-flaring ARs. For X-class flares associated with non-emerging ARs, an OHR could not be found.

astro-ph.SR↗

arXiv2024

Assessment of the near-Sun magnetic field of the 10 March 2022 coronal mass ejection observed by Solar Orbiter

We estimate the near-Sun axial magnetic field of a coronal mass ejection (CME) on 10 March 2022. Solar Orbiter's in situ measurements, 7.8 degrees east of the Sun-Earth line at 0.43 AU, provided a unique vantage point, along with the WIND measurements at 0.99 AU. We determine a single power-law index from near-Sun to L1, including in situ measurements from both vantage points. We tracked the temporal evolution of the instantaneous relative magnetic helicity of the source active region (AR), NOAA AR 12962. By estimating the helicity budget of the pre-and post-eruption AR, we estimated the helicity transported to the CME. Assuming a Lundquist flux-rope model and geometrical parameters obtained through the graduated cylindrical shell (GCS) CME forward modelling, we determined the CME axial magnetic field at a GCS-fitted height. Assuming a power-law variation of the axial magnetic field with heliocentric distance, we extrapolated the estimated near-Sun axial magnetic field to in situ measurements at 0.43 AU and 0.99 AU. The net helicity difference between the post-and pre-eruption AR is $(-7.1 \pm 1.2) \times 10^{41} \mathrm{Mx^{2}}$, which is assumed to be bodily transported to the CME. The estimated CME axial magnetic field at a near-Sun heliocentric distance of 0.03 AU is 2067 $\pm$ 405 nT. From 0.03 AU to L1, a single power-law falloff, including both vantage points at 0.43 AU and 0.99 AU, gives an index $-1.23 \pm 0.18$. We observed a significant decrease in the pre-eruptive AR helicity budget. Extending previous studies on inner-heliospheric intervals from 0.3 AU to $\sim$1 AU, referring to estimates from 0.03 AU to measurements at $\sim$1 AU. Our findings indicate a less steep decline in the magnetic field strength with distance compared to previous studies, but they align with studies that include near-Sun in situ magnetic field measurements, such as from Parker Solar Probe.

astro-ph.SR↗

arXiv2024

Magnetogram-to-Magnetogram: Generative Forecasting of Solar Evolution

Investigating the solar magnetic field is crucial to understand the physical processes in the solar interior as well as their effects on the interplanetary environment. We introduce a novel method to predict the evolution of the solar line-of-sight (LoS) magnetogram using image-to-image translation with Denoising Diffusion Probabilistic Models (DDPMs). Our approach combines "computer science metrics" for image quality and "physics metrics" for physical accuracy to evaluate model performance. The results indicate that DDPMs are effective in maintaining the structural integrity, the dynamic range of solar magnetic fields, the magnetic flux and other physical features such as the size of the active regions, surpassing traditional persistence models, also in flaring situation. We aim to use deep learning not only for visualisation but as an integrative and interactive tool for telescopes, enhancing our understanding of unexpected physical events like solar flares. Future studies will aim to integrate more diverse solar data to refine the accuracy and applicability of our generative model.

astro-ph.SR↗

arXiv2024

Magnetic Helicity Signs and Flaring Propensity: Comparing Force-free Parameter with the Helicity signs of Hα Filaments and X-ray Sigmoids

Sigmoids produce strong eruptive events. Earlier studies have shown that the ICME axial magnetic field Bz can be predicted with some credibility by observing the corresponding filament or the polarity inversion line in the region of eruption and deriving the magnetic field direction from that. Sigmoids are coronal structures often associated with filaments in the sigmoidal region. In this study, firstly we compare filament chirality with sigmoid handedness to observe their correlation. Secondly, we perform non-linear force-free approximations of the coronal magnetic connectivity using photospheric vector magnetograms underneath sigmoids to obtain a weighted-average value of the force-free parameter and to correlate it with filament chirality and the observed coronal sigmoid handedness. Importantly, we find that the sigmoids and their filament counterparts do not always have the same helicity signs. Production of eruptive events by regions that do not have the same signs of helicities is $\sim$3.5 times higher than when they do. A case study of magnetic energy/ helicity evolution in NOAA AR 12473 is also presented.

astro-ph.SR↗

arXiv2023

Explainable Deep Learning-based Solar Flare Prediction with post hoc Attention for Operational Forecasting

This paper presents a post hoc analysis of a deep learning-based full-disk solar flare prediction model. We used hourly full-disk line-of-sight magnetogram images and selected binary prediction mode to predict the occurrence of $\geq$M1.0-class flares within 24 hours. We leveraged custom data augmentation and sample weighting to counter the inherent class-imbalance problem and used true skill statistic and Heidke skill score as evaluation metrics. Recent advancements in gradient-based attention methods allow us to interpret models by sending gradient signals to assign the burden of the decision on the input features. We interpret our model using three post hoc attention methods: (i) Guided Gradient-weighted Class Activation Mapping, (ii) Deep Shapley Additive Explanations, and (iii) Integrated Gradients. Our analysis shows that full-disk predictions of solar flares align with characteristics related to the active regions. The key findings of this study are: (1) We demonstrate that our full disk model can tangibly locate and predict near-limb solar flares, which is a critical feature for operational flare forecasting, (2) Our candidate model achieves an average TSS=0.51$\pm$0.05 and HSS=0.38$\pm$0.08, and (3) Our evaluation suggests that these models can learn conspicuous features corresponding to active regions from full-disk magnetograms.

cs.LG↗

arXiv2022

Changes of Magnetic Energy and Helicity in Solar Active Regions from Major Flares

Magnetic free energy powers solar flares and coronal mass ejections (CMEs), and the buildup of magnetic helicity might play a role in the development of unstable structures that subsequently erupt. To better understand the roles of energy and helicity in large flares and eruptions, we have characterized the evolution of magnetic energy and helicity associated with 21 X-class flares from 2010 to 2017. Our sample includes both confined and eruptive events, with 6 and 15 in each category, respectively. Using HMI vector magnetic field observations from several hours before to several hours after each event, we employ (a) the Differential Affine Velocity Estimator for Vector Magnetograms (DAVE4VM) to determine the photospheric fluxes of energy and helicity, and (b) non-linear force-free field (NLFFF) extrapolations to estimate the coronal content of energy and helicity in source-region fields. Using Superposed Epoch analysis (SPE), we find, on average: (1) decreases in both magnetic energy and helicity, in both photospheric fluxes and coronal content, that persist for a few hours after eruptions, but no clear changes, notably in relative helicity, for confined events; (2) significant increases in the twist of photospheric fields in eruptive events, with twist uncertainties too large in confined events to constrain twist changes (and lower overall twist in confined events); and (3) on longer time scales (event time +12 hours), replenishment of free magnetic energy and helicity content to near pre-event levels for eruptive events. For eruptive events, magnetic helicity and free energy in coronal models clearly decrease after flares, with the amounts of decrease proportional to each region's pre-flare content.

astro-ph.SR↗

arXiv2022

Towards Coupling Full-disk and Active Region-based Flare Prediction for Operational Space Weather Forecasting

Solar flare prediction is a central problem in space weather forecasting and has captivated the attention of a wide spectrum of researchers due to recent advances in both remote sensing as well as machine learning and deep learning approaches. The experimental findings based on both machine and deep learning models reveal significant performance improvements for task specific datasets. Along with building models, the practice of deploying such models to production environments under operational settings is a more complex and often time-consuming process which is often not addressed directly in research settings. We present a set of new heuristic approaches to train and deploy an operational solar flare prediction system for $\geq$M1.0-class flares with two prediction modes: full-disk and active region-based. In full-disk mode, predictions are performed on full-disk line-of-sight magnetograms using deep learning models whereas in active region-based models, predictions are issued for each active region individually using multivariate time series data instances. The outputs from individual active region forecasts and full-disk predictors are combined to a final full-disk prediction result with a meta-model. We utilized an equal weighted average ensemble of two base learners' flare probabilities as our baseline meta learner and improved the capabilities of our two base learners by training a logistic regression model. The major findings of this study are: (i) We successfully coupled two heterogeneous flare prediction models trained with different datasets and model architecture to predict a full-disk flare probability for next 24 hours, (ii) Our proposed ensembling model, i.e., logistic regression, improves on the predictive performance of two base learners and the baseline meta learner measured in terms of two widely used metrics True Skill Statistic (TSS) and Heidke Skill core (HSS), and (iii) Our result analysis suggests that the logistic regression-based ensemble (Meta-FP) improves on the full-disk model (base learner) by $\sim9\%$ in terms TSS and $\sim10\%$ in terms of HSS. Similarly, it improves on the AR-based model (base learner) by $\sim17\%$ and $\sim20\%$ in terms of TSS and HSS respectively. Finally, when compared to the baseline meta model, it improves on TSS by $\sim10\%$ and HSS by $\sim15\%$.

physics.space-ph↗

arXiv2022

Integrated Geostationary Solar Energetic Particle Events Catalog: GSEP

We present a catalog of solar energetic particle (SEP) events covering solar cycles 22, 23 and 24. We correlate and integrate three existing catalogs based on Geostationary Operational Environmental Satellite (GOES) integral proton flux data. We visually verified and labeled each event in the catalog to provide a homogenized data set. We have identified a total of 341 SEP events of which 245 cross the space weather prediction center (SWPC) threshold of a significant proton event. The metadata consists of physical parameters and observables concerning the possible source solar eruptions, namely flares and coronal mass ejections for each event. The sliced time series data of each event, along with intensity profiles of proton fluxes in several energy bands, have been made publicly available. This data set enables researchers in machine learning (ML) and statistical analysis to understand the SEPs and the source eruption characteristics useful for space weather prediction.

astro-ph.SR↗

arXiv2022

Influence of coronal hole morphology on the solar wind speed at Earth

It has long been known that the high-speed stream (HSS) peak velocity at Earth directly depends on the area of the coronal hole (CH) on the Sun. Different degrees of association between the two parameters have been shown by many authors. In this study, we revisit this association in greater detail for a sample of 45 nonpolar CHs during the minimum phase of solar cycle 24. The aim is to understand how CHs of different properties influence the HSS peak speeds observed at Earth and draw from this to improve solar wind modeling. The characteristics of the CHs of our sample were extracted based on the Collection of Analysis Tools for Coronal Holes (CATCH) which employs an intensity threshold technique applied to extreme-ultraviolet (EUV) filtergrams. We first examined all the correlations between the geometric characteristics of the CHs and the HSS peak speed and duration at Earth, for the entire sample. The CHs were then categorized in different groups based on morphological criteria, such as the aspect ratio, the orientation angle and the geometric complexity, a parameter which is often neglected when the formation of the fast solar wind at Earth is studied. Our results, confirmed also by the bootstrapping technique, show that all three aforementioned morphological criteria play a major role in determining the HSS peak speed at 1 AU. Therefore, they need to be taken into consideration for empirical models that aim to forecast the fast solar wind at Earth based on the observed CH solar sources.

astro-ph.SR↗

arXiv2021

All-Clear Flare Prediction Using Interval-based Time Series Classifiers

An all-clear flare prediction is a type of solar flare forecasting that puts more emphasis on predicting non-flaring instances (often relatively small flares and flare quiet regions) with high precision while still maintaining valuable predictive results. While many flare prediction studies do not address this problem directly, all-clear predictions can be useful in operational context. However, in all-clear predictions, finding the right balance between avoiding false negatives (misses) and reducing the false positives (false alarms) is often challenging. Our study focuses on training and testing a set of interval-based time series classifiers named Time Series Forest (TSF). These classifiers will be used towards building an all-clear flare prediction system by utilizing multivariate time series data. Throughout this paper, we demonstrate our data collection, predictive model building and evaluation processes, and compare our time series classification models with baselines using our benchmark datasets. Our results show that time series classifiers provide better forecasting results in terms of skill scores, precision and recall metrics, and they can be further improved for more precise all-clear forecasts by tuning model hyperparameters.

cs.LG↗

arXiv2021

How to Train Your Flare Prediction Model: Revisiting Robust Sampling of Rare Events

We present a case study of solar flare forecasting by means of metadata feature time series, by treating it as a prominent class-imbalance and temporally coherent problem. Taking full advantage of pre-flare time series in solar active regions is made possible via the Space Weather Analytics for Solar Flares (SWAN-SF) benchmark dataset; a partitioned collection of multivariate time series of active region properties comprising 4075 regions and spanning over 9 years of the Solar Dynamics Observatory (SDO) period of operations. We showcase the general concept of temporal coherence triggered by the demand of continuity in time series forecasting and show that lack of proper understanding of this effect may spuriously enhance models' performance. We further address another well-known challenge in rare event prediction, namely, the class-imbalance issue. The SWAN-SF is an appropriate dataset for this, with a 60:1 imbalance ratio for GOES M- and X-class flares and a 800:1 for X-class flares against flare-quiet instances. We revisit the main remedies for these challenges and present several experiments to illustrate the exact impact that each of these remedies may have on performance. Moreover, we acknowledge that some basic data manipulation tasks such as data normalization and cross validation may also impact the performance -- we discuss these problems as well. In this framework we also review the primary advantages and disadvantages of using true skill statistic and Heidke skill score, as two widely used performance verification metrics for the flare forecasting task. In conclusion, we show and advocate for the benefits of time series vs. point-in-time forecasting, provided that the above challenges are measurably and quantitatively addressed.

astro-ph.SR↗