Supervised Machine Learning (ML) models for solar flare prediction rely on accurate labels for a given input data set, commonly obtained from the GOES/XRS X-ray flare catalog. With increasing interest in utilizing ultraviolet (UV) and extreme ultraviolet (EUV) image data as input to these models, we seek to understand if flaring activity can be defined and quantified using EUV data alone. This would allow us to move away from the GOES single pixel measurement definition of flares and use the same data we use for flare prediction for label creation. In this work, we present a Solar Dynamics Observatory (SDO) Atmospheric Imaging Assembly (AIA)-based flare catalog covering flare of GOES X-ray magnitudes C, M and X from 2010 to 2017. We use active region (AR) cutouts of full disk AIA images to match the corresponding SDO/Helioseismic and Magnetic Imager (HMI) SHARPS (Space weather HMI Active Region Patches) that have been extensively used in ML flare prediction studies, thus allowing for labeling of AR number as well as flare magnitude and timing. Flare start, peak, and end times are defined using a peak-finding algorithm on AIA time series data obtained by summing the intensity across the AIA cutouts. An extremely randomized trees (ERT) regression model is used to map SDO/AIA flare magnitudes to GOES X-ray magnitude, achieving a low-variance regression. We find an accurate overlap on 85% of M/X flares between our resulting AIA catalog and the GOES flare catalog. However, we also discover a number of large flares unrecorded or mislabeled in the GOES catalog.
more »
« less
Beyond Traditional Flare Forecasting: A Data-driven Labeling Approach for High-fidelity Predictions
Solar flare prediction is a central problem in space weather forecasting. Existing solar flare prediction tools are mainly dependent on the GOES classification system, and models commonly use a proxy of maximum (peak) X-ray flux measurement over a particular prediction window to label instances. However, the background X-ray flux dramatically fluctuates over a solar cycle and often misleads both flare detection and flare prediction models during solar minimum, leading to an increase in false alarms. We aim to enhance the accuracy of flare prediction methods by introducing novel labeling regimes that integrate relative increases and cumulative measurements over prediction windows. Our results show that the data-driven labels can offer more precise prediction capabilities and complement the existing efforts.
more »
« less
- Award ID(s):
- 2104004
- PAR ID:
- 10435332
- Date Published:
- Journal Name:
- The 25th International Conference on Big Data Analytics and Knowledge Discovery (DAWAK 2023)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Plasmoids (or magnetic islands) are believed to play an important role in the onset of fast magnetic reconnection and particle acceleration during solar flares and eruptions. Direct imaging of flare current sheets and the formation/ejection of multiple plasmoids in extreme-ultraviolet images, along with simultaneous X-ray and radio observations, offers significant insights into the mechanisms driving particle acceleration in solar flares. Here, we present direct imaging of the formation and ejection of multiple plasmoids in flare plasma/current sheets and the associated quasiperiodic pulsations (QPPs) observed at X-ray and radio wavelengths, using observations from the Solar Dynamics Observatory/Atmospheric Imaging Assembly, RHESSI, and the Fermi Gamma-ray Burst Monitor. These plasmoids propagate bidirectionally upward and downward along the flare current sheet beneath the erupting flux rope during two successive flares associated with confined/failed eruptions. The flux rope exhibits evidence of helical kink instability, with the formation and ejection of multiple plasmoids in the flare current sheet, as predicted in an MHD simulation of a kink-unstable flux rope. RHESSI X-ray images show double coronal sources (“looptop” and higher coronal sources) located at both ends of the flare current/plasma sheet. Moreover, we detect an additional transient faint X-ray source (6–12 keV) located between the double coronal sources, which is cospatial with multiple plasmoids in the flare current sheet. X-ray (soft and hard) and radio (decimetric) observations unveil QPPs (periods ≈ 10 s and 100 s) associated with the ejection and coalescence of plasmoids. These observations suggest that energetic electrons are accelerated during the ejection and coalescence of multiple plasmoids in the flare current sheet.more » « less
-
Abstract Over‐the‐Horizon communication is strongly dependent on the state of the ionosphere, which is susceptible to solar flares. Trans‐ionospheric high frequency (HF, 3–30 MHz) signals can experience strong attenuation following a solar flare that lasts typically for an hour, commonly referred to as shortwave fadeout (SWF). In this study, we examine the role of dispersion relation and collision frequency formulations on the estimation of SWF in riometer observations using a new physics‐based model framework. The new framework first uses modified solar irradiance models incorporating high‐resolution solar flux data from the GOES satellite X‐ray sensors as input to compute the enhanced ionization produced during a flare event. The framework then uses different dispersion relation and collision frequency formulations to estimate the enhanced HF absorption. The modeled HF absorption is compared with riometer data to determine which formulation best reproduces the observations. We find the Appleton‐Hartree dispersion relation in combination with the averaged collision frequency profile reproduces riometer observations with an average skill score of 0.4, representing 40% better forecast ability than the existing D‐region Absorption Prediction model. Our modeling results also indicate that electron temperature plays an important role in controlling HF absorption. We suggest that adoption of the Appleton‐Hartree dispersion relation in combination with the averaged collision frequency be considered for improved forecasting of ionospheric absorption following solar flares.more » « less
-
Helioseismic response to solar flares ("sunquakes") occurs due to localized force or/and momentum impacts observed during the flare impulsive phase in the lower atmosphere. Such impacts may be caused by precipitation of high-energy particles, downward shocks, or magnetic Lorentz force. Understanding the mechanism of sunquakes is a key problem of the flare energy release and transport. Our statistical analysis of M-X class flares observed by the Solar Dynamics Observatory during Solar Cycle 24 has shown that contrary to expectations, many relatively weak M-class flares produced strong sunquakes, while for some powerful X-class flares, helioseismic waves were not observed or were weak. The analysis also revealed that there were active regions characterized by the most efficient generation of sunquakes during the solar cycle. We found that the sunquake power correlates with maximal values of the X-ray flux derivative better than with the X-ray class. The sunquake data challenge the current theories of solar flares.more » « less
-
Abstract Solar flare prediction plays an important role in understanding and forecasting space weather. The main goal of the Helioseismic and Magnetic Imager (HMI), one of the instruments on NASA’s Solar Dynamics Observatory, is to study the origin of solar variability and characterize the Sun’s magnetic activity. HMI provides continuous full-disk observations of the solar vector magnetic field with high cadence data that lead to reliable predictive capability; yet, solar flare prediction effort utilizing these data is still limited. In this paper, we present a machine-learning-as-a-service (MLaaS) framework, called DeepSun, for predicting solar flares on the web based on HMI’s data products. Specifically, we construct training data by utilizing the physical parameters provided by the Space-weather HMI Active Region Patch (SHARP) and categorize solar flares into four classes, namely B, C, M and X, according to the X-ray flare catalogs available at the National Centers for Environmental Information (NCEI). Thus, the solar flare prediction problem at hand is essentially a multi-class (i.e., four-class) classification problem. The DeepSun system employs several machine learning algorithms to tackle this multi-class prediction problem and provides an application programming interface (API) for remote programming users. To our knowledge, DeepSun is the first MLaaS tool capable of predicting solar flares through the internet.more » « less