An official website of the United States government
The purpose of this study is to provide a comprehensive resource for the selection of data representations for machine learning-oriented models and components in solar flare prediction tasks. Major solar flares occurring in the solar corona and heliosphere can bring potential destructive consequences, posing significant risks to astronauts, space stations, electronics, communication systems, and numerous technological infrastructures. For this reason, the accurate detection of major flares is essential for mitigating these hazards and ensuring the safety of our technology-dependent society. In response, leveraging machine learning techniques for predicting solar flares has emerged as a significant application within the realm of data science, relying on sensor data collected from solar active region photospheric magnetic fields by space- and ground-based observatories. In this research, three distinct solar flare prediction strategies utilizing the photospheric magnetic field parameter-based multivariate time series dataset are evaluated, with a focus on data representation techniques. Specifically, we examine vector-based, time series-based, and graph-based approaches to identify the most effective data representation for capturing key characteristics of the dataset. The vector-based approach condenses multivariate time series into a compressed vector form, the time series representation leverages temporal patterns, and the graph-based method models interdependencies between magnetic field parameters. The results demonstrate that the vector representation approach exhibits exceptional robustness in predicting solar flares, consistently yielding strong and reliable classification outcomes by effectively encapsulating the intricate relationships within photospheric magnetic field data when coupled with appropriate downstream machine learning classifiers.
more »
« less
Intelligent Databases and Machine-Learning Analysis Tools for Heliophysics
The project focuses on developing innovative tools to extract and analyze the available observational and modeling data to enable new physics-based and machine-learning approaches for understanding and predicting solar activity and its influence on the geospace and Earth systems. Numerous space and ground-based observatories produce several terabytes of multi-wavelength data, from radio waves to gamma rays, every day. Finding and processing the relevant information for specific space weather applications is currently a difficult task. The Team has developed and implemented interactive databases of solar flares and coronal holes that provide a synergy of ground-based and space observations, taking advantage of big datasets from a wide range of instruments. The databases and analysis tools allow the larger research community to significantly speed up investigations of flare events, perform a broad range of new statistical and case studies, and test and validate theoretical and computational models. The databases store, integrate, and present physical descriptors of solar flares and provide automatic real-time machine-learning identification and characterization of solar coronal holes, which are sources of open magnetic flux and fast solar wind.
more »
« less
- Award ID(s):
- 1639683
- PAR ID:
- 10284256
- Date Published:
- Journal Name:
- 2021 EarthCube Annual Meeting
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Owing to the ever-present solar wind, our vast solar system is full of plasmas. The turbulent solar wind, together with sporadic solar eruptions, introduces various space plasma processes and phenomena in the solar atmosphere all the way to the Earth's ionosphere and atmosphere and outward to interact with the interstellar media to form the heliopause and termination shock. Remarkable progress has been made in space plasma physics in the last 65 years, mainly due to sophisticated in-situ measurements of plasmas, plasma waves, neutral particles, energetic particles, and dust via space-borne satellite instrumentation. Additionally high technology ground-based instrumentation has led to new and greater knowledge of solar and auroral features. As a result, a new branch of space physics, i.e., space weather, has emerged since many of the space physics processes have a direct or indirect influence on humankind. After briefly reviewing the major space physics discoveries before rockets and satellites, we aim to review all our updated understanding on coronal holes, solar flares and coronal mass ejections, which are central to space weather events at Earth, solar wind, storms and substorms, magnetotail and substorms, emphasizing the role of the magnetotail in substorm dynamics, radiation belts/energetic magnetospheric particles, structures and space weather dynamics in the ionosphere, plasma waves, instabilities, and wave-particle interactions, long-period geomagnetic pulsations, auroras, geomagnetically induced currents (GICs), planetary magnetospheres and solar/stellar wind interactions with comets, moons and asteroids, interplanetary discontinuities, shocks and waves, interplanetary dust, space dusty plasmas and solar energetic particles and shocks, including the heliospheric termination shock. This paper is aimed to provide a panoramic view of space physics and space weather.more » « less
-
Abstract Solar flares, especially the M- and X-class flares, are often associated with coronal mass ejections. They are the most important sources of space weather effects, which can severely impact the near-Earth environment. Thus it is essential to forecast flares (especially the M- and X-class ones) to mitigate their destructive and hazardous consequences. Here, we introduce several statistical and machine-learning approaches to the prediction of an active region’s (AR) flare index (FI) that quantifies the flare productivity of an AR by taking into account the number of different class flares within a certain time interval. Specifically, our sample includes 563 ARs that appeared on the solar disk from 2010 May to 2017 December. The 25 magnetic parameters, provided by the Space-weather HMI Active Region Patches (SHARP) from the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory, characterize coronal magnetic energy stored in ARs by proxy and are used as the predictors. We investigate the relationship between these SHARP parameters and the FI of ARs with a machine-learning algorithm (spline regression) and the resampling method (Synthetic Minority Oversampling Technique for Regression with Gaussian Noise). Based on the established relationship, we are able to predict the value of FIs for a given AR within the next 1 day period. Compared with other four popular machine-learning algorithms, our methods improve the accuracy of FI prediction, especially for a large FI. In addition, we sort the importance of SHARP parameters by the Borda count method calculated from the ranks that are rendered by nine different machine-learning methods.more » « less
-
Detecting and classifying solar filaments is critical in forecasting Earth-affecting transient solar events, including large solar flares and coronal mass ejections. Undetected, these space weather events can cause catastrophic geomagnetic storms resulting in substantial economic damage and death. A network of ground-based observatories, named the Global Oscillation Network Group, was created to provide continuous observation of solar activity. However, parsing the large volume of image data continuously streaming in from GONG tests the limitations of human analysis and presents challenges for space weather research. To address this, we proposed the Machine Learning Ecosystem for Filament Detection (MLEcoFi), an NSF-funded, multiyear project that will produce an open-source collection of filament data and computer vision software for space weather research. In cooperation with NSO, MLEcoFi will assist in automatically detecting, classifying, localizing, and segmenting solar filaments in full-disk H-alpha images. The present phase of research aims to produce a dataset of thousands of GONG H-alpha images, with all filaments’ chirality, bounding box, and segmentation mask manually annotated following strong quality assurance standards, advancing research of filaments and filament-related topics. This dataset, as the first MLEcoFi product, will aid in ongoing and future development of products, including a chirality-aware filament data augmentation engine, high-precision image segmentation loss function, deep neural network segmentation and classification model, and filament detection module that is planned for deployment into NSO’s live infrastructure for the research community. The MLEcoFi team is eager to present its progress and future milestones to obtain valuable feedback from the future users of this ecosystem.more » « less
-
Abstract An overview is presented of our current understanding and open questions related to magnetic reconnection in solar flares and the near-sun (within around 20$$R_{s}$$ ) solar wind. The solar-flare-related topics include the mechanisms that facilitate fast energy release and that control flare onset, electron energization, ion energization and abundance enhancement, electron and ion transport, and flare-driven heating. Recent observations and models suggesting that interchange reconnection of multipolar magnetic fields within coronal holes could provide the energy required to drive the fast solar wind are also discussed. Recentin situobservations that reconnection in the heliospheric current sheet close to the sun drives energetic ions are also presented. The implications ofin situobservations of reconnection in the Earth space environment for understanding flares are highlighted. Finally, the impact of emerging computational and observational tools for understanding flare dynamics are discussed.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.6084/m9.figshare.14848713.v1
