Abstract:Abstract. In this paper, we investigate whether incorporating sunspot-groups classification information would further improve the performance of our previous logistic regression based solar flare forecasting method, which uses only line-of-sight photospheric magnetic parameters. show that sunspot-groups classification combined with total gradient on the strong gradient polarity neutral line achieve the highest forecasting accuracy and thus it testifies sunspot-groups classification does help in solar flare for… Show more
“…Big Bear Solar Observatory/Machine Learning Techniques -Y. Yuan,A.3 The method developed at NJIT (Yuan et al 2010(Yuan et al , 2011 computes three parameters describing an active region: the total unsigned magnetic flux, the length of the strong-gradient neutral line, and the total magnetic energy dissipation, following Abramenko et al (2003). Ordinal logistic regression and support vector machines are used to make predictions.…”
Section: Overview Of Prediction Methodsmentioning
confidence: 99%
“…The reliability plots ( Figure A3, top) show a systematic over-prediction for the larger event thresholds, and ROC plots ( Figure A3, bottom) show lower probability of detection for high false alarm rates than most other methods. Another approach that uses a machine learning technique as the statistical forecasting method has been developed at the New Jersey Institute of Technology (Yuan et al 2010(Yuan et al , 2011. The steps in this method are:…”
Section: New Data Are Then Used To Generate Real-time Predictionsmentioning
Solar flares produce radiation which can have an almost immediate effect on the near-Earth environment, making it crucial to forecast flares in order to mitigate their negative effects. The number of published approaches to flare forecasting using photospheric magnetic field observations has proliferated, with varying claims about how well each works. Because of the different analysis techniques and data sets used, it is essentially impossible to compare the results from the literature. This problem is exacerbated by the low event rates of large solar flares. The challenges of forecasting rare events have long been recognized in the meteorology community, but have yet to be fully acknowledged by the space weather community. During the interagency workshop on "all clear" forecasts held in Boulder, CO in 2009, the performance of a number of existing algorithms was compared on common data sets, specifically line-of-sight magnetic field and continuum intensity images from MDI, with consistent definitions of what constitutes an event. We demonstrate the importance of making such systematic comparisons, and of using standard verification statistics to determine what constitutes a good prediction scheme. When a comparison was made in this fashion, no one method clearly outperformed all others, which may in part be due to the strong correlations among the parameters used by different methods to characterize an active region. For M-class flares and above, the set of methods tends towards a weakly positive skill score (as measured with several distinct metrics), with no participating method proving substantially better than climatological forecasts.
“…Big Bear Solar Observatory/Machine Learning Techniques -Y. Yuan,A.3 The method developed at NJIT (Yuan et al 2010(Yuan et al , 2011 computes three parameters describing an active region: the total unsigned magnetic flux, the length of the strong-gradient neutral line, and the total magnetic energy dissipation, following Abramenko et al (2003). Ordinal logistic regression and support vector machines are used to make predictions.…”
Section: Overview Of Prediction Methodsmentioning
confidence: 99%
“…The reliability plots ( Figure A3, top) show a systematic over-prediction for the larger event thresholds, and ROC plots ( Figure A3, bottom) show lower probability of detection for high false alarm rates than most other methods. Another approach that uses a machine learning technique as the statistical forecasting method has been developed at the New Jersey Institute of Technology (Yuan et al 2010(Yuan et al , 2011. The steps in this method are:…”
Section: New Data Are Then Used To Generate Real-time Predictionsmentioning
Solar flares produce radiation which can have an almost immediate effect on the near-Earth environment, making it crucial to forecast flares in order to mitigate their negative effects. The number of published approaches to flare forecasting using photospheric magnetic field observations has proliferated, with varying claims about how well each works. Because of the different analysis techniques and data sets used, it is essentially impossible to compare the results from the literature. This problem is exacerbated by the low event rates of large solar flares. The challenges of forecasting rare events have long been recognized in the meteorology community, but have yet to be fully acknowledged by the space weather community. During the interagency workshop on "all clear" forecasts held in Boulder, CO in 2009, the performance of a number of existing algorithms was compared on common data sets, specifically line-of-sight magnetic field and continuum intensity images from MDI, with consistent definitions of what constitutes an event. We demonstrate the importance of making such systematic comparisons, and of using standard verification statistics to determine what constitutes a good prediction scheme. When a comparison was made in this fashion, no one method clearly outperformed all others, which may in part be due to the strong correlations among the parameters used by different methods to characterize an active region. For M-class flares and above, the set of methods tends towards a weakly positive skill score (as measured with several distinct metrics), with no participating method proving substantially better than climatological forecasts.
“…The method by Bloomfield et al (2012) uses historical flaring rates related to the McIntosh class of the source active region to make forecasts using Poisson probabilities. Yuan et al (2010Yuan et al ( , 2011 apply machine learning techniques to provide flare forecasts from characteristic magnetic parameters, such as the total unsigned magnetic flux, length of the strong-gradient polarity inversion line, and total magnetic energy dissipation. The method by McAteer et al (2010) is based on the fractal dimension of the magnetic flux concentrations in an active region to determine its flare productivity.…”
Section: Predictions Based On Observationsmentioning
Coronal mass ejections (CMEs) were discovered in the early 1970s when spaceborne coronagraphs revealed that eruptions of plasma are ejected from the Sun. Today, it is known that the Sun produces eruptive flares, filament eruptions, coronal mass ejections and failed eruptions; all thought to be due to a release of energy stored in the coronal magnetic field during its drastic reconfiguration. This review discusses the observations and physical mechanisms behind this eruptive activity, with a view to making an assessment of the current capability of forecasting these events for space weather risk and impact mitigation. Whilst a wealth of observations exist, and detailed models have been developed, there still exists a need to draw these approaches together. In particular more realistic models are encouraged in order to asses the full range of complexity of the solar atmosphere and the criteria for which an eruption is formed. From the observational side, a more detailed understanding of the role of photospheric flows and reconnection is needed in order to identify the evolutionary path that ultimately means a magnetic structure will erupt.
“…Neural networks, which go beyond simple binary classification by learning complex nonlinear relationships among their inputs, have also been used to great advantage by Nishizuka et al (2018). A variety of other ML algorithms, such as Bayesian networks (Yu et al, 2010), radial basis model networks (Colak and Qahwaji, 2009), logistic regression (Yuan et al, 2010), LASSO regression (Campi et al, 2019), and random forests or ERTs (Nishizuka et al, 2017;Campi et al, 2019) have also been implemented for solar flare prediction with some degree of success. Nishizuka et al (2017) and Jonas et al (2018) include Solar Dynamics Observatory (SDO) Atmospheric Imaging Assembly and EUV image characteristics in addition to magnetogram data in a fully connected neural network architecture.…”
Current operational forecasts of solar eruptions are made by human experts using a combination of qualitative shape-based classification systems and historical data about flaring frequencies. In the past decade, there has been a great deal of interest in crafting machine-learning (ML) flareprediction methods to extract underlying patterns from a training set-e.g., a set of solar magnetogram images, each characterized by features derived from the magnetic field and labeled as to whether it was an eruption precursor. These patterns, captured by various methods (neural nets, support vector machines, etc.), can then be used to classify new images. A major challenge with any ML method is the featurization of the data: pre-processing the raw images to extract higherlevel properties, such as characteristics of the magnetic field, that can streamline the training and use of these methods. It is key to choose features that are informative, from the standpoint of the task at hand. To date, the majority of ML-based solar eruption methods have used physics-based magnetic and electric field features such as the total unsigned magnetic flux, the gradients of the fields, the vertical current density, etc. In this paper, we extend the relevant feature set to include characteristics of the magnetic field that are based purely on the geometry and topology of 2D magnetogram images and show that this improves the prediction accuracy of a neural-net based flare-prediction method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.