A Comparative Study of Clustering Methods for Active Region Detection in Solar EUV Images

Caballero, Carlos; Aranda, M. Carmen

doi:10.1007/s11207-013-0239-2

Cited by 7 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, a suite of classifiers, many not listed here, were developed in association with NASA's Solar Dynamics Observatory mission (Martens et al, 2012). With so many different classification approaches, Caballero and Aranda (2013) conducted an independent study of a variety of approaches applied to active regions and identified where they disagree.…”

Section: Introductionmentioning

confidence: 99%

Real-time solar image classification: Assessing spectral, pixel-based approaches

Hughes

Hsu

Seaton

et al. 2019

J. Space Weather Space Clim.

View full text Add to dashboard Cite

In order to utilize solar imagery for real-time feature identification and large-scale data science investigations of solar structures, we need maps of the Sun where phenomena, or themes, are labeled. Since solar imagers produce observations every few minutes, it is not feasible to label all images by hand. Here, we compare three machine learning algorithms performing solar image classification using extreme ultraviolet and Hα images: a maximum likelihood model assuming a single normal probability distribution for each theme from Rigler et al. (2012), a maximum-likelihood model with an underlying Gaussian mixtures distribution, and a random forest model. We create a small database of expert-labeled maps to train and test these algorithms. Due to the ambiguity between the labels created by different experts, a collaborative labeling is used to include all inputs. We find the random forest algorithm performs the best amongst the three algorithms. The advantages of this algorithm are best highlighted in: comparison of outputs to hand-drawn maps; response to short-term variability; and tracking long-term changes on the Sun. Our work indicates that the next generation of solar image classification algorithms would benefit significantly from using spatial structure recognition, compared to only using spectral, pixel-by-pixel brightness distributions.

show abstract

Section: Introductionmentioning

confidence: 99%

Real-time solar image classification: Assessing spectral, pixel-based approaches

Hughes

Hsu

Seaton

et al. 2019

J. Space Weather Space Clim.

View full text Add to dashboard Cite

show abstract

“…Edge-based methods on the other hand focus on discontinuities and thus on locating region boundaries (Zharkov et al 2005;Curto et al 2008;Watson et al 2009) These methods can be combined in many ways, and the literature on the subject is extensive. Aschwanden (2010) and Martens et al (2012) review and summarize recent work in this area while Verbeeck et al (2013) and Caballero & Aranda (2013) compare different segmentation procedures.…”

Section: Introductionmentioning

confidence: 99%

Supervised classification of solar features using prior information

Visscher

Delouille

Dupont

et al. 2015

J. Space Weather Space Clim.

View full text Add to dashboard Cite

Context: The Sun as seen by Extreme Ultraviolet (EUV) telescopes exhibits a variety of large-scale structures. Of particular interest for space-weather applications is the extraction of active regions (AR) and coronal holes (CH). The next generation of GOES-R satellites will provide continuous monitoring of the solar corona in six EUV bandpasses that are similar to the ones provided by the SDO-AIA EUV telescope since May 2010. Supervised segmentations of EUV images that are consistent with manual segmentations by for example space-weather forecasters help in extracting useful information from the raw data. Aims: We present a supervised segmentation method that is based on the Maximum A Posteriori rule. Our method allows integrating both manually segmented images as well as other type of information. It is applied on SDO-AIA images to segment them into AR, CH, and the remaining Quiet Sun (QS) part. Methods: A Bayesian classifier is applied on training masks provided by the user. The noise structure in EUV images is nontrivial, and this suggests the use of a non-parametric kernel density estimator to fit the intensity distribution within each class. Under the Naive Bayes assumption we can add information such as latitude distribution and total coverage of each class in a consistent manner. Those information can be prescribed by an expert or estimated with an Expectation-Maximization algorithm. Results: The segmentation masks are in line with the training masks given as input and show consistency over time. Introduction of additional information besides pixel intensity improves upon the quality of the final segmentation. Conclusions: Such a tool can aid in building automated segmentations that are consistent with some ground truth' defined by the users.

show abstract

Deep Learning in Solar Object Detection Tasks

Yan

Huang

2022

SpringerBriefs in Computer Science

View full text Add to dashboard Cite

A Comparative Study of Clustering Methods for Active Region Detection in Solar EUV Images

Cited by 7 publications

References 42 publications

Real-time solar image classification: Assessing spectral, pixel-based approaches

Real-time solar image classification: Assessing spectral, pixel-based approaches

Supervised classification of solar features using prior information

Deep Learning in Solar Object Detection Tasks

Contact Info

Product

Resources

About