Tufan Colak

Automatic detection and verification of solar features

A fast hybrid system for the automated detection and verification of active regions (plages) and filaments in solar images is presented in this paper. The system combines automated image processing with machine learning. The imaging part consists of five major stages. The solar disk is detected in the first stage, using a morphological hit‐miss transform, watershed transform and Filling algorithm. An image‐enhancement technique is introduced to remove the limb‐darkening effect and intensity filtering is implemented followed by a modified region‐growing technique to detect the regions of interest (RoI). The algorithms are tested on H‐α and CA II K3‐line solar images that are obtained from Meudon Observatory, covering the period from July 2, 2001 till August 4, 2001. The detection algorithm is fast and it achieves false acceptance rate (FAR) error rate of 67% and false rejection rate (FRR) error rate of 3% for active regions, and FAR error rate of 19% and FRR error rate of 14% for filaments, when compared with the manually detected filaments in the synoptic maps. The detection performance is enhanced further using a neural network (NN), which is trained on statistical features extracted from the RoI and non‐RoI. With the use of this combination the FAR has dropped to 2% for active regions and 4% for filaments.© 2006 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 15, 199–210, 2005

Automatic Sunspot Classification for Real-Time Forecasting of Solar Activities

Solar imaging is currently an active area of research. A fast hybrid system for the automated detection and classification of sunspot groups on MDI Continuum images using active regions data extracted from MDI Magnetogram images is presented in this paper. The system has three major stages: sunspots detection from MDI Continuum images, sunspots grouping and Mcintosh classification of sunspot groups. Image processing and machine learning are integrated in all these stages.

A new technique for the calculation and 3D visualisation of magnetic complexities on solar satellite images

In this paper, we introduce two novel models for processing real-life satellite images to quantify and then visualise their magnetic structures in 3D. We believe this multidisciplinary work is a real convergence between image processing, 3D visualisation and solar physics. The first model aims to calculate the value of the magnetic complexity in active regions and the solar disk. A series of experiments are carried out using this model and a relationship has been indentified between the calculated magnetic complexity values and solar flare events. The second model aims to visualise the calculated magnetic complexities in 3D colour maps in order to identify the locations of eruptive regions on the Sun. Both models demonstrate promising results and they can be potentially used in the fields of solar imaging, space weather and solar flare prediction and forecasting.

A new method for processing solar images to calculate the magnetic energies associated with active regions

In this paper, a new method is applied to calculate the magnetic energies of active regions and sunspots in satellites images. Digital images from the Solar & Heliospheric Observatory (SOHO) satellite are used in this study. The magnetic energies are calculated using the Ising model, which has been modified for our application. The new algorithm is integrated with our existing ASAP system (Automate Solar Activity Prediction). Extensive testing was carried out and the promising results are obtained that will aid in enhancing the accuracy of our automated real-time solar prediction system are presented.

Using the real, gentle and modest AdaBoost learning algorithms to investigate the computerised associations between Coronal Mass Ejections and filaments

Space weather forecasting is a very challenging task and investigating the associations between properties (i.e., shape, scale, location) of the related solar features, appearing in solar images, are usually complicated because of the variation in their physical and visual properties. Establishing the correlations among the occurrences of solar activities and solar features is a long-standing problem in solar imaging. This work is an attempt to shed more light on the driving forces behind the initiations of Coronal Mass Ejections (CMEs). This is still a big mystery in this field and in this work we have analysed years of data relating to one particular feature, filaments, to determine if an association between filaments and the eruptions of CMEs can be drawn. The resulting association set has been fed to a powerful machine learning algorithm to determine if CMEs can be predicted solely based on filaments. Our learning algorithm, AdaBoost, is used because of robust and accurate performance. Three of the most common versions of the Adaboost algorithm are used in this work, which are the Gentle AdaBoost, the Real AdaBoost and the Modest AdaBoost.

Automated Prediction of Solar Flares Using Neural Networks and Sunspots Associations

An automated neural network-based system for predicting solar flares from their associated sunspots and simulated solar cycle is introduced. A sunspot is the cooler region of the Sun’s photosphere which, thus, appears dark on the Sun’s disc, and a solar flare is sudden, short lived, burst of energy on the Sun’s surface, lasting from minutes to hours. The system explores the publicly available solar catalogues from the National Geophysical Data Center to associate sunspots and flares. Size, shape and spot density of relevant sunspots are used as input values, in addition to the values found by the solar activity model introduced by Hathaway. Two outputs are provided: The first is a flare/ no flare prediction, while the second is type of the solar flare prediction (X or M type flare). Our system provides 91.7% correct prediction for the possible occurrences and, 88.3% correct prediction for the type of the solar flares.

Applying a modified ising algorithm to calculate the energy of solar active regions in solar images

This paper describes the application of a new method to calculate energies of solar active regions and sunspots in satellites images. Digital images from the Solar & Heliospheric Observatory (SOHO) satellite are used I n this study and energies are calculated using the Ising model, which has been modified for our application. The new algorithm has been integrated with our existing ASAP system (Automate Solar Activity Prediction) and extensive testing carried out. The results obtained are promising and will help enhance the accuracy of our automated real-time solar flare prediction.

Morphological-Based Filtering of Noise: Practical Study on Solar Images

In this paper, a morphological-based algorithm is proposed for noise filtering in digital images. This algorithm is based on the morphological hit-miss transform (HMT). It is applied on a real-life problem, which is the detection of solar features in H-alpha solar images that are obtained from Meudon Observatory. These images are processed by the automated detection system of Filaments reported by R. Qahwaji and T. Colak [1]. The automated detection system works well when detecting filaments in noise-free solar images; it achieves false acceptance rate (FAR) error rate of 4% and false rejection rate (FRR) error rate of 36% when compared with the manually detected filaments in the synoptic maps. When the detection is applied after the addition of Gaussian noise to the solar images it achieves FAR of 3% and FRR of 51%. Then by filtering using the proposed algorithm, the detection performance is enhanced to achieve FAR of 8% and FRR of 13%.

Calculate the Energy of Active Regions and Solar Disk on Satellite Images for Real-Time Solar Flare Forecasting

It is extremely important to design preventive measures to avoid or mitigate the influence of space weather. Severe solar activities could have a catastrophic impact on human activities in general i.e. damaging satellites, flight navigation, power distribution stations, telecommunications, etc. In this paper, a new model has been designed and implemented to calculate the energy of solar active regions and the solar disk energy. The method has been tested in a series of experiments and a relationship has been found between the calculated energies and solar flare events. A final automated real-time model will be designed later to provide flare forecasting, based on the proposed model.

Prediction of halloween storm with automated solar activity prediction tool (ASAP)

The Halloween storm, which occurred late October early November 2003, caused serious problems including damaging 28 satellites, knocking two out of commission, diverting airplane routes and causing power failures. In this paper, we tested our fully Automated Solar Activity Prediction (ASAP) tool with the solar data corresponding to this period. The prediction capability of the tool is evaluated using various performance measures. With this study we are aiming to answer if solar flares during Halloween storm could have been predicted using ASAP and if ASAP can be used for the prediction of such extreme events in the future.