Now showing1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Morphological classification of radio galaxies with Wasserstein generative adversarial network-supported augmentation(2023-05-26); ; ; ; Machine learning techniques that perform morphological classification of astronomical sources often suffer from a scarcity of labelled training data. Here, we focus on the case of supervised deep learning models for the morphological classification of radio galaxies, which is particularly topical for the forthcoming large radio surveys. We demonstrate the use of generative models, specifically Wasserstein generative adversarial networks (wGANs), to generate data for different classes of radio galaxies. Further, we study the impact of augmenting the training data with images from our wGAN on three different classification architectures. We find that this technique makes it possible to improve models for the morphological classification of radio galaxies. A simple fully connected neural network benefits most from including generated images into the training set, with a considerable improvement of its classification accuracy. In addition, we find it is more difficult to improve complex classifiers. The classification performance of a convolutional neural network can be improved slightly. However, this is not the case for a vision transformer.Publicationtype: Journal Article15 11 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , FIRST radio galaxy data set containing curated labels of classes FRI, FRII, compact and bent(Elsevier, 2023-02-11); ; ; ; Automated classification of astronomical sources is often challenging due to the scarcity of labelled training data. We present a data set with a total number of 2158 data items that contains radio galaxy images with their corresponding morphological labels taken from various catalogues [1,2]. The data set is curated by removing duplicates, ambiguous morphological labels and by different meta data formats. The image data was acquired by the VLA FIRST (Faint Images of the Radio Sky at Twenty-Centimeters) survey [3]. The morphological labels are collected and the catalogue specific classification definition is converted into a 4-class classification scheme: FRI, FRII, Compact and Bent sources. FRI and FRII correspond to the two classes of the widely used Faranoff-Riley classification [4]. We consider two more classes: compact sources and bent-tail galaxies. For duplicates with different morphological labels, the galaxy is regarded as ambiguously labeled and both coordinates are removed. For the remaining list of coordinates, the radio galaxy images are collected from the virtual observatory skyview (https://skyview.gsfc.nasa.gov/current/cgi/query.pl). The gray value images are provided in the size of 300 × 300 pixel and all pixels with a value below three times the local RMS of the noise are set to this threshold value. The data set is useful for the development of robust machine learning models that automate the classification of radio galaxy images.Publicationtype: Data PaperScopus© Citations 2 44 80