4 results
Now showing1 - 4 of 4
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Deep-learning-based radiointerferometric imaging with GAN-aided trainingContext. The incomplete coverage of the spatial Fourier space, which leads to imaging artifacts, has been troubling radio interferometry for a long time. The currently best technique is to create an image for which the visibility data are Fourier-transformed and to clean the systematic effects originating from incomplete data in Fourier space. We have shown previously how super-resolution methods based on convolutional neural networks can reconstruct sparse visibility data. Aims. The training data in our previous work were not very realistic. The aim of this work is to build a whole simulation chain for realistic radio sources that then leads to an improved neural net for the reconstruction of missing visibilities. This method offers considerable improvements in terms of speed, automatization, and reproducibility over the standard techniques. Methods. We generated large amounts of training data by creating images of radio galaxies with a generative adversarial network that was trained on radio survey data. Then, we applied the radio interferometer measurement equation in order to simulate the measurement process of a radio interferometer. Results. We show that our neural network can faithfully reconstruct images of realistic radio galaxies. The reconstructed images agree well with the original images in terms of the source area, integrated flux density, peak flux density, and the multiscale structural similarity index. Finally, we show that the neural net can be adapted for estimating the uncertainties in the imaging process.Publicationtype: Journal Article12 32 - 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 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Radio Galaxy Classification with wGAN-Supported AugmentationNovel techniques are indispensable to process the flood of data from the new generation of radio telescopes. In particular, the classification of astronomical sources in images is challenging. Morphological classification of radio galaxies could be automated with deep learning models that require large sets of labelled training data. Here, we demonstrate the use of generative models, specifically Wasserstein GANs (wGAN), to generate artificial data for different classes of radio galaxies. Subsequently, we augment the training data with images from our wGAN. We find that a simple fully-connected neural network for classification can be improved significantly by including generated images into the training set.Publicationtype: Conference Paper15