Machine learning techniques have been increasingly useful in astronomical applications over the last few years, for example in the morphological classification of galaxies. Convolutional neural networks have proven to be highly effective in classifying objects in image data. In the context of radio-interferometric imaging in astronomy, we looked for ways to identify multiple components of individual sources. To this effect, we design a convolutional neural network to differentiate between different morphology classes using sources from the Radio Galaxy Zoo (RGZ) citizen science project. In this first step, we focus on exploring the factors that affect the performance of such neural networks, such as the amount of training data, number and nature of layers, and the hyperparameters. We begin with a simple experiment in which we only differentiate between two extreme morphologies, using compact and multiple-component extended sources. We found that a three-convolutional layer architecture yielded very good results, achieving a classification accuracy of 97.4 per cent on a test data set. The same architecture was then tested on a four-class problem where we let the network classify sources into compact and three classes of extended sources, achieving a test accuracy of 93.5 per cent. The best-performing convolutional neural network set-up has been verified against RGZ Data Release 1 where a final test accuracy of 94.8 per cent was obtained, using both original and augmented images. The use of sigma clipping does not offer a significant benefit overall, except in cases with a small number of training images.
Finding and classifying astronomical sources is key in the scientific exploitation of radio surveys. Source-finding usually involves identifying the parts of an image belonging to an astronomical source, against some estimated background. This can be problematic in the radio regime, owing to the presence of correlated noise, which can interfere with the signal from the source. In the current work, we present ConvoSource, a novel method based on a deep learning technique, to identify the positions of radio sources, and compare the results to a Gaussian-fitting method. Since the deep learning approach allows the generation of more training images, it should perform well in the source-finding task. We test the source-finding methods on artificial data created for the data challenge of the Square Kilometer Array (SKA). We investigate sources that are divided into three classes: star forming galaxies (SFGs) and two classes of active galactic nuclei (AGN). The artificial data are given at two different frequencies (560 MHz and 1400 MHz), three total integration times (8 h, 100 h, 1000 h), and three signal-to-noise ratios (SNRs) of 1, 2, and 5. At lower SNRs, ConvoSource tends to outperform a Gaussian-fitting approach in the recovery of SFGs and all sources, although at the lowest SNR of one, the better performance is likely due to chance matches. The Gaussian-fitting method performs better in the recovery of the AGN-type sources at lower SNRs. At a higher SNR, ConvoSource performs better on average in the recovery of AGN sources, whereas the Gaussian-fitting method performs better in the recovery of SFGs and all sources. ConvoSource usually performs better at shorter total integration times and detects more true positives and misses fewer sources compared to the Gaussian-fitting method; however, it detects more false positives.
1 October 2016 in Proceedings of the International Astronomical Union
Machine learning techniques have proven to be increasingly useful in astronomical applications over the last few years, for example in object classification, estimating redshifts and data mining. One example of object classification is classifying galaxy morphology. This is a tedious task to do manually, especially as the datasets become larger with surveys that have a broader and deeper search-space. The Kaggle Galaxy Zoo competition presented the challenge of writing an algorithm to find the probability that a galaxy belongs in a particular class, based on SDSS optical spectroscopy data. The use of convolutional neural networks (convnets), proved to be a popular solution to the problem, as they have also produced unprecedented classification accuracies in other image databases such as the database of handwritten digits (MNIST †) and large database of images (CIFAR ‡). We experiment with the convnets that comprised the winning solution, but using broad classifications. The effect of changing the number of layers is explored, as well as using a different activation function, to help in developing an intuition of how the networks function and to see how they can be applied to radio galaxy images.
Next-generation radio surveys will yield an unprecedented amount of data, warranting analysis by use of machine learning techniques. Convolutional neural networks are the deep learning technique that has proven to be the most successful in classifying image data. Capsule networks are a more recently developed technique that use capsules comprised of groups of neurons, that describe properties of an image including the relative spatial locations of features. The current work explores the performance of different capsule network architectures against simpler convolutional neural network architectures, in reproducing the classifications into the classes of unresolved, FRI and FRII morphologies. We utilise images from a LOFAR survey which is the deepest, wide-area radio survey to date, revealing more complex radio-source structures compared to previous surveys, presenting further challenges for machine learning algorithms. The 4- and 8-layer convolutional networks attain an average precision of 93.3% and 94.3% respectively, compared to 89.7% obtained with the capsule network, when training on original and augmented images. Implementing transfer learning achieves a precision of 94.4%, that is within the confidence interval of the 8-layer convolutional network. The convolutional networks always outperform any variation of the capsule network, as they prove to be more robust to the presence of noise in images. The use of pooling appears to allow more freedom for the intra-class variability of radio galaxy morphologies, as well as reducing the impact of noise.
Machine learning techniques have been increasingly useful in astronomical applications over the last few years, for example in the morphological classification of galaxies. Convolutional neural networks have proven to be highly effective in classifying objects in image data. The current work aims to establish when multiple components are present, in the astronomical context of synthesis imaging observations of radio sources. To this effect, we design a convolutional neural network to differentiate between different morphology classes using sources from the Radio Galaxy Zoo (RGZ) citizen science project. In this first step, we focus on exploring the factors that affect the performance of such neural networks, such as the amount of training data, number and nature of layers and the hyperparameters. We begin with a simple experiment in which we only differentiate between two extreme morphologies, using compact and multiple component extended sources. We found that a three convolutional layer architecture yielded very good results, achieving a classification accuracy of 97.4% on a test data set. The same architecture was then tested on a four-class problem where we let the network classify sources into compact and three classes of extended sources, achieving a test achieving a test accuracy of 93.5%. The best-performing convolutional neural network setup has been verified against RGZ Data Release 1 where a final test accuracy of 94.8% was obtained, using both original and augmented images. The use of sigma clipping does not offer a significant benefit overall, except in cases with a small number of training images.