ABSTRACT
State-of-the-art radio observatories produce large amounts of data which can be used to study the properties of radio galaxies. However, with this rapid increase in data volume, it has ...become unrealistic to manually process all of the incoming data, which in turn led to the development of automated approaches for data processing tasks, such as morphological classification. Deep learning plays a crucial role in this automation process and it has been shown that convolutional neural networks (CNNs) can deliver good performance in the morphological classification of radio galaxies. This paper investigates two adaptations to the application of these CNNs for radio galaxy classification. The first adaptation consists of using principal component analysis (PCA) during pre-processing to align the galaxies’ principal components with the axes of the coordinate system, which will normalize the orientation of the galaxies. This adaptation led to a significant improvement in the classification accuracy of the CNNs and decreased the average time required to train the models. The second adaptation consists of guiding the CNN to look for specific features within the samples in an attempt to utilize domain knowledge to improve the training process. It was found that this adaptation generally leads to a stabler training process and in certain instances reduced overfitting within the network, as well as the number of epochs required for training.
ABSTRACT The modern era has witnessed a rapid uptake of technological use – from air travel to mobile cellphones. Technological advancement has however come at the cost of radio spectrum crowding and ...as such the efficient detection of radio frequency interference (RFI) from radio sky images has become more paramount. Detecting RFI is a complex task that blends semantic segmentation and anomaly detection, further complicated by the limited availability of public data sets with accurate ground truth labels. Recent studies show that deep learning models improve RFI detection compared to current state-of-the-art tools. However, many astronomers are hesitant to adopt these models, possibly due to the dependence of these models on noisy labels from existing tools when accurate ground truth labels are largely unavailable in the public domain. This study argues that utilizing large weakly labelled training data sets yields lower performance than appropriately employing a modest set of expertly annotated samples. Further, Remove First Detect Later (RFDL), an augmented deep learning framework, is proposed. First, counter-intuitively, removing RFI with inpainting, RFDL feeds the difference between the original and inpainted images into existing detection models. RFDL’s performance is benchmarked against current state-of-the-art deep learning methods and the prevalent AOFlagger pipeline, using AUROC, AUPRC, and F1 score metrics. It is shown that RFDL significantly outperforms the state-of-the-art while only necessitating the use of 20 expertly labelled images.
ABSTRACT
Calibration is the process by which we try to remove atmospheric and instrumental errors that corrupt the observations made by interferometers. Calibration is however an imperfect process ...and when we calibrate with an incomplete sky model systematics or artefacts manifest in our final images. One of the more striking artefacts that can appear in images are ghost sources. This paper explores these ghost artefacts in greater depth. We are particularly interested in the systematics or artefacts that are created if we partially model extended emission. A theoretical model that utilizes an east–west layout is developed (and empirically validated) that can give insight into the systematics so formed. The results from this study reveal that when we only partially model extended emission then the calibration systematics that form can manifest as extended emission in images. The aforementioned systematics alter the original extended source in various ways; the flux density of the extended source is modified and becomes comparable to the flux density of the source in the calibration sky model and its profile is slightly modified (it becomes more point like). More importantly, we found that the shorter baselines that are more sensitive to extended emission are in general more affected by the calibration systematics than the longer baselines are. In related works, it was found that the number of antennas greatly influence the brightness of the created systematics. For the use case, we investigate in the paper, however, we found this to not be the case.
ABSTRACT
In the realm of radio astronomy, the detection of radio frequency interference (RFI) stands as a pivotal pursuit. This study performs a novel comparative analysis of deep learning ...methodologies and introduces a novel transfer learning method, called fine-tuning. We compare various aspects and factors relating to this problem, including supervised fully convolutional network (FCN) architectures used within the literature, loss functions, regularization techniques, and training methodologies, to establish the most effective strategies for RFI detection. Moreover, the relationship between parameters, FLOPS, and inference times are examined. Fine-tuning involves pre-training models with low-quality aoflagger reference outputs, a very popular and accessible RFI flagging software package, and thereafter re-training the models with high-quality reference outputs. We utilize two data sets: real observations from LOFAR and simulated data from HERA. The mean squared error (MSE) loss function emerges as a robust performer if a high recall is desired. In contrast, the binary cross-entropy (BCE) loss function excels in generalization but falls short in classification performance. The Dice loss function emerges as the top performer, maximizing the F1 score and thereby serving as the choice for our further investigations. Notably, we highlight the important role of data quality and model capacity. In particular, we find that low-capacity models exhibit resilience when trained with low-quality flags from aoflagger, showcasing their ability to mitigate overfitting and overflagging tendencies. In contrast, high-capacity models excel when trained with high-quality flags. Fine-tuning proved to be an effective method to unlearn the overflagging tendencies of aoflagger, whilst requiring very little data.
ABSTRACT
The key challenge in the observation of the redshifted 21-cm signal from cosmic reionization is its separation from the much brighter foreground emission. Such separation relies on the ...different spectral properties of the two components, although, in real life, the foreground intrinsic spectrum is often corrupted by the instrumental response, inducing systematic effects that can further jeopardize the measurement of the 21-cm signal. In this paper, we use Gaussian Process Regression to model both foreground emission and instrumental systematics in ∼2 h of data from the Hydrogen Epoch of Reionization Array. We find that a simple co-variance model with three components matches the data well, giving a residual power spectrum with white noise properties. These consist of an ‘intrinsic’ and instrumentally corrupted component with a coherence scale of 20 and 2.4 MHz, respectively (dominating the line-of-sight power spectrum over scales k∥ ≤ 0.2 h cMpc−1) and a baseline-dependent periodic signal with a period of ∼1 MHz (dominating over k∥ ∼ 0.4–0.8 h cMpc−1), which should be distinguishable from the 21-cm Epoch of Reionization signal whose typical coherence scale is ∼0.8 MHz.
Human settlement expansion is one of the most pervasive forms of land cover change in the Gauteng province of South Africa. A method for detecting new settlement developments in areas that are ...typically covered by natural vegetation using 500 m MODIS time-series satellite data is proposed. The method is a per pixel change alarm that uses the temporal autocorrelation to infer a change index which yields a change or no-change decision after thresholding. Simulated change data was generated and used to determine a threshold during an off-line optimization phase. After optimization the method was evaluated on examples of known land cover change in the study area and experimental results indicate a 92% change detection accuracy with a 15% false alarm rate. The method shows good performance when compared to a traditional NDVI differencing method that achieved a 75% change detection accuracy with a 24% false alarm rate for the same study area.
State-of-the-art radio observatories produce large amounts of data which can be used to study the properties of radio galaxies. However, with this rapid increase in data volume, it has become ...unrealistic to manually process all of the incoming data, which in turn led to the development of automated approaches for data processing tasks, such as morphological classification. Deep learning plays a crucial role in this automation process and it has been shown that convolutional neural networks (CNNs) can deliver good performance in the morphological classification of radio galaxies. This paper investigates two adaptations to the application of these CNNs for radio galaxy classification. The first adaptation consists of using principal component analysis (PCA) during preprocessing to align the galaxies' principal components with the axes of the coordinate system, which will normalize the orientation of the galaxies. This adaptation led to a significant improvement in the classification accuracy of the CNNs and decreased the average time required to train the models. The second adaptation consists of guiding the CNN to look for specific features within the samples in an attempt to utilize domain knowledge to improve the training process. It was found that this adaptation generally leads to a stabler training process and in certain instances reduced overfitting within the network, as well as the number of epochs required for training.
The key challenge in the observation of the redshifted 21-cm signal from cosmic reionization is its separation from the much brighter foreground emission. Such separation relies on the different ...spectral properties of the two components, although, in real life, the foreground intrinsic spectrum is often corrupted by the instrumental response, inducing systematic effects that can further jeopardize the measurement of the 21-cm signal. In this paper, we use Gaussian Process Regression to model both foreground emission and instrumental systematics in \(\sim 2\) hours of data from the Hydrogen Epoch of Reionization Array. We find that a simple co-variance model with three components matches the data well, giving a residual power spectrum with white noise properties. These consist of an "intrinsic" and instrumentally corrupted component with a coherence-scale of 20 MHz and 2.4 MHz respectively (dominating the line of sight power spectrum over scales \(k_{\parallel} \le 0.2\) h cMpc\(^{-1}\)) and a baseline dependent periodic signal with a period of \(\sim 1\) MHz (dominating over \(k_{\parallel} \sim 0.4 - 0.8\)h cMpc\(^{-1}\)) which should be distinguishable from the 21-cm EoR signal whose typical coherence-scales is \(\sim 0.8\) MHz.