Abstract:Radio Frequency Interference (RFI) is a known growing challenge for radio astronomy, intensified by increasing observatory sensitivity and prevalence of orbital RFI sources. Spiking Neural Networks (SNNs) offer a promising solution for real-time RFI detection by exploiting the time-varying nature of radio observation and neuron dynamics together. This work explores the inclusion of polarisation information in SNN-based RFI detection, using simulated data from the Hydrogen Epoch of Reionisation Array (HERA) instrument and provides power usage estimates for deploying SNN-based RFI detection on existing neuromorphic hardware. Preliminary results demonstrate state-of-the-art detection accuracy and highlight possible extensive energy-efficiency gains.
Abstract:Radio Frequency Interference (RFI) from anthropogenic radio sources poses significant challenges to current and future radio telescopes. Contemporary approaches to detecting RFI treat the task as a semantic segmentation problem on radio telescope spectrograms. Typically, complex heuristic algorithms handle this task of `flagging' in combination with manual labeling (in the most difficult cases). While recent machine-learning approaches have demonstrated high accuracy, they often fail to meet the stringent operational requirements of modern radio observatories. Owing to their inherently time-varying nature, spiking neural networks (SNNs) are a promising alternative method to RFI-detection by utilizing the time-varying nature of the spectrographic source data. In this work, we apply Liquid State Machines (LSMs), a class of spiking neural networks, to RFI-detection. We employ second-order Leaky Integrate-and-Fire (LiF) neurons, marking the first use of this architecture and neuron type for RFI-detection. We test three encoding methods and three increasingly complex readout layers, including a transformer decoder head, providing a hybrid of SNN and ANN techniques. Our methods extend LSMs beyond conventional classification tasks to fine-grained spatio-temporal segmentation. We train LSMs on simulated data derived from the Hyrogen Epoch of Reionization Array (HERA), a known benchmark for RFI-detection. Our model achieves a per-pixel accuracy of 98% and an F1-score of 0.743, demonstrating competitive performance on this highly challenging task. This work expands the sophistication of SNN techniques and architectures applied to RFI-detection, and highlights the effectiveness of LSMs in handling fine-grained, complex, spatio-temporal signal-processing tasks.
Abstract:Spiking Neural Networks (SNNs) promise efficient spatio-temporal data processing owing to their dynamic nature. This paper addresses a significant challenge in radio astronomy, Radio Frequency Interference (RFI) detection, by reformulating it as a time-series segmentation task inherently suited for SNN execution. Automated RFI detection systems capable of real-time operation with minimal energy consumption are increasingly important in modern radio telescopes. We explore several spectrogram-to-spike encoding methods and network parameters, applying first-order leaky integrate-and-fire SNNs to tackle RFI detection. To enhance the contrast between RFI and background information, we introduce a divisive normalisation-inspired pre-processing step, which improves detection performance across multiple encoding strategies. Our approach achieves competitive performance on a synthetic dataset and compelling results on real data from the Low-Frequency Array (LOFAR) instrument. To our knowledge, this work is the first to train SNNs on real radio astronomy data successfully. These findings highlight the potential of SNNs for performing complex time-series tasks, paving the way for efficient, real-time processing in radio astronomy and other data-intensive fields.
Abstract:Radio Frequency Interference (RFI) poses a significant challenge in radio astronomy, arising from terrestrial and celestial sources, disrupting observations conducted by radio telescopes. Addressing RFI involves intricate heuristic algorithms, manual examination, and, increasingly, machine learning methods. Given the dynamic and temporal nature of radio astronomy observations, Spiking Neural Networks (SNNs) emerge as a promising approach. In this study, we cast RFI detection as a supervised multi-variate time-series segmentation problem. Notably, our investigation explores the encoding of radio astronomy visibility data for SNN inference, considering six encoding schemes: rate, latency, delta-modulation, and three variations of the step-forward algorithm. We train a small two-layer fully connected SNN on simulated data derived from the Hydrogen Epoch of Reionization Array (HERA) telescope and perform extensive hyper-parameter optimization. Results reveal that latency encoding exhibits superior performance, achieving a per-pixel accuracy of 98.8% and an f1-score of 0.761. Remarkably, these metrics approach those of contemporary RFI detection algorithms, notwithstanding the simplicity and compactness of our proposed network architecture. This study underscores the potential of RFI detection as a benchmark problem for SNN researchers, emphasizing the efficacy of SNNs in addressing complex time-series segmentation tasks in radio astronomy.
Abstract:Radio Frequency Interference (RFI) detection and mitigation is critical for enabling and maximising the scientific output of radio telescopes. The emergence of machine learning methods capable of handling large datasets has led to their application in radio astronomy, particularly in RFI detection. Spiking Neural Networks (SNNs), inspired by biological systems, are well-suited for processing spatio-temporal data. This study introduces the first application of SNNs to an astronomical data-processing task, specifically RFI detection. We adapt the nearest-latent-neighbours (NLN) algorithm and auto-encoder architecture proposed by previous authors to SNN execution by direct ANN2SNN conversion, enabling simplified downstream RFI detection by sampling the naturally varying latent space from the internal spiking neurons. We evaluate performance with the simulated HERA telescope and hand-labelled LOFAR dataset that the original authors provided. We additionally evaluate performance with a new MeerKAT-inspired simulation dataset. This dataset focuses on satellite-based RFI, an increasingly important class of RFI and is, therefore, an additional contribution. Our SNN approach remains competitive with the original NLN algorithm and AOFlagger in AUROC, AUPRC and F1 scores for the HERA dataset but exhibits difficulty in the LOFAR and MeerKAT datasets. However, our method maintains this performance while completely removing the compute and memory-intense latent sampling step found in NLN. This work demonstrates the viability of SNNs as a promising avenue for machine-learning-based RFI detection in radio telescopes by establishing a minimal performance baseline on traditional and nascent satellite-based RFI sources and is the first work to our knowledge to apply SNNs in astronomy.
Abstract:Neuromorphic computing and spiking neural networks aim to leverage biological inspiration to achieve greater energy efficiency and computational power beyond traditional von Neumann architectured machines. In particular, spiking neural networks hold the potential to advance artificial intelligence as the basis of third-generation neural networks. Aided by developments in memristive and compute-in-memory technologies, neuromorphic computing hardware is transitioning from laboratory prototype devices to commercial chipsets; ushering in an era of low-power computing. As a nexus of biological, computing, and material sciences, the literature surrounding these concepts is vast, varied, and somewhat distinct from artificial neural network sources. This article uses bibliometric analysis to survey the last 22 years of literature, seeking to establish trends in publication and citation volumes (III-A); analyze impactful authors, journals and institutions (III-B); generate an introductory reading list (III-C); survey collaborations between countries, institutes and authors (III-D), and to analyze changes in research topics over the years (III-E). We analyze literature data from the Clarivate Web of Science using standard bibliometric methods. By briefly introducing the most impactful literature in this field from the last two decades, we encourage AI practitioners and researchers to look beyond contemporary technologies toward a potentially spiking future of computing.