arXiv subjects

Andreas Wicenec

Publications and source records attributed to Andreas Wicenec.

At least 19 recordsLinked to original sources

arXiv2026

The Potential Impact of Neuromorphic Computing on Radio Telescope Observatories

Radio astronomy relies on bespoke, experimental and innovative computing solutions. This will continue as next-generation telescopes such as the Square Kilometre Array (SKA) and next-generation Very Large Array (ngVLA) take shape. Under increasingly demanding power consumption, and increasingly challenging radio environments, science goals may become intractable with conventional von Neumann computing due to related power requirements. Neuromorphic computing offers a compelling alternative, and combined with a desire for data-driven methods, Spiking Neural Networks (SNNs) are a promising real-time power-efficient alternative. Radio Frequency Interference (RFI) detection is an attractive use-case for SNNs where recent exploration holds promise. This work presents a comprehensive analysis of the potential impact of deploying varying neuromorphic approaches across key stages in radio astronomy processing pipelines for several existing and near-term instruments. Our analysis paves a realistic path from near-term FPGA deployment of SNNs in existing instruments, allowing the addition of advanced data-driven RFI detection for no capital cost, to neuromorphic ASICs for future instruments, finding that commercially available solutions could reduce the power budget for key processing elements by up to three orders of magnitude, transforming the operational budget of the observatory. High-data-rate spectrographic processing could be a well-suited target for the neuromorphic computing industry, as we cast radio telescopes as the world's largest in-sensor compute challenge.

astro-ph.IM↗

arXiv2025

Searching for binary black hole mergers with deep learning in Advanced LIGO's third observing run

The detection of gravitational waves from compact binary coalescences has provided significant insights into our Universe, and the discovery of new and unique gravitational wave candidates from independent searches remains an ongoing field of research. In this work, we built a hybrid search pipeline that combines matched filtering and deep learning to identify stellar-mass binary black hole candidates from detector strain data. We first present results from a targeted injection study to benchmark the sensitivity of our method and compare it with existing search pipelines. We demonstrate that our hybrid approach has comparable sensitivity for injections with a source-frame chirp mass greater than 25$\,$M$_{\odot}$, and below this threshold our sensitivity drops off for signals with a network SNR less than 15. We also observe that our search method can identify a significant population of unique candidates. Furthermore, we conduct an offline search for gravitational wave candidates in the third observing run of the LIGO-Virgo-KAGRA Collaboration (LVK), yielding 31 candidates previously reported by the LVK with a probability of astrophysical origin $p_{\rm astro}\geq0.5$. We identify two other candidates: one previously reported only in a search conducted by the Institute for Advanced Study, and one previously unreported promising new candidate with a $p_{\rm astro}$ of 0.63. This unique candidate has a high chirp mass and a high probability that the primary black hole is an intermediate-mass black hole.

gr-qc↗

arXiv2025

Neuromorphic Astronomy: An End-to-End SNN Pipeline for RFI Detection Hardware

Imminent radio telescope observatories provide massive data rates making deep learning based processing appealing while simultaneously demanding real-time performance at low-energy; prohibiting the use of many artificial neural network based approaches. We begin tackling the scientifically existential challenge of Radio Frequency Interference (RFI) detection by deploying deep Spiking Neural Networks (SNNs) on resource-constrained neuromorphic hardware. Our approach partitions large, pre-trained networks onto SynSense Xylo hardware using maximal splitting, a novel greedy algorithm. We validate this pipeline with on-chip power measurements, achieving instrument-scaled inference at 100mW. While our full-scale SNN achieves state-of-the-art accuracy among SNN baselines, our experiments reveal a more important insight that a smaller un-partitioned model significantly outperforms larger, split models. This finding highlights that hardware co-design is paramount for optimal performance. Our work thus provides a practical deployment blueprint, a key insight into the challenges of model scaling, and reinforces radio astronomy as a demanding yet ideal domain for advancing applied neuromorphic computing.

cs.NE↗

arXiv2025

Polarisation-Inclusive Spiking Neural Networks for Real-Time RFI Detection in Modern Radio Telescopes

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.

cs.NE↗

arXiv2025

Advancing RFI-Detection in Radio Astronomy with Liquid State Machines

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.

cs.NE↗

arXiv2025

Optimising the Processing and Storage of Visibilities using lossy compression

The next-generation radio astronomy instruments are providing a massive increase in sensitivity and coverage, through increased stations in the array and frequency span. Two primary problems encountered when processing the resultant avalanche of data are the need for abundant storage and I/O. An example of this is the data deluge expected from the SKA Telescopes of more than 60PB per day, all to be stored on the buffer filesystem. Compressing the data is an obvious solution. We used MGARD, an error-controlled compressor, and applied it to simulated and real visibility data, in noise-free and noise-dominated regimes. As the data has an implicit error level in the system temperature, using an error bound in compression provides a natural metric for compression. Measuring the degradation of images reconstructed using the lossy compressed data, we explore the trade-off between these error bounds and the corresponding compression ratios, as well as the impact on science quality derived from the lossy compressed data products through a series of experiments. We studied the global and local impacts on the output images. We found relative error bounds of as much as $10\%$, which provide compression ratios of about 20, have a limited impact on the continuum imaging as the increased noise is less than the image RMS. For extremely sensitive observations and for very precious data, we would recommend a $0.1\%$ error bound with compression ratios of about 4. These have noise impacts two orders of magnitude less than the image RMS levels. At these levels, the limits are due to instabilities in the deconvolution methods. We compared the results to the alternative compression tool DYSCO, in both the impacts on the images and in the relative flexibility. MGARD provides better compression for similar error bounds, and has a host of potentially powerful additional features.

astro-ph.IM↗

arXiv2025

Binary Neutron Star Merger Search Pipeline Powered by Deep Learning

Gravitational waves are now routinely detected from compact binary mergers, with binary neutron star mergers being of note for multi-messenger astronomy as they have been observed to produce electromagnetic counterparts. Novel search pipelines for these mergers could increase the combined search sensitivity, and could improve the ability to detect real gravitational wave signals in the presence of glitches and non-stationary detector noise. Deep learning has found success in other areas of gravitational wave data analysis, but a sensitive deep learning-based search for binary neutron star mergers has proven elusive due to their long signal length. In this work, we present a deep learning pipeline for detecting binary neutron star mergers. By training a convolutional neural network to detect binary neutron star mergers in the signal-to-noise ratio time series, we concentrate signal power into a shorter and more consistent timescale than strain-based methods, while also being able to train our network to be robust against glitches. We compare our pipeline's sensitivity to the three offline detection pipelines using injections in real gravitational wave data, and find that our pipeline has a comparable sensitivity to the current pipelines below the 1 per 2 months detection threshold. Furthermore, we find that our pipeline can increase the total number of binary neutron star detections by 12% at a false alarm rate of 1 per 2 months. The pipeline is also able to successfully detect the two binary neutron star mergers detected so far by the LIGO-Virgo-KAGRA collaboration, GW170817 and GW190425, despite the loud glitch present in GW170817.

gr-qc↗

arXiv2025

Novel Deep Learning Approach to Detecting Binary Black Hole Mergers

Gravitational wave detection has opened up new avenues for exploring and understanding some of the fundamental principles of the universe. The optimal method for detecting modelled gravitational-wave events involves template-based matched filtering and performing a multi-detector coincidence search in the resulting signal-to-noise ratio time series. In recent years, advancements in machine learning and deep learning have led to a flurry of research into using these techniques to replace matched filtering searches and for efficient and robust parameter estimation of the gravitational wave sources. This paper presents a feasibility study for a novel approach to detecting binary black hole gravitational wave signals, which utilizes deep learning techniques on the signal-to-noise ratio time series produced from matched filtering. We show that a deep-learning search can efficiently detect binary black hole gravitational waves from the signal-to-noise ratio time series in simulated Gaussian noise with simulated transient glitches. Furthermore, our search method can outperform a maximum SNR-based matched filtering search on simulated data of the Hanford and Livingston LIGO detectors in the presence of glitches. We further demonstrate that our approach can improve the detection sensitivity for binary black hole mergers at lower masses, relative to a baseline sensitivity of existing search pipelines and deep learning approaches. Lastly, since we are building upon the foundations of a matched filtering search pipeline, we can extract estimates for the signal-to-noise ratio and detector frame chirp mass of a gravitational wave event with similar accuracy as existing pipelines.

gr-qc↗

arXiv2024

Formal Definition and Implementation of Reproducibility Tenets for Computational Workflows

Computational workflow management systems power contemporary data-intensive sciences. The slowly resolving reproducibility crisis presents both a sobering warning and an opportunity to iterate on what science and data processing entails. The Square Kilometre Array (SKA), the world's largest radio telescope, is among the most extensive scientific projects underway and presents grand scientific collaboration and data-processing challenges. In this work, we aim to improve the ability of workflow management systems to facilitate reproducible, high-quality science. This work presents a scale and system-agnostic computational workflow model and extends five well-known reproducibility concepts into seven well-defined tenets for this workflow model. Additionally, we present a method to construct workflow execution signatures using cryptographic primitives in amortized constant time. We combine these three concepts and provide a concrete implementation in Data Activated Flow Graph Engine (DALiuGE), a workflow management system for the SKA to embed specific provenance information into workflow signatures, demonstrating the possibility of facilitating automatic formal verification of scientific quality in amortized constant time. We validate our approach with a simple yet representative astronomical processing task: filtering a noisy signal with a lowpass filter using CPU and GPU methods. This example shows the practicality and efficacy of combining formal tenet definitions with a workflow signature generation mechanism. Our framework, spanning formal UML specification, principled provenance information collection based on reproducibility tenets, and finally, a concrete example implementation in DALiuGE illuminates otherwise obscure scientific discrepancies and similarities between principally identical workflow executions.

cs.DC↗

arXiv2024

Spiking Neural Networks for Radio Frequency Interference Detection in Radio Astronomy

Spiking Neural Networks (SNNs) promise efficient and dynamic spatio-temporal data processing. This paper reformulates a significant challenge in radio astronomy, Radio Frequency Interference (RFI) detection, as a time-series segmentation task suited for SNN execution. Automated systems capable of real-time operation with minimal energy consumption are increasingly important in modern radio telescopes. We explore several spectrogram encoding methods and network parameters, applying first and second-order leaky integrate and fire SNNs to tackle RFI detection. We introduce a divisive normalisation-inspired pre-processing step, improving detection performance across multiple encodings strategies. Our approach achieves competitive performance on a synthetic dataset and compelling initial results on real data from the Low-Frequency Array (LOFAR). We position SNNs as a viable path towards real-time RFI detection, with many possibilities for follow-up studies. These findings highlight the potential for SNNs performing complex time-series tasks, paving the way towards efficient, real-time processing in radio astronomy and other data-intensive fields.

cs.NE↗

arXiv2024

Supervised Radio Frequency Interference Detection with SNNs

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 twolayer 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.

cs.NE↗

arXiv2024

Deep Investigation of Neutral Gas Origins (DINGO): Options for the Processing and Storage of Radio Astronomy Data for robust Deep Spectral Line Imaging in the SKA-Era using uv-Grids

The next generation of radio astronomy telescopes are challenging existing data analysis paradigms, as they have an order of magnitude more antennas and larger bandwidth. Foremost amongst these are deep spectral line surveys, because these have the largest number of epochs and spectral channels per dataset. For example, the Deep Investigation of Neutral Gas Origins (DINGO) project on the Australian Square Kilometre Array Pathfinder (ASKAP) aims to observe over 3,200 hours spread over hundreds of observing sessions, covering two tiles, two footprints and two frequency settings. The two primary problems encountered when processing this data are the need for storage and that processing is primarily I/O limited. To address these issues, we have implemented a deep imaging pipeline based on the storage of an intermediate data product in the software ASKAPsoft, that of the uv-gridded data, and have demonstrated lossy and lossless compression of this data on ASKAP, using MGARD and ADIOS2 libraries. We find data compression ratios from a factor of 7 (lossless) up to 20 (using lossy compression with an absolute error bound of $10^{-4}$), and processing is significantly faster for lossless compression. We discuss the effectiveness of lossy MGARD compression and its adherence to the designated error bounds, the trade-off between these error bounds and the corresponding compression ratios, as well as the potential consequences of these I/O and storage improvements on the science quality of the data products. As lossless compression allows us to achieve the DINGO goals within the storage limitations for the project, this will be the option adopted.

astro-ph.IM↗

arXiv2023

RFI Detection with Spiking Neural Networks

Detecting and mitigating Radio Frequency Interference (RFI) is critical for enabling and maximising the scientific output of radio telescopes. The emergence of machine learning methods has led to their application in radio astronomy, and in RFI detection. Spiking Neural Networks (SNNs), inspired by biological systems, are well-suited for processing spatio-temporal data. This study introduces the first exploratory 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. Our subsequent evaluation aims to determine whether SNNs are viable for future RFI detection schemes. We evaluate detection performance with the simulated HERA telescope and hand-labelled LOFAR observation dataset the original authors provided. We additionally evaluate detection performance with a new MeerKAT-inspired simulation dataset that provides a technical challenge for machine-learnt RFI detection methods. This dataset focuses on satellite-based RFI, an increasingly important class of RFI and is an additional contribution. Our approach remains competitive with existing methods in AUROC, AUPRC and F1 scores for the HERA dataset but exhibits difficulty in the LOFAR and Tabascal datasets. Our method maintains this accuracy 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.

astro-ph.IM↗

arXiv2023

A Bibliometric Review of Neuromorphic Computing and Spiking Neural Networks

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.

cs.NE↗

arXiv2022

Radio Transient Detection with Closure Products and Machine Learning

For transient sources with timescales of 1-100 seconds, standardized imaging for all observations at each time step become impossible as large modern interferometers produce significantly large data volumes in this observation time frame. Here we propose a method based on machine learning and using interferometric closure products as input features to detect transient source candidates directly from the spatial frequency domain without imaging. We train a simple neural network classifier on a synthetic dataset of Noise/Transient/RFI events, which we construct to tackle the lack of labelled data. We also use the hyper-parameter dropout rate of the model to allow the model to approximate Bayesian inference, and select the optimal dropout rate to match the posterior prediction to the actual underlying probability distribution of the detected events. The overall F1-score of the classifier on the simulated dataset is greater than 85\%, with the signal-to-noise at 7$σ$. The performance of the trained neural network with Monte Carlo dropout is evaluated on semi-real data, which includes a simulated transient source and real noise. This classifier accurately identifies the presence of transient signals in the detectable signal-to-noise levels (above 4$σ$) with the optimal variance. Our findings suggest that a feasible radio transient classifier can be built up with only simulated data for applying to the prediction of real observation, even in the absence of annotated real samples for the purpose of training.

astro-ph.IM↗

arXiv2021

An Empirical Evaluation On the Applicability of the DALiuGE Execution Framework

The Square Kilometre Array (SKA) project is an international cooperation project to build the largest radio telescope worldwide. Data processing is one of the biggest challenges of building the SKA telescope. As a distributed execution framework, the Data Activated Liu Graph Engine (DALiuGE) was proposed to be one of the candidates for addressing the massive data of the SKA. DALiuGE has many distinctive features, but its actual ability to handle scientific data is still not evident. In this paper, we perform an objective evaluation of the usability of DALiuGE concerning the execution performance, developer workload, and implementation difficulty of porting the SAGECal to DALiuGE. The evaluation results showed that the DALiuGE enables fast integration of astronomical software, but there are significant differences in the efficiency of different parallel granularities. Even with the deep optimization of the program, there is still a gap between the current DALiuGE and the traditional MPI in execution performance. Therefore, we come to a preliminary conclusion that the DALiuGE has no performance advantage in batch processing of massive data, while it may be more suitable for application scenarios with more customized computational tasks, such as SKA science regional centers.

astro-ph.IM↗

arXiv2021

Enhanced Remote Astronomical Archive System Based on the File-Level Unlimited Sliding-Window Technique

Data archiving is one of the most critical issues for modern astronomical observations. With the development of a new generation of radio telescopes, the transfer and archiving of massive remote data have become urgent problems to be solved. Herein, we present a practical and robust file-level flow-control approach, called the Unlimited Sliding-Window (USW), by referring to the classic flow-control method in TCP protocol. Basing on the USW and the Next Generation Archive System (NGAS) developed for the Murchison Widefield Array telescope, we further implemented an enhanced archive system (ENGAS) using ZeroMQ middleware. The ENGAS substantially improves the transfer performance and ensures the integrity of transferred files. In the tests, the ENGAS is approximately three to twelve times faster than the NGAS and can fully utilize the bandwidth of network links. Thus, for archiving radio observation data, the ENGAS reduces the communication time, improves the bandwidth utilization, and solves the remote synchronous archiving of data from observatories such as Mingantu spectral radioheliograph. It also provides a better reference for the future construction of the Square Kilometer Array (SKA) Science Regional Center.

astro-ph.IM↗

arXiv2019

SKA shakes hands with Summit

Recently, a full-scale data processing workflow of the Square Kilometre Array (SKA) Phase 1 was successfully executed on the world's fastest supercomputer Summit, proving that scientists have the expertise, software tools and computing resources to process the SKA data. The SKA-Summit experiment shows the importance of multidisciplinary cooperation between astronomy, computer science and others communities. The SKA science cannot be achieved without the joint efforts of talents from multiple fields.

astro-ph.IM↗