Radio Astronomy

Follow this topic Ask about this topic

Latest papers

8 papers2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Missed Detections and False Alarms in a CNN Technosignature Detector on Breakthrough Listen Data
Oct 15, 2026Omer ImranRadio Astronomy Distribution Shift Robustness
Independent researcher
SIFARI: Self-Supervised Interferometric Fitting for Astronomical Radio Imaging
Sep 28, 2026Shunyuan Mao, Andrea Isella, Paris Perdikaris +2Radio Astronomy Image Reconstruction
Department of Physics and Astronomy, Rice University, 6100 Main St, Houston, TX 77005, USA · Rice Space Institute, Rice University, 6100 Main St, Houston, TX 77005, USA · National Radio Astronomy Observatory, 520 Edgemont Road, Charlottesville, VA 22903, USA +4
Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy
Jul 23, 2026Elisa Chiarotto, Jingbo Li, P. Chris Broekema +1Large Language Model-Guided Optimization Code Generation
LIACS, Leiden University · NWO-I ASTRON
Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector
Jul 8, 2026Raiff H. Santos, Amilcar R. Queiroz, Tharcisyo S. S. Duarte +2VLM Evaluation Zero-Shot Learning
Universidade Federal de Campina Grande, R. Apr´ıgio Veloso 882, Bairro Universit´ario, 58429-900, Campina Grande, PB, Brazil · Instituto de Forma¸c˜ao de Educadores, Universidade Federal do Cariri, Rua Oleg´ario Em´ıdio de Ara´ujo, s/n, Aldeota, 63260-000, Brejo Santo, CE, Brazil
FRTSearch: Unified Detection and Parameter Inference of Fast Radio Transients using Instance Segmentation
Apr 14, 2026Bin Zhang, Yabiao Wang, Xiaoyao Xie +11Radio Astronomy Parameter Estimation
School of Mathematical Sciences, Guizhou Normal University, Guiyang 550001, China · Guizhou Provincial Key Laboratory of Information and Computing Science , Guizhou Normal University, Guiyang 550001, China · School of Cyber Science and Technology, Guizhou Normal University, Guiyang 550001, China +7
STRADAViT: Self-Supervised Domain Adaptation of Vision Transformer Backbones for Radio Astronomy
Mar 31, 2026Andrea DeMarco, Ian Fenech Conti, Hayley Camilleri +2Radio Astronomy Domain-Adaptive Pretraining
Institute of Space Sciences and Astronomy, University of Malta, Msida, MSD2080, Malta · School of Physics and Astronomy, Royal Observatory, University of Edinburgh, Edinburgh, United Kingdom · Istituto Nazionale di Astrofisica (INAF), Osservatorio Astrofisico di Catania, Catania, Italy
Explainable machine learning workflows for radio astronomical data processing
Mar 17, 2026S. Yatawatta, A. Ahmadi, B. Asabere +3Radio Astronomy Interpretable ML
ASTRON, The Netherlands Institute for Radio Astronomy, Dwingeloo, The Netherlands
POLISH'ing the Sky: Wide-Field and High-Dynamic Range Interferometric Image Reconstruction with Application to Strong Lens Discovery
Mar 10, 2026Zihui Wu, Liam Connor, Samuel McCarty +1Radio Astronomy Image Reconstruction
Department of Computing and Mathematical Sciences, California Institute of Technology (Caltech), Pasadena, CA, USA · Center for Astrophysics | Harvard & Smithsonian, Cambridge, MA, USA

Oct 15, 2026J/K move · Enter open · S save

Missed Detections and False Alarms in a CNN Technosignature Detector on Breakthrough Listen Data

Omer Imran

Independent researcher

Radio Astronomy Distribution Shift Robustness Convolutional Neural Networks

Open paper AskPDF arXiv

Radio technosignature searches rely on machine learning detectors to shrink the candidate pool before a human looks at it. They are validated on held-out data from the training distribution, which excludes the cases where they are most likely to fail: a technosignature has unknown morphology, and terrestrial interference is unbounded in variety. I trained a standard competition detector once, froze it, and probed it with 15,000 injections across ten morphologies and five amplitudes, placed into real Green Bank backgrounds. Two directions were tested: genuine signals with morphologies other than a straight narrowband line, and interference resembling the training data. Recall did not follow the predicted ordering, and it fell as signals brightened, even for a needle of the kind the detector was trained on (from 0.590 to 0.090). One interference morphology reached a false positive rate of 0.627, comparable to the detector's own baseline recall of 0.5525 on genuine signals. Gradient-weighted Class Activation Mapping (Grad-CAM) showed attention along the injected path in one missed family by a pre-specified test, and visually in a second. A pre-specified, time-averaged ON-OFF filter removed false alarms and genuine detections at the same rate. The detector reads only the ON panels. Since the only evidence distinguishing a genuine candidate from terrestrial interference lies in the discarded OFF panels, it cannot tell if a signal originates from the target star; it can only tell if it resembles the training data. This explains the false alarm directly; the missed signals reflect what the detector learned to recognise, which reading the OFF panels would not by itself change.