EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing fast radio transient detection with Mask R-CNN image segmentation

Sergio Belmonte Díaz, Rene P Breton, Zafiirah Hosenie, Benjamin W Stappers

RAS Techniques and Instruments · 06.01.2026 · 5

DOI: 10.1093/rasti/rzag006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift RAS Techniques and Instruments, online erschienen am 21.01.2026. Verfasst von Sergio Belmonte Díaz und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Facilities Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditionally, fast radio transient searches are conducted on dedispersed time series using thresholding techniques. However, peaks in dedispersed time series do not directly provide information on the nature of the source. In the DM–time domain, the S/N variation of real, dispersed astrophysical signals forms a characteristic bow tie shape, whereas radio frequency interference (RFI) can take multiple different forms. We have developed a method that bypasses the thresholding step of traditional single-pulse searches in favour of a direct DM–time domain image analysis. We further generalize the expected S/N degradation of a single pulse as a function of dispersion measure to define physically motivated DM and time ranges for constructing optimal search windows. We also propose a modified version of the traditional dedispersion plan optimized for this method. The backbone of our pipeline is a Mask R-CNN, a deep learning model designed for object detection, enabling it to identify the bow tie signature and distinguish real sources from RFI. We have trained the model on simulated bursts injected on top of real MeerKAT noise observations. We tested the model on MeerKAT follow-up observations of the repeater FRB20240114A and we were able to recover all bursts with a signal-to-noise above the traditional threshold, while detecting two bursts that were fainter. Notably, the pipeline can identify multiple bursts within the same search window. Our new approach considerably reduces the number of candidates above a nominal threshold while being capable of running in real time for typical surveys.

Förderung

  • Science and Technology Facilities Council

Zitieren

APA

Díaz, S. B., Breton, R. P., Hosenie, Z., & Stappers, B. W. (2026). Enhancing fast radio transient detection with Mask R-CNN image segmentation. RAS Techniques and Instruments, 5. https://doi.org/10.1093/rasti/rzag006

Vancouver

Díaz SB, Breton RP, Hosenie Z, Stappers BW. Enhancing fast radio transient detection with Mask R-CNN image segmentation. RAS Techniques and Instruments. 2026;5. doi:10.1093/rasti/rzag006

BibTeX
@article{Daz2026,
  author = {Díaz, Sergio Belmonte and Breton, Rene P and Hosenie, Zafiirah and Stappers, Benjamin W},
  title = {Enhancing fast radio transient detection with Mask R-CNN image segmentation},
  journal = {RAS Techniques and Instruments},
  year = {2026},
  volume = {5},
  doi = {10.1093/rasti/rzag006}
}
Kostenlos starten →