EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Segmenting RFI Using Meta’s Segment Anything Model

Derod Deal, Preshanth Jagannathan

Research Notes of the AAS · 14.10.2024 · 8 (10) · 257

DOI: 10.3847/2515-5172/ad84fa ↗

Kurz gefasst

Fachartikel in der Zeitschrift Research Notes of the AAS, online erschienen am 14.10.2024. Verfasst von Derod Deal und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 8 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Radio Frequency Interference (RFI), radio signals from electronics, permeates through astronomical observations using radio telescopes. The interference results in lower sensitivity and higher noise when present. Existing methods, such as TFCrop and RFlag, flag RFI to prevent the contamination of observations. However, these approaches are partially automatic and require manual input to flag RFI. We explore artificial intelligence methods using Meta’s Segment Anything Model (SAM) and its parameter space in segmenting RFI. We have developed an open-source pipeline called SamRFI , which segments and flags RFI from measurement sets. We trained SAM’s masking weights from Hugging Face to fine-tune the model using Very Large Array data and synthetic waterfall plots injected with RFI. We define a metric, calcquality , to measure the performance of our models based on sensitivity and overflagging. Retrained SAM models identify RFI structure and allow for further exploration in RFI segmentation.

Förderung

  • National Science Foundation

Zitieren

APA

Deal, D., & Jagannathan, P. (2024). Segmenting RFI Using Meta’s Segment Anything Model. Research Notes of the AAS, 8(10), 257. https://doi.org/10.3847/2515-5172/ad84fa

Vancouver

Deal D, Jagannathan P. Segmenting RFI Using Meta’s Segment Anything Model. Research Notes of the AAS. 2024;8(10):257. doi:10.3847/2515-5172/ad84fa

BibTeX
@article{Deal2024,
  author = {Deal, Derod and Jagannathan, Preshanth},
  title = {Segmenting RFI Using Meta’s Segment Anything Model},
  journal = {Research Notes of the AAS},
  year = {2024},
  volume = {8},
  number = {10},
  pages = {257},
  doi = {10.3847/2515-5172/ad84fa}
}
Kostenlos starten →