A study of Neural networks point source extraction on simulated Fermi/LAT Telescope images
| Autor: | Drozdova Mariia, Ustyuzhanin Andrey, Malyshev Denys, Broilovskiy Anton |
|---|---|
| Přispěvatelé: | École polytechnique (X) |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Point spread function
FOS: Computer and information sciences Point source Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition FOS: Physical sciences 01 natural sciences Convolutional neural network law.invention Telescope law 0103 physical sciences Point (geometry) [INFO]Computer Science [cs] gamma rays: observations – techniques: image processing 010303 astronomy & astrophysics Physics High Energy Astrophysical Phenomena (astro-ph.HE) Artificial neural network 010308 nuclear & particles physics business.industry Astronomy and Astrophysics Pattern recognition telescopes – methods: data analysis Data set Space and Planetary Science Artificial intelligence business [PHYS.ASTR]Physics [physics]/Astrophysics [astro-ph] Astrophysics - High Energy Astrophysical Phenomena catalogs Fermi Gamma-ray Space Telescope |
| Zdroj: | Astron.Nachr. Astron.Nachr., 2020, 341 (8), pp.819-826. ⟨10.1002/asna.202013788⟩ |
| Popis: | Astrophysical images in the GeV band are challenging to analyze due to the strong contribution of the background and foreground astrophysical diffuse emission and relatively broad point spread function of modern space-based instruments. In certain cases, even finding of point sources on the image becomes a non-trivial task. We present a method for point sources extraction using a convolution neural network (CNN) trained on our own artificial data set which imitates images from the Fermi Large Area Telescope. These images are raw count photon maps of 10x10 degrees covering energies from 1 to 10 GeV. We compare different CNN architectures that demonstrate accuracy increase by ~15% and reduces the inference time by at least the factor of 4 accuracy improvement with respect to a similar state of the art models. Accepted to Astronomische Nachrichten |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|