اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدBackground Rejection in Atmospheric Cherenkov Telescopes using Recurrent Convolutional Neural Networks
67
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
In this work, we present a new, high performance algorithm for background rejection in imaging atmospheric Cherenkov telescopes. We build on the already popular machine-learning techniques used in gamma-ray astronomy by the application of the latest techniques in machine learning, namely recurrent and convolutional neural networks, to the background rejection problem. Use of these machine-learning techniques addresses some of the key challenges encountered in the currently implemented algorithms and helps to significantly increase the background rejection performance at all energies. We apply these machine learning techniques to the H.E.S.S. telescope array, first testing their performance on simulated data and then applying the analysis to two well known gamma-ray sources. With real observational data we find significantly improved performance over the current standard methods, with a 20-25% reduction in the background rate when applying the recurrent neural network analysis. Importantly, we also find that the convolutional neural network results are strongly dependent on the sky brightness in the source region which has important implications for the future implementation of this method in Cherenkov telescope analysis.
قيم البحث
اقرأ أيضاً
Arrays of Cherenkov telescopes typically use multi-level trigger schemes to keep the rate of random triggers from the night sky background low. At a first stage, individual telescopes produce a trigger signal from the pixel information in the telesco
pe camera. The final event trigger is then formed by combining trigger signals from several telescopes. In this poster, we present a possible scheme for the Cherenkov Telescope Array telescope trigger, which is based on the analog pulse information of the pixels in a telescope camera. Advanc
The stereoscopic imaging atmospheric Cherenkov technique, developed in the 1980s and 1990s, is now used by a number of existing and planned gamma-ray observatories around the world. It provides the most sensitive view of the very high energy gamma-ra
y sky (above 30 GeV), coupled with relatively good angular and spectral resolution over a wide field-of-view. This Chapter summarizes the details of the technique, including descriptions of the telescope optical systems and cameras, as well as the most common approaches to data analysis and gamma-ray reconstruction.
The IceCube Neutrino Observatory has revealed the existence of sources of high-energy astrophysical neutrinos. However, identification of the sources is challenging because astrophysical neutrinos are difficult to separate from the background of atmo
spheric neutrinos produced in cosmic-ray-induced particle cascades in the atmosphere. The efficient detection of air showers in coincidence with detected neutrinos can greatly reduce those backgrounds and increase the sensitivity of neutrino telescopes. Imaging Air Cherenkov Telescopes (IACTs) are sensitive to gamma-ray-induced (and cosmic-ray-induced) air showers in the 50 GeV to 50 TeV range, and can therefore be used as background-identifiers for neutrino observatories. This paper describes the feasibility of an array of small scale, wide field-of-view, cost-effective IACTs as an air shower veto for neutrino astronomy. A surface array of 250 to 750 telescopes would significantly improve the performance of a cubic kilometer-scale detector like IceCube, at a cost of a few percent of the original investment. The number of telescopes in the array can be optimized based on astronomical and geometrical considerations.
Imaging Atmospheric Cherenkov Telescopes (IACTs) currently in operation feature large mirrors and order of 1 ns time response to signals of a few photo-electrons produced by optical photons. This means that they are ideally suited for optical interfe
rometry observations. Thanks to their sensitivity to visible wavelengths and long baselines optical intensity interferometry with IACTs allows reaching angular resolutions of tens to microarcsec. We have installed a simple optical setup on top of the cameras of the two 17 m diameter MAGIC IACTs and observed coherent fluctuations in the photon intensity measured at the two telescopes for three different stars. The sensitivity is roughly 10 times better than that achieved in the 1970s with the Narrabri interferometer.
Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the N
EXT experiment, which will search for neutrinoless double-beta decay in $^{136}$Xe. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6-MeV gamma rays from a $^{228}$Th calibration source. We train a network on Monte Carlo-simulated events and show that, by applying on-the-fly data augmentation, the network can be made robust against differences between simulation and data. The use of CNNs offer significant improvement in signal efficiency/background rejection when compared to previous non-CNN-based analyses.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
