Enhancing Gamma-Ray Burst Detection: Evaluation of Neural Network Background Estimator and Explainable AI Insights

被引:0
作者
Crupi, Riccardo [1 ,2 ]
Dilillo, Giuseppe [3 ]
Della Casa, Giovanni [3 ]
Fiore, Fabrizio [2 ]
Vacchi, Andrea [1 ,4 ]
机构
[1] Univ Udine, Dipartimento Sci Matemat Informat & Fis, Via Sci 206, I-33100 Udine, Italy
[2] INAF, Osservatorio Astron Trieste, Via Tiepolo 11, I-34143 Trieste, Italy
[3] INAF, IAPS, Via Fosso Cavaliere 100, I-00133 Rome, Italy
[4] INFN, Sez Trieste, Via Padriciano 99, I-34149 Trieste, Italy
来源
GALAXIES | 2024年 / 12卷 / 02期
关键词
GRB; neural network; XAI;
D O I
10.3390/galaxies12020012
中图分类号
P1 [天文学];
学科分类号
0704 ;
摘要
The detection of Gamma-Ray Bursts (GRBs) using spaceborne X/gamma-ray photon detectors depends on a reliable background count rate estimate. This study focuses on evaluating a data-driven background estimator based on a neural network designed to adapt to various X/gamma-ray space telescopes. Three trials were conducted to assess the effectiveness and limitations of the proposed estimator. Firstly, quantile regression was employed to obtain an estimation with a confidence range prediction. Secondly, we assessed the performance of the neural network, emphasizing that a dataset of four months is sufficient for training. We tested its adaptability across various temporal contexts, identified its limitations and recommended re-training for each specific period. Thirdly, utilizing Explainable Artificial Intelligence (XAI) techniques, we delved into the neural network output, determining distinctions between a network trained during solar maxima and one trained during solar minima. This entails conducting a thorough analysis of the neural network behavior under varying solar conditions.
引用
收藏
页数:13
相关论文
共 20 条
  • [11] Hui C., 2017, P 7 INT FERM S, P129
  • [12] Analysis of Sub-threshold Short Gamma-Ray Bursts in Fermi GBM Data
    Kocevski, D.
    Burns, E.
    Goldstein, A.
    Dal Canton, T.
    Briggs, M. S.
    Blackburn, L.
    Veres, P.
    Hui, C. M.
    Hamburg, R.
    Roberts, O. J.
    Wilson-Hodge, C. A.
    Connaughton, V.
    Racusin, J.
    Littenberg, T.
    von Kienlin, A.
    Bissaldi, E.
    [J]. ASTROPHYSICAL JOURNAL, 2018, 862 (02)
  • [13] Kommers J.M., 1999, Ph.D. Thesis
  • [14] Lundberg SM, 2017, ADV NEUR IN, V30
  • [15] THE FERMI GAMMA-RAY BURST MONITOR
    Meegan, Charles
    Lichti, Giselher
    Bhat, P. N.
    Bissaldi, Elisabetta
    Briggs, Michael S.
    Connaughton, Valerie
    Diehl, Roland
    Fishman, Gerald
    Greiner, Jochen
    Hoover, Andrew S.
    van der Horst, Alexander J.
    Von Kienlin, Andreas
    Kippen, R. Marc
    Kouveliotou, Chryssa
    McBreen, Sheila
    Paciesas, W. S.
    Preece, Robert
    Steinle, Helmut
    Wallace, Mark S.
    Wilson, Robert B.
    Wilson-Hodge, Colleen
    [J]. ASTROPHYSICAL JOURNAL, 2009, 702 (01) : 791 - 804
  • [16] FACTORIAL SAMPLING PLANS FOR PRELIMINARY COMPUTATIONAL EXPERIMENTS
    MORRIS, MD
    [J]. TECHNOMETRICS, 1991, 33 (02) : 161 - 174
  • [17] Nori H, 2019, Arxiv, DOI arXiv:1909.09223
  • [18] The fourth BATSE gamma-ray burst catalog (revised)
    Paciesas, WS
    Meegan, CA
    Pendleton, GN
    Briggs, MS
    Kouveliotou, C
    Koshut, TM
    Lestrade, JP
    McCollough, ML
    Brainerd, JJ
    Hakkila, J
    Henze, W
    Preece, RD
    Connaughton, V
    Kippen, RM
    Mallozzi, RS
    Fishman, GJ
    Richardson, GA
    Sahi, M
    [J]. ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES, 1999, 122 (02) : 465 - 495
  • [19] Sadeh I, 2019, Arxiv, DOI arXiv:1902.03620
  • [20] Poisson-FOCuS: An Efficient Online Method for Detecting Count Bursts with Application to Gamma Ray Burst Detection
    Ward, Kes
    Dilillo, Giuseppe
    Eckley, Idris
    Fearnhead, Paul
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2025, 120 (549) : 7 - 19