Application of Deep Learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM TTE Data

Abstract

To investigate GRBs in depth, it is crucial to develop an effective method for identifying GRBs accurately. Current criteria, e.g., onboard blind search, ground blind search, and target search, are limited by manually set thresholds and perhaps miss GRBs, especially for sub-threshold events. We propose a novel approach that utilizes convolutional neural networks (CNNs) to distinguish GRBs and non-GRBs directly. We structured three CNN models, plain-CNN, ResNet, and ResNet-CBAM, and endeavored to exercise fusing strategy models. Count maps of NaI detectors onboard Fermi/GBM were employed as the input samples of datasets and models were implemented to evaluate their performance on different time scale data. The ResNet-CBAM model trained on 64 ms dataset achieves high accuracy overall, which includes residual and attention mechanism modules. The visualization methods of Grad-CAM and t-SNE explicitly displayed that the optimal model focuses on the key features of GRBs precisely. The model was applied to analyze one-year data, accurately identifying approximately 98% of GRBs listed in the Fermi burst catalog, 8 out of 9 sub-threshold GRBs, and 5 GRBs triggered by other satellites, which demonstrated the deep learning methods could effectively distinguish GRBs from observational data. Besides, thousands of unknown candidates were retrieved and compared with the bursts of SGR J1935+2154 for instance, which exemplified the potential scientific value of these candidates indeed. Detailed studies on integrating our model into real-time analysis pipelines thus may improve their accuracy of inspection, and provide valuable guidance for rapid follow-up observations of multi-band telescopes.

arXiv commentaccepted for publication in ApJSS. 45 pages,17 figures

References in corpus (35)

• The Physics of Gamma-Ray Bursts and Relativistic Jets
• Predictions for The Very Early Afterglow and The Optical Flash
• The Fermi GBM Gamma-Ray Burst Spectral Catalog: Four Years Of Data
• The Fourth Fermi-GBM Gamma-Ray Burst Catalog: A Decade of Data
• Gamma-ray burst early optical afterglows: implications for the initial Lorentz factor and the central engine
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• The 3rd Fermi GBM Gamma-Ray Burst Catalog: The First Six Years
• Fast Radio Burst 121102 Pulse Detection and Periodicity: A Machine Learning Approach
• FETCH: A deep-learning based classifier for fast transient classification
• The Ep,i - Eiso correlation: type I gamma-ray bursts and the new classification method
• Burst properties of the most recurring transient magnetar SGR J1935+2154
• Fermi/GBM View of the 2019 and 2020 Burst Active Episodes of SGR J1935+2154
• An Unambiguous Separation of Gamma-Ray Bursts into Two Classes from Prompt Emission Alone
• Gamma-ray Urgent Archiver for Novel Opportunities (GUANO): Swift/BAT event data dumps on demand to enable sensitive sub-threshold GRB searches
• A comprehensive statistical study on gamma-ray bursts
• Analysis of Sub-threshold Short Gamma-ray Bursts in Fermi GBM Data
• A Deep Learning Approach to Infer Galaxy Cluster Masses from Planck Compton$-y$ parameter maps
• Deep Learning Detection and Classification of Gravitational Waves from Neutron Star-Black Hole Mergers
• A Gamma-Ray Burst Trigger Toolkit
• Detection, Instance Segmentation, and Classification for Astronomical Surveys with Deep Learning (DeepDISC): Detectron2 Implementation and Demonstration with Hyper Suprime-Cam Data
• Classification of BATSE, Swift, and Fermi Gamma-Ray Bursts from Prompt Emission Alone
• Revisit the periodicity of SGR J1935+2154 bursts with updated sample
• A Machine-Learning-Based Direction-of-Origin Filter for the Identification of Radio Frequency Interference in the Search for Technosignatures
• Periodicity Search on X-ray Bursts of SGR J1935+2154 Using 8.5 yr of Fermi/GBM Data
• GECAM Localization of High Energy Transients and the Systematic Error
• Prompt-to-afterglow transition of optical emission in a long gamma-ray burst consistent with a fireball
• 81 New Candidate Fast Radio Bursts in Parkes Archive
• Which $E_{\mathrm{peak}}$? - The Characteristic Energy of Gamma-Ray Burst Spectra
• Physical Implications of the Sub-threshold GRB GBM-190816 and its Associated Sub-threshold Gravitational Wave Event
• A Deep Learning Method for AGILE-GRID GRB Detection
• AutoSourceID-Classifier. Star-Galaxy Classification using a Convolutional Neural Network with Spatial Information
• Target Detection Framework for Lobster Eye X-Ray Telescopes with Machine Learning Algorithms
• Deep learning techniques for Imaging Air Cherenkov Telescopes
• A machine learning approach for GRB detection in AstroSat CZTI data
• LRP2020: Machine Learning Advantages in Canadian Astrophysics

Cited by in corpus (1)

• Gamma-ray burst light curve reconstruction with predictive models