Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LUNCH: A Lightweight Unified Deep-Learning Framework for General Transients Classification in High-Energy Time-Domain Astronomy

Peng Zhang, Chen-Wei Wang, Zheng-Hang Yu, Ren-Zhou Gui, Shao-Lin Xiong, Xiao-Bo Li, Li-Ming Song, Shi-Jie Zheng, Xiao-Yun Zhao, Yue Huang, Wang-Chen Xue, Ya-Qi Wang, Long-Bo Han, Jia-Cong Liu, Chao Zheng, Wen-Jun Tan, Sheng-Lun Xie, Ce Cai, Yan-Qiu Zhang, Hao-Xuan Guo, Yue Wang, Yang-Zhao Ren

TL;DR

The Lightweight Unified Neural Classifier for High-energy Transients (LUNCH) is developed - an end-to-end deep-learning framework that performs general transient classification directly from raw multi-band light curves, eliminating the need for background subtraction or source localization.

Abstract

The increasing data volume of high-energy space monitors necessitates real-time, automated transient classification for multi-messenger follow-up. Conventional methods rely on empirical features like hardness ratios and reliable localization, which are not always precisely available during early detection. We developed the Lightweight Unified Neural Classifier for High-energy Transients (LUNCH) - an end-to-end deep-learning framework that performs general transient classification directly from raw multi-band light curves, eliminating the need for background subtraction or source localization. Its dual-scale architecture fuses long- and short-scale temporal evolution adaptively. Evaluated on 15 years of Fermi/GBM triggers, the optimal model achieves 97.23% accuracy when trained on complete energy spectra. A lightweight version using only three broad energy bands retains 95.07% accuracy, demonstrating that coarse spectral information fused with temporal context enables robust discrimination. The system significantly outperforms the GBM in-flight classifier on three months of independent test data. Feature visualization reveals well-separated class clusters, confirming physical interpretability. LUNCH combines high accuracy, low computational cost, and instrument-agnostic inputs, offering a practical solution for real-time in-flight processing that enables timely triggers for immediate multi-wavelength and multi-messenger follow-up observations in future time-domain missions.

LUNCH: A Lightweight Unified Deep-Learning Framework for General Transients Classification in High-Energy Time-Domain Astronomy

TL;DR

The Lightweight Unified Neural Classifier for High-energy Transients (LUNCH) is developed - an end-to-end deep-learning framework that performs general transient classification directly from raw multi-band light curves, eliminating the need for background subtraction or source localization.

Abstract

The increasing data volume of high-energy space monitors necessitates real-time, automated transient classification for multi-messenger follow-up. Conventional methods rely on empirical features like hardness ratios and reliable localization, which are not always precisely available during early detection. We developed the Lightweight Unified Neural Classifier for High-energy Transients (LUNCH) - an end-to-end deep-learning framework that performs general transient classification directly from raw multi-band light curves, eliminating the need for background subtraction or source localization. Its dual-scale architecture fuses long- and short-scale temporal evolution adaptively. Evaluated on 15 years of Fermi/GBM triggers, the optimal model achieves 97.23% accuracy when trained on complete energy spectra. A lightweight version using only three broad energy bands retains 95.07% accuracy, demonstrating that coarse spectral information fused with temporal context enables robust discrimination. The system significantly outperforms the GBM in-flight classifier on three months of independent test data. Feature visualization reveals well-separated class clusters, confirming physical interpretability. LUNCH combines high accuracy, low computational cost, and instrument-agnostic inputs, offering a practical solution for real-time in-flight processing that enables timely triggers for immediate multi-wavelength and multi-messenger follow-up observations in future time-domain missions.
Paper Structure (1 section, 1 figure)

This paper contains 1 section, 1 figure.

Table of Contents

  1. Introduction

Figures (1)

  • Figure 1: Representative samples of the five trigger classes with Grad-CAM feature visualizations. For each event, the top panel shows the normalized multi-channel (128 energy bins) count map, the middle panel shows the summed light curve across all energy channels, and the bottom panel displays the Grad-CAM heatmap, highlighting the spatio-temporal features (time-energy bins) that most influenced the model's classification.