ComptonUNet: A Deep Learning Model for GRB Localization with Compton Cameras under Noisy and Low-Statistic Conditions

TL;DR

ComptonUNet is a novel deep learning framework that enhances gamma-ray burst localization accuracy under noisy, low-photon conditions by combining raw data processing with image reconstruction.

Contribution

It introduces a hybrid deep learning model that effectively balances statistical robustness and noise suppression for GRB localization in challenging conditions.

Findings

Outperforms existing methods in localization accuracy.

Effective under low photon statistics and high background noise.

Demonstrated through realistic simulations.

Abstract

Gamma-ray bursts (GRBs) are among the most energetic transient phenomena in the universe and serve as powerful probes for high-energy astrophysical processes. In particular, faint GRBs originating from a distant universe may provide unique insights into the early stages of star formation. However, detecting and localizing such weak sources remains challenging owing to low photon statistics and substantial background noise. Although recent machine learning models address individual aspects of these challenges, they often struggle to balance the trade-off between statistical robustness and noise suppression. Consequently, we propose ComptonUNet, a hybrid deep learning framework that jointly processes raw data and reconstructs images for robust GRB localization. ComptonUNet was designed to operate effectively under conditions of limited photon statistics and strong background contamination by combining the statistical efficiency of direct reconstruction models with the denoising capabilities of image-based architectures. We perform realistic simulations of GRB-like events embedded in background environments representative of low-Earth orbit missions to evaluate the performance of ComptonUNet. Our results demonstrate that ComptonUNet significantly outperforms existing approaches, achieving improved localization accuracy across a wide range of low-statistic and high-background scenarios.