BGRem: A background noise remover for astronomical images based on a diffusion model

TL;DR

BGRem addresses background noise in astronomical imaging by introducing a diffusion-denoising framework with an attention U‑Net backbone trained on optical MeerLICHT simulations and γ-ray-like Fermi-LAT data. It demonstrates improved source-detection performance when used as a pre-processing step with SExtractor and shows zero-shot generalization across optical instruments and cross-wavelength γ-ray data, indicating potential as a general background-removal tool for multi-wavelength surveys. The method achieves order-of-magnitude improvements in detection under certain conditions and provides robust flux reconstruction while maintaining non-negativity, highlighting practical impact for catalog construction in large surveys. Overall, BGRem offers a transferable, data-driven pre-processing solution to enhance astronomical source catalogs without detector-level changes.

Abstract

Context: Astronomical imaging aims to maximize signal capture while minimizing noise. Enhancing the signal-to-noise ratio directly on detectors is difficult and expensive, leading to extensive research in advanced post-processing techniques. Aims: Removing background noise from images is a valuable pre-processing step catalog-building tasks. We introduce BGRem, a machine learning (ML) based tool to remove background noise from astronomical images. Methods: BGRem uses a diffusion-based model with an attention U-Net as backbone, trained on simulated images for optical and gamma (γ)-ray data from the MeerLICHT and Fermi-LAT telescopes. In a supervised manner, BGRem learns to denoise astronomical images over several diffusion steps. Results: BGRem performance was compared with a widely used tool for cataloging astronomical sources, SourceExtractor (SExtractor). It was shown that the amount of true positive sources using SExtractor increased by about 7% for MeerLICHT data when BGRem was used as a pre-processing step. We also show the generalizability of BGRem by testing it with optical images from different telescopes and also on simulated γ-ray data representative of the Fermi-LAT telescope. We show that in both cases, BGRem improves the source detection efficiency. Conclusions: BGRem can improve the accuracy in source detection of traditional pixel-based methods by removing complex background noise. Using zero-shot approach, BGRem can generalize well to a wide range of optical images. The successful application of BGRem to simulated γ-ray images, alongside optical data, demonstrates its adaptability to distinct noise characteristics and observational domains. This cross-wavelength performance highlights its potential as a general-purpose background removal framework for multi-wavelength astronomical surveys.

Figures (17)

• Figure 1: Example of the working of a diffusion model with five diffusion steps. The shown input is already pre-processed, while between step 4 and output there is a model prediction and post-processing, excluding denormalisation.
• Figure 2: The fraction of noise and ground truth per diffusion step for the standard diffusion model (left) and the modified diffusion model during denoising for seven diffusion steps and noise levels equal to the image for BGRem (right). On the y-axis is the fraction of the total image flux, and on the x-axis is the diffusion step.
• Figure 3: Schematic of the diffusion model used in BGRem for 3 diffusion steps. The forward noise addition is only used during training. When making predictions, the model goes from right to left, iteratively removing the noise.
• Figure 4: Schematic of the backbone architecture used in BGRem, modified from the original attention U-Net oktay2018attention.
• Figure 5: MeerLICHT image (left) and the image with the background noise removed with BGRem (right).