JESSNet: Joint dEconvolution and Sparse Separation Network for HI 21 cm foreground cleaning
Abstract
Foreground cleaning is a major challenge for H\,{\sc i} 21 cm intensity mapping, particularly in the presence of a chromatic instrumental beam that couples angular foreground structure into the frequency direction and under incomplete sky coverage. We introduce JESSNet, a beam-aware, mask-compatible foreground-cleaning framework for single-dish intensity mapping. Building on SDecGMCA, JESSNet introduces three main extensions: a multiscale angular decomposition with scale-dependent mixing matrices and channel selection, a learned spherical-wavelet ''learnlet'' sparse regularization operator, and a mask-constrained reconstruction applicable to Galactic masks and survey footprints. We test JESSNet on simulated SKA-MID-like observations over 900−1300 MHz (z≃0.09−0.58), including H\,{\sc i} emission, Galactic and extragalactic foregrounds, thermal noise, and an oscillating MeerKAT-inspired chromatic beam. The multiscale reconstruction accurately recovers the angular and frequency power spectra of the input H\,{\sc i} signal, improves the recovery at low and intermediate angular scales relative to a single-scale implementation, and reduces residual beam-induced spectral features. JESSNet also remains effective for a synthetic survey footprint, preserving the H\,{\sc i} power spectra under incomplete sky coverage. The code and analysis pipeline are publicly released to facilitate reproducibility and future applications to simulated and observational data.
Related
- Foreground Characterization and Mitigation in the Observations of the CD/EoR with the SKA
- The Canadian Galactic Emission Mapper (CGEM): A Cosmic Microwave Foreground Experiment
- Intermittency in the Multiphase ISM --- II. Non-Gaussian Dust Polarization and Foreground Variance
- Foreground Groups and Host-Galaxy Geometry in the Dispersion-Measure Scatter of Fast Radio Bursts
- PIFFLE: Characterizing the Foreground Contributions from 4 Decades in Halo Mass to the FRB20230907D Dispersion Measure
BibTeX
@misc{gkogkou2026jessnet,
title = {{JESSNet: Joint dEconvolution and Sparse Separation Network for HI 21 cm foreground cleaning}},
author = {Athanasia Gkogkou and Victor Bonjean and Jean-Luc Starck and Pauline Gorbatchev and Marta Spinelli and Panagiotis Tsakalides},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.06199},
eprint = {2610.06199},
archivePrefix = {arXiv},
url = {https://hal.science/hal-05842248v1},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - JESSNet: Joint dEconvolution and Sparse Separation Network for HI 21 cm foreground cleaning
AU - Athanasia Gkogkou
AU - Victor Bonjean
AU - Jean-Luc Starck
AU - Pauline Gorbatchev
AU - Marta Spinelli
AU - Panagiotis Tsakalides
PY - 2026
DA - 2026/10/05
PB - HAL
DO - 10.48550/arxiv.2610.06199
UR - https://hal.science/hal-05842248v1
AB - Foreground cleaning is a major challenge for H\,{\sc i} 21 cm intensity mapping, particularly in the presence of a chromatic instrumental beam that couples angular foreground structure into the frequency direction and under incomplete sky coverage. We introduce JESSNet, a beam-aware, mask-compatible foreground-cleaning framework for single-dish intensity mapping. Building on SDecGMCA, JESSNet introduces three main extensions: a multiscale angular decomposition with scale-dependent mixing matrices and channel selection, a learned spherical-wavelet ''learnlet'' sparse regularization operator, and a mask-constrained reconstruction applicable to Galactic masks and survey footprints. We test JESSNet on simulated SKA-MID-like observations over 900−1300 MHz (z≃0.09−0.58), including H\,{\sc i} emission, Galactic and extragalactic foregrounds, thermal noise, and an oscillating MeerKAT-inspired chromatic beam. The multiscale reconstruction accurately recovers the angular and frequency power spectra of the input H\,{\sc i} signal, improves the recovery at low and intermediate angular scales relative to a single-scale implementation, and reduces residual beam-induced spectral features. JESSNet also remains effective for a synthetic survey footprint, preserving the H\,{\sc i} power spectra under incomplete sky coverage. The code and analysis pipeline are publicly released to facilitate reproducibility and future applications to simulated and observational data.
ER -