Application of Physics-Informed Neural Networks in Removing Telescope Beam Effects
arXiv:2409.05718 · doi:10.3847/1538-4357/adf223
Abstract
This study introduces {\tt{PI-AstroDeconv}}, a physics-informed semi-supervised learning method specifically designed for removing beam effects in astronomical telescope observation systems. The method utilizes an encoder-decoder network architecture and combines the telescope's point spread function or beam as prior information, while integrating fast Fourier transform accelerated convolution techniques into the deep learning network. This enables effective removal of beam effects from astronomical observation images. {\tt{PI-AstroDeconv}} can handle multiple PSFs or beams, tolerate imprecise measurements to some extent, and significantly improve the efficiency and accuracy of image deconvolution. Therefore, this architecture is particularly suitable for astronomical data processing that does not rely on annotated data. To validate the reliability of the architecture, we used the SKA Science Data Challenge 3a datasets and compared it with the deconvolution method at the 21-cm power spectrum level. The results demonstrate that our algorithm not only restores details and reduces blurriness in celestial images at the pixel level but also more accurately recovers the true neutral hydrogen power spectrum at the power spectrum level.
Accepted for publication in the Astrophysical Journal
References in corpus (45)
- A Flat Universe from High-Resolution Maps of the Cosmic Microwave Background Radiation
- The Murchison Widefield Array: the Square Kilometre Array Precursor at low radio frequencies
- 21-cm cosmology
- WSClean: an implementation of a fast, generic wide-field imager for radio astronomy
- The Five-Hundred-Meter Aperture Spherical Radio Telescope (FAST) Project
- The large-scale structure of the Universe
- 21cmFAST: A Fast, Semi-Numerical Simulation of the High-Redshift 21-cm Signal
- Multi-Scale CLEAN deconvolution of radio synthesis images
- The Expanded Very Large Array -- a New Telescope for New Science
- A model of diffuse Galactic Radio Emission from 10 MHz to 100 GHz
- Science with ASKAP - the Australian Square Kilometre Array Pathfinder
- The CHIME Fast Radio Burst Project: System Overview
- Stellar Radio Astronomy. Probing Stellar Atmospheres from Protostars to Giants
- Late-time cosmology with 21cm intensity mapping experiments
- An optimized algorithm for multi-scale wideband deconvolution of radio astronomical images
- Considerations for a Multi-beam Multi-purpose Survey with FAST
- Cosmology with Phase 1 of the Square Kilometre Array; Red Book 2018: Technical specifications and performance forecasts
- GLEAM: The GaLactic and Extragalactic All-sky MWA survey
- Foreground simulations for the LOFAR - Epoch of Reionization Experiment
- Inferring the astrophysics of reionization and cosmic dawn from galaxy luminosity functions and the 21-cm signal
- Science With The Australian Square Kilometre Array Pathfinder
- Canadian Hydrogen Intensity Mapping Experiment (CHIME) Pathfinder
- An Improved Model of Diffuse Galactic Radio Emission from 10 MHz to 5 THz
- Revival of the magnetar PSR J1622-4950: observations with MeerKAT, Parkes, XMM-Newton, Swift, Chandra, and NuSTAR
- Blind foreground subtraction for intensity mapping experiments
- Probing the First Stars and Black Holes in the Early Universe with the Dark Ages Radio Explorer (DARE)
- Observing Neutral Hydrogen Above Redshift 6: The "Global" Perspective
- 21cmFAST v3: A Python-integrated C code forgenerating 3D realizations of the cosmic 21cm signal
- The Impact of the First Galaxies on Cosmic Dawn and Reionization
- LOFAR, a new low frequency radio telescope
- Unveiling the nature of dark matter with high redshift 21 cm line experiments
- SKAO HI Intensity Mapping: Blind Foreground Subtraction Challenge
- Multi-Scale CLEAN: A comparison of its performance against classical CLEAN in galaxies using THINGS
- The nature of dark matter from the global high redshift HI 21 cm signal
- Image Domain Gridding: a fast method for convolutional resampling of visibilities
- deep21: a Deep Learning Method for 21cm Foreground Removal
- Deep Learning-based Imaging in Radio Interferometry
- Eliminating Primary Beam Effect in Foreground Subtraction of Neutral Hydrogen Intensity Mapping Survey with Deep Learning
- Deep learning enabled superfast and accurate M^2 evaluation for fiber beams
- Analysing the impact of far-out side-lobes on the imaging performance of the SKA-LOW telescope
- Early Observations of the MHONGOOSE Galaxies: Getting Ready for MeerKAT
- Eliminating polarization leakage effect for neutral hydrogen intensity mapping with deep learning
- The optimal redshift for detecting ionized bubbles in HI 21-cm maps
- SKA shakes hands with Summit
- Deep learning-based deconvolution for interferometric radio transient reconstruction