Advancing weak lensing mass mapping with a mask-aware HEALPix transformer

Abstract

We present HEALFormer, a transformer-based neural network architecture for weak gravitational lensing mass mapping that reconstructs convergence maps from incomplete and noisy shear observations on the celestial sphere. The model operates directly on the Hierarchical Equal Area isoLatitude Pixelization and employs learnable mask tokens to handle arbitrary survey geometries without requiring preprocessing. Through a progressive training strategy, HEALFormer efficiently processes high-resolution maps up to Nside = 1024 and demonstrates excellent performance across diverse survey footprints including KiDS, DES, DECaLS, and Planck. The model generalizes robustly to cosmological parameters beyond its training set, producing nearly unbiased reconstructions with superior noise suppression compared to traditional Kaiser-Squires and Wiener filter methods. Remarkably, HEALFormer exceeds the theoretical phase recovery limits of linear reconstruction methods at small scales, achieving a fundamental breakthrough in weak lensing analysis. The combination of computational efficiency, reconstruction accuracy, and adaptability to varying survey configurations makes HEALFormer well-suited for current and next-generation cosmological surveys. Code is available at GitHub.

15 pages and 7 figures for main text. Accepted by PRD

References in corpus (31)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Array Programming with NumPy
• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• Weak Gravitational Lensing
• Overview of the DESI Legacy Imaging Surveys
• Planck 2018 results. I. Overview and the cosmological legacy of Planck
• KiDS-450: Cosmological parameter constraints from tomographic weak gravitational lensing
• KiDS-1000 Cosmology: Multi-probe weak gravitational lensing and spectroscopic galaxy clustering constraints
• A unified pseudo-$C_{\ell }$ framework
• Weak lensing for precision cosmology
• Dark matter maps reveal cosmic scaffolding
• Core Cosmology Library: Precision Cosmological Predictions for LSST
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• The Effective Number Density of Galaxies for Weak Lensing Measurements in the LSST Project
• Weak lensing analysis in three dimensions
• Dark Energy Survey Year 1 Results: Curved-Sky Weak Lensing Mass Map
• Dark Energy Survey Year 3 results: curved-sky weak lensing mass map reconstruction
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• Introduction to the Chinese Space Station Survey Telescope (CSST)
• GLIMPSE: Accurate 3D weak lensing reconstructions using sparsity
• Noise reduction for weak lensing mass mapping: An application of generative adversarial networks to Subaru Hyper Suprime-Cam first-year data
• Probabilistic Mass Mapping with Neural Score Estimation
• Euclid: Reconstruction of Weak Lensing mass maps for non-Gaussianity studies
• Precise weak lensing constraints from deep high-resolution $K_{\mathrm{s}}$ images: VLT/HAWK-I analysis of the super-massive galaxy cluster RCS2$J$232727.7$-$020437 at $z=0.70$
• Weak lensing mass reconstruction using sparsity and a Gaussian random field
• KaRMMa -- Kappa Reconstruction for Mass Mapping
• Wiener filtering and pure E/B decomposition of CMB maps with anisotropic correlated noise
• Dark Energy Survey Year 1 Results: Wide field mass maps via forward fitting in harmonic space
• Fast Sampling from Wiener Posteriors for Image Data with Dataflow Engines
• Accurate Kappa Reconstruction Algorithm for masked shear catalog (AKRA)
• AKRA 2.0: Accurate Kappa Reconstruction Algorithm for masked shear catalog