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

TL;DR

HEALFormer is a transformer-based neural network that improves weak lensing mass mapping by handling incomplete data, noise, and complex survey geometries, surpassing traditional methods and approaching fundamental limits.

Contribution

The paper introduces HEALFormer, a novel mask-aware transformer architecture that enhances convergence map reconstruction from noisy, incomplete shear data on the celestial sphere, with robust generalization across surveys.

Findings

Outperforms traditional Kaiser-Squires and Wiener filter methods.

Achieves near-unbiased reconstructions with superior noise suppression.

Exceeds theoretical phase recovery limits at small scales.

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.