Advancing weak lensing mass mapping with a mask-aware HEALPix transformer
Paper • 2603.25471 • Published
HealFormer nside1024 DECaLS projection model
Inference-ready HealFormer v0.2.0 checkpoint for NESTED HEALPix maps at
Nside=1024. It uses learned positional projection, a fixed DECaLS mask, and
no map rotation. Interpolation checkpoints are not part of this release.
The public repository deliberately uses standard short filenames:
config.json and model.safetensors.
100-sample diagnostics
On 100 independent fixed-DECaLS skies:
- Power-ratio RMSE:
0.0884 ± 0.0179 - Mean harmonic cross correlation:
0.9622 ± 0.0010
The uncertainty is one sample standard deviation, not standard error.
Usage
from healformers import MassMappingPipeline
pipeline = MassMappingPipeline.from_pretrained(
"lalala404/healformer-nside1024-decals"
)
kappa = pipeline(gamma1, gamma2, mask_npix)
Inputs are physical gamma1, gamma2, and integer mask_npix arrays in
NESTED ordering. Mask values are 0 visible, 1 reconstruction edge, and 2
unseen. The returned convergence map is in physical units.
Integrity and limitations
release-manifest.json records byte sizes and SHA-256 checksums. This model is
for simulated weak-lensing mass mapping at the stated resolution and should be
validated before scientific use on a new survey pipeline.
Citation
Yihe Wang and Yu Yu, Advancing weak lensing mass mapping with a mask-aware HEALPix transformer, arXiv:2603.25471.
- Downloads last month
- 50