FLUMEN: Neural Emulator of an Advanced Stochastic Weak Lensing Model
Abstract
Weak gravitational lensing by intervening structure magnifies distant sources and induces scatter in their luminosity distances. We develop an improved stochastic model for the distribution of weak lensing magnifications, d P/dμ, that resolves individual lenses down to 107 M⊙ and, besides field halos and filaments, includes subhalos and large-scale clustering of the lens population. Both extensions broaden the distribution, and the resulting scatter in the luminosity distances agrees with the halo-model prediction from the nonlinear matter power spectrum and exceeds that obtained from N-body ray tracing, which we attribute to the finite mass resolution and box size of the simulations. Building on this model, we develop \texttt{FLUMEN}, a conditional normalizing-flow emulator that predicts d P/dμ as a function of the source redshift up to zs=12 and six cosmological parameters {h,ΩM,ΩB,σ8,ns,zeq}. The emulator enforces the empty-beam cutoff and the fold-caustic power-law tail analytically, and reproduces the Monte Carlo distributions on held-out cosmologies with a median Kullback--Leibler divergence of $0.0048$ at negligible cost. Our results provide a fast and flexible framework for incorporating the full magnification distribution into cosmological analyses of standard sirens, supernovae, and other point sources.
Related
- A Hybrid Neural Network Emulator for M1 Neutrino Reaction Rates in Binary Neutron Star Merger Simulations
- An asteroseismic age estimate for the Pleiades using a neural-network emulator of rotating δ Scuti pulsation models
- Neural Posterior Estimation for Tomographic Weak Lensing Mass Mapping
- 21cmEMUv3: A hybrid diffusion and long short-term memory emulator of 21cmFAST summary observables
- Stochastic analysis of finite-temperature effects on cosmological parameters by artificial neural networks
BibTeX
@misc{baltabay2026flumen,
title = {{FLUMEN: Neural Emulator of an Advanced Stochastic Weak Lensing Model}},
author = {Galymzhan Baltabay and Ville Vaskonen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.21806},
eprint = {2609.21806},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.21806},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - FLUMEN: Neural Emulator of an Advanced Stochastic Weak Lensing Model
AU - Galymzhan Baltabay
AU - Ville Vaskonen
PY - 2026
DA - 2026/09/18
PB - arXiv
DO - 10.48550/arxiv.2609.21806
UR - https://arxiv.org/abs/2609.21806
AB - Weak gravitational lensing by intervening structure magnifies distant sources and induces scatter in their luminosity distances. We develop an improved stochastic model for the distribution of weak lensing magnifications, d P/dμ, that resolves individual lenses down to 10^7 M_⊙ and, besides field halos and filaments, includes subhalos and large-scale clustering of the lens population. Both extensions broaden the distribution, and the resulting scatter in the luminosity distances agrees with the halo-model prediction from the nonlinear matter power spectrum and exceeds that obtained from N-body ray tracing, which we attribute to the finite mass resolution and box size of the simulations. Building on this model, we develop \texttt{FLUMEN}, a conditional normalizing-flow emulator that predicts d P/dμ as a function of the source redshift up to z_s=12 and six cosmological parameters {h,Ω_M,Ω_B,σ_8,n_s,z_eq}. The emulator enforces the empty-beam cutoff and the fold-caustic power-law tail analytically, and reproduces the Monte Carlo distributions on held-out cosmologies with a median Kullback--Leibler divergence of $0.0048$ at negligible cost. Our results provide a fast and flexible framework for incorporating the full magnification distribution into cosmological analyses of standard sirens, supernovae, and other point sources.
ER -