Learning Astrophysical Uncertainties in Dark Matter Direct Detection with Simulation-Based Inference
Abstract
We present a proof-of-concept study of neural ratio estimation (NRE) - a simulation-based inference algorithm - applied to WIMP direct detection using the XENONnT experiment as an example. A binary classifier is trained on simulated parameter-observation pairs to approximate the likelihood ratio for the WIMP mass mχ and spin-independent proton coupling cp, using realistic scintillation and ionization signals produced by the fuse detector simulation. We demonstrate that astrophysical uncertainties from halo model variations are marginalized over implicitly and at no additional inference cost by including multiple halo models in the training data. Using extreme ±5σ Standard Halo Model variations, we show that training on a combined dataset recovers well-calibrated posteriors even under severe misspecification, while more realistic halo models produce nearly indistinguishable results. The signal-plus-background classifier yields an exclusion limit that is both qualitatively and (after accounting for differences between frequentist and Bayesian approaches) quantitatively consistent with the XENONnT expected sensitivity. These results establish NRE as a scalable complement to the profile likelihood ratio approach, with particular advantages as experiments probe deeper into the neutrino fog.
Related
- Confronting the Higgsino Interpretation of the LZ Event with Astrophysical Uncertainties and the Solar Capture Constraints
- Transformers with Physics-Informed Encodings and Simulation-Based Inference for Robust Detection of Eccentric Binary Black Holes in Pulsar Timing Array Data
- SCALE: Simulation-Calibrated Amortized Learning for Energy Materials (A hybrid architecture connecting deterministic modeling, real-world data, and transformer-scale inference for accelerated energy-materials discovery)
- Analytic Marginalization Over Calibration Uncertainties in Gravitational Wave Inference and Application to Black Hole Ringdown
- Do Quantum Measurement Advantages Survive to Astrophysical Inference? Seven Benchmarks in Optical Interferometry and Imaging
BibTeX
@misc{kahlhoefer2026learning,
title = {{Learning Astrophysical Uncertainties in Dark Matter Direct Detection with Simulation-Based Inference}},
author = {Felix Kahlhoefer and Niklas Reus},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.06159},
eprint = {2610.06159},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.06159},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learning Astrophysical Uncertainties in Dark Matter Direct Detection with Simulation-Based Inference
AU - Felix Kahlhoefer
AU - Niklas Reus
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.06159
UR - https://arxiv.org/abs/2610.06159
AB - We present a proof-of-concept study of neural ratio estimation (NRE) - a simulation-based inference algorithm - applied to WIMP direct detection using the XENONnT experiment as an example. A binary classifier is trained on simulated parameter-observation pairs to approximate the likelihood ratio for the WIMP mass m_χ and spin-independent proton coupling c_p, using realistic scintillation and ionization signals produced by the fuse detector simulation. We demonstrate that astrophysical uncertainties from halo model variations are marginalized over implicitly and at no additional inference cost by including multiple halo models in the training data. Using extreme ±5σ Standard Halo Model variations, we show that training on a combined dataset recovers well-calibrated posteriors even under severe misspecification, while more realistic halo models produce nearly indistinguishable results. The signal-plus-background classifier yields an exclusion limit that is both qualitatively and (after accounting for differences between frequentist and Bayesian approaches) quantitatively consistent with the XENONnT expected sensitivity. These results establish NRE as a scalable complement to the profile likelihood ratio approach, with particular advantages as experiments probe deeper into the neutrino fog.
ER -