Inferring dark matter substructure with astrometric lensing beyond the power spectrum

TL;DR

This paper introduces a neural network-based method for detecting dark matter substructure through astrometric lensing, outperforming traditional correlation-based techniques in sensitivity and noise robustness.

Contribution

The authors develop a novel neural likelihood-ratio estimation approach that enhances detection sensitivity of dark matter signatures in astrometric data beyond existing methods.

Findings

Method shows improved sensitivity to dark matter lensing signals.

Approach is robust to complex and unmodeled noise features.

Demonstrates viability of machine learning for dark matter characterization.

Abstract

Astrometry -- the precise measurement of positions and motions of celestial objects -- has emerged as a promising avenue for characterizing the dark matter population in our Galaxy. By leveraging recent advances in simulation-based inference and neural network architectures, we introduce a novel method to search for global dark matter-induced gravitational lensing signatures in astrometric datasets. Our method based on neural likelihood-ratio estimation shows significantly enhanced sensitivity to a cold dark matter population and more favorable scaling with measurement noise compared to existing approaches based on two-point correlation statistics. We demonstrate the real-world viability of our method by showing it to be robust to non-trivial modeled as well as unmodeled noise features expected in astrometric measurements. This establishes machine learning as a powerful tool for characterizing dark matter using astrometric data.