Differentiable probabilistic programming for strong gravitational lensing

TL;DR

This paper introduces a new analysis pipeline for strong gravitational lensing that combines deep learning, physical models, and sampling techniques to improve the detection and characterization of Dark Matter subhaloes.

Contribution

It presents a novel pipeline integrating neural networks with physical models and sampling methods for analyzing gravitational lensing data.

Findings

Pipeline accurately reconstructs main lensing parameters

Combines deep learning with physical modeling and sampling

Demonstrates effectiveness on simulated data

Abstract

The difficult task of observing Dark Matter subhaloes is of paramount importance since it would constrain Dark Matter particle properties (cold or warm relic) and confirm once again the longstanding $\Lambda$CDM model. In the near future the new generation of ground and space surveys will observe thousands of strong gravitational lensing systems providing a unique probe of Dark Matter substructures. Here, we describe a new strong lensing analysis pipeline that combines deep Convolutional Neural Networks with physical models and exploits traditional sampling techniques such as Hamiltonian Monte Carlo. Using simulated strong gravitational lensing systems, we discuss first results and characterize the accuracy of the reconstruction of the main lensing parameters.