Strong Gravitational Lensing Parameter Estimation with Vision Transformer

10/09/2022
by   Kuan Wei Huang, et al.
10

Quantifying the parameters and corresponding uncertainties of hundreds of strongly lensed quasar systems holds the key to resolving one of the most important scientific questions: the Hubble constant (H_0) tension. The commonly used Markov chain Monte Carlo (MCMC) method has been too time-consuming to achieve this goal, yet recent work has shown that convolution neural networks (CNNs) can be an alternative with seven orders of magnitude improvement in speed. With 31,200 simulated strongly lensed quasar images, we explore the usage of Vision Transformer (ViT) for simulated strong gravitational lensing for the first time. We show that ViT could reach competitive results compared with CNNs, and is specifically good at some lensing parameters, including the most important mass-related parameters such as the center of lens θ_1 and θ_2, the ellipticities e_1 and e_2, and the radial power-law slope γ'. With this promising preliminary result, we believe the ViT (or attention-based) network architecture can be an important tool for strong lensing science for the next generation of surveys. The open source of our code and data is in <https://github.com/kuanweih/strong_lensing_vit_resnet>.

READ FULL TEXT
research
10/18/2021

Finding Strong Gravitational Lenses Through Self-Attention

The upcoming large scale surveys are expected to find approximately 10^5...
research
10/08/2020

MatDRAM: A pure-MATLAB Delayed-Rejection Adaptive Metropolis-Hastings Markov Chain Monte Carlo Sampler

Markov Chain Monte Carlo (MCMC) algorithms are widely used for stochasti...
research
01/31/2022

Exoplanet Characterization using Conditional Invertible Neural Networks

The characterization of an exoplanet's interior is an inverse problem, w...
research
05/12/2023

T-former: An Efficient Transformer for Image Inpainting

Benefiting from powerful convolutional neural networks (CNNs), learning-...
research
11/11/2022

Detection of Strongly Lensed Arcs in Galaxy Clusters with Transformers

Strong lensing in galaxy clusters probes properties of dense cores of da...
research
08/27/2020

Improvement of a dedicated model for open domain persona-aware dialogue generation

This paper analyzes some speed and performance improvement methods of Tr...

Please sign up or login with your details

Forgot password? Click here to reset