A fully connected network trained on millions of simulated quads predicts SIE lens mass and ellipticity from four image positions, cutting optimisation time for real and simulated quadruply lensed quasars to minutes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.GA 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Speeding up Gravitational Lens Mass Models with Machine Learning: Applications in X-ray Astronomy
A fully connected network trained on millions of simulated quads predicts SIE lens mass and ellipticity from four image positions, cutting optimisation time for real and simulated quadruply lensed quasars to minutes.