Deep Learning Unresolved Lensed Lightcurves
arXiv:2202.11903 · doi:10.1093/mnras/stac1726
Abstract
Gravitationally lensed sources may have unresolved or blended multiple images, and for time varying sources the lightcurves from individual images can overlap. We use convolutional neural nets to both classify the lightcurves as due to unlensed, double, or quad lensed sources and fit for the time delays. Focusing on lensed supernova systems with time delays days, we achieve 100\% precision and recall in identifying the number of images and then estimating the time delays to day, with a speedup relative to our previous Monte Carlo technique. This also succeeds for flux noise levels . For days we obtain 94--98\% accuracy, depending on image configuration. We also explore using partial lightcurves where observations only start near maximum light, without the rise time data, and quantify the success.
10 pages, 7 figures; v2: minor clarifications
References in corpus (11)
- Projected Cosmological Constraints from Strongly Lensed Supernovae with the Roman Space Telescope
- ParSNIP: Generative Models of Transient Light Curves with Physics-Enabled Deep Learning
- The Impact of Observing Strategy on Cosmological Constraints with LSST
- HOLISMOKES -- VII. Time-delay measurement of strongly lensed Type Ia supernovae using machine learning
- Be It Unresolved: Measuring Time Delays from Lensed Supernovae
- Measuring time delays: II. Using observations of the unresolved flux and astrometry
- Discovering Strongly-lensed QSOs From Unresolved Light Curves
- Identifying lensed quasars and measuring their time-delays from unresolved light curves
- Measuring time delays: I. Using a flux time series that is a linear combination of time-shifted light curves
- Out of One, Many: Distinguishing Time Delays from Lensed Supernovae
- STag: Supernova Tagging and Classification