Autoencoder Reconstruction of Cosmological Microlensing Magnification Maps
Enhanced modeling of microlensing variations in light curves of strongly lensed quasars improves measurements of cosmological time delays, the Hubble Constant, and quasar structure. Traditional methods for modeling extragalactic microlensing rely on computationally expensive magnification map genera...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | The Astrophysical Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/1538-4357/ada5ff |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832545242755104768 |
|---|---|
| author | Somayeh Khakpash Federica B. Bianco Georgios Vernardos Gregory Dobler Charles Keeton |
| author_facet | Somayeh Khakpash Federica B. Bianco Georgios Vernardos Gregory Dobler Charles Keeton |
| author_sort | Somayeh Khakpash |
| collection | DOAJ |
| description | Enhanced modeling of microlensing variations in light curves of strongly lensed quasars improves measurements of cosmological time delays, the Hubble Constant, and quasar structure. Traditional methods for modeling extragalactic microlensing rely on computationally expensive magnification map generation. With large data sets expected from wide-field surveys like the Vera C. Rubin Legacy Survey of Space and Time, including thousands of lensed quasars and hundreds of multiply imaged supernovae, faster approaches become essential. We introduce a deep-learning model that is trained on pre-computed magnification maps covering the parameter space on a grid of κ , γ , and s . Our autoencoder creates a low-dimensional latent space representation of these maps, enabling efficient map generation. Quantifying the performance of magnification map generation from a low dimensional space is an essential step in the roadmap to develop neural network-based models that can replace traditional feed-forward simulation at much lower computational costs. We develop metrics to study various aspects of the autoencoder generated maps and show that the reconstruction is reliable. Even though we observe a mild loss of resolution in the generated maps, we find this effect to be smaller than the smoothing effect of convolving the original map with a source of a plausible size for its accretion disk in the red end of the optical spectrum and larger wavelengths and particularly one suitable for studying the broad-line region of quasars. Used to generate large samples of on-demand magnification maps, our model can enable fast modeling of microlensing variability in lensed quasars and supernovae. |
| format | Article |
| id | doaj-art-801d12c764464fad80500a79ceb76076 |
| institution | Kabale University |
| issn | 1538-4357 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astrophysical Journal |
| spelling | doaj-art-801d12c764464fad80500a79ceb760762025-02-03T07:28:53ZengIOP PublishingThe Astrophysical Journal1538-43572025-01-0198013510.3847/1538-4357/ada5ffAutoencoder Reconstruction of Cosmological Microlensing Magnification MapsSomayeh Khakpash0https://orcid.org/0000-0002-1910-7065Federica B. Bianco1https://orcid.org/0000-0003-1953-8727Georgios Vernardos2https://orcid.org/0000-0001-8554-7248Gregory Dobler3https://orcid.org/0000-0002-9276-3261Charles Keeton4https://orcid.org/0000-0001-6812-2467Rutgers University–New Brunswick , Department of Physics & Astronomy, 136 Frelinghuysen Road, Piscataway, NJ 08854, USA; LSST-DA Catalyst FellowUniversity of Delaware Department of Physics and Astronomy 217 Sharp Lab Newark , DE 19716, USA; University of Delaware Joseph R. Biden , Jr. School of Public Policy and Administration, 184 Academy Street, Newark, DE 19716, USA; University of Delaware Data Science Institute , USA; Vera C. Rubin Observatory , Tucson, AZ 85719, USADepartment of Physics and Astronomy, Lehman College of the City University of New York , Bronx, NY 10468, USA; Department of Astrophysics , American Museum of Natural History, Central Park West and 79th Street, NY 10024, USAUniversity of Delaware Department of Physics and Astronomy 217 Sharp Lab Newark , DE 19716, USA; University of Delaware Joseph R. Biden , Jr. School of Public Policy and Administration, 184 Academy Street, Newark, DE 19716, USA; University of Delaware Data Science Institute , USARutgers University–New Brunswick , Department of Physics & Astronomy, 136 Frelinghuysen Road, Piscataway, NJ 08854, USAEnhanced modeling of microlensing variations in light curves of strongly lensed quasars improves measurements of cosmological time delays, the Hubble Constant, and quasar structure. Traditional methods for modeling extragalactic microlensing rely on computationally expensive magnification map generation. With large data sets expected from wide-field surveys like the Vera C. Rubin Legacy Survey of Space and Time, including thousands of lensed quasars and hundreds of multiply imaged supernovae, faster approaches become essential. We introduce a deep-learning model that is trained on pre-computed magnification maps covering the parameter space on a grid of κ , γ , and s . Our autoencoder creates a low-dimensional latent space representation of these maps, enabling efficient map generation. Quantifying the performance of magnification map generation from a low dimensional space is an essential step in the roadmap to develop neural network-based models that can replace traditional feed-forward simulation at much lower computational costs. We develop metrics to study various aspects of the autoencoder generated maps and show that the reconstruction is reliable. Even though we observe a mild loss of resolution in the generated maps, we find this effect to be smaller than the smoothing effect of convolving the original map with a source of a plausible size for its accretion disk in the red end of the optical spectrum and larger wavelengths and particularly one suitable for studying the broad-line region of quasars. Used to generate large samples of on-demand magnification maps, our model can enable fast modeling of microlensing variability in lensed quasars and supernovae.https://doi.org/10.3847/1538-4357/ada5ffGravitational microlensingQuasar microlensingConvolutional neural networksNeural networks |
| spellingShingle | Somayeh Khakpash Federica B. Bianco Georgios Vernardos Gregory Dobler Charles Keeton Autoencoder Reconstruction of Cosmological Microlensing Magnification Maps The Astrophysical Journal Gravitational microlensing Quasar microlensing Convolutional neural networks Neural networks |
| title | Autoencoder Reconstruction of Cosmological Microlensing Magnification Maps |
| title_full | Autoencoder Reconstruction of Cosmological Microlensing Magnification Maps |
| title_fullStr | Autoencoder Reconstruction of Cosmological Microlensing Magnification Maps |
| title_full_unstemmed | Autoencoder Reconstruction of Cosmological Microlensing Magnification Maps |
| title_short | Autoencoder Reconstruction of Cosmological Microlensing Magnification Maps |
| title_sort | autoencoder reconstruction of cosmological microlensing magnification maps |
| topic | Gravitational microlensing Quasar microlensing Convolutional neural networks Neural networks |
| url | https://doi.org/10.3847/1538-4357/ada5ff |
| work_keys_str_mv | AT somayehkhakpash autoencoderreconstructionofcosmologicalmicrolensingmagnificationmaps AT federicabbianco autoencoderreconstructionofcosmologicalmicrolensingmagnificationmaps AT georgiosvernardos autoencoderreconstructionofcosmologicalmicrolensingmagnificationmaps AT gregorydobler autoencoderreconstructionofcosmologicalmicrolensingmagnificationmaps AT charleskeeton autoencoderreconstructionofcosmologicalmicrolensingmagnificationmaps |