| 1. |
- Kodi Ramanah, Doogesh, et al.
(författare)
-
AI-driven spatio-temporal engine for finding gravitationally lensed type Ia supernovae
- 2022
-
Ingår i: Monthly notices of the Royal Astronomical Society. - : Oxford University Press (OUP). - 0035-8711 .- 1365-2966. ; 512:4, s. 5404-5417
-
Tidskriftsartikel (refereegranskat)abstract
- We present a spatio-temporal AI framework that concurrently exploits both the spatial and time-variable features of gravitationally lensed supernovae in optical images to ultimately aid in future discoveries of such exotic transients in wide-field surveys. Our spatio-temporal engine is designed using recurrent convolutional layers, while drawing from recent advances in variational inference to quantify approximate Bayesian uncertainties via a confidence score. Using simulated Young Supernova Experiment (YSE) images of lensed and non-lensed supernovae as a showcase, we find that the use of time-series images adds relevant information from time variability of spatial light distribution of partially blended images of lensed supernova, yielding a substantial gain of around 20 per cent in classification accuracy over single-epoch observations. Preliminary application of our network to mock observations from the Legacy Survey of Space and Time (LSST) results in detections with accuracy reaching around 99 per cent. Our innovative deep learning machinery is versatile and can be employed to search for any class of sources that exhibit variability both in flux and spatial distribution of light.
|
|
| 2. |
- Kostić, Andrija, et al.
(författare)
-
Optimal machine-driven acquisition of future cosmological data
- 2022
-
Ingår i: Astronomy and Astrophysics. - : EDP Sciences. - 0004-6361 .- 1432-0746. ; 657
-
Tidskriftsartikel (refereegranskat)abstract
- We present a set of maps classifying regions of the sky according to their information gain potential as quantified by Fisher information. These maps can guide the optimal retrieval of relevant physical information with targeted cosmological searches. Specifically, we calculated the response of observed cosmic structures to perturbative changes in the cosmological model and we charted their respective contributions to Fisher information. Our physical forward-modeling machinery transcends the limitations of contemporary analyses based on statistical summaries to yield detailed characterizations of individual 3D structures. We demonstrate this advantage using galaxy counts data and we showcase the potential of our approach by studying the information gain of the Coma cluster. We find that regions in the vicinity of the filaments and cluster core, where mass accretion ensues from gravitational infall, are the most informative with regard to our physical model of structure formation in the Universe. Hence, collecting data in those regions would be most optimal for testing our model predictions. The results presented in this work are the first of their kind to elucidate the inhomogeneous distribution of cosmological information in the Universe. This study paves a new way forward for the performance of efficient targeted searches for the fundamental physics of the Universe, where search strategies are progressively refined with new cosmological data sets within an active learning framework.
|
|
