Search

Intelligent scheduling of the sequence of scientific exposures taken at ground-based astronomical observatories is massively challenging. Observing time is over-subscribed and atmospheric conditions are constantly changing. We propose to guide observatory scheduling using machine learning. Leveraging a 15-year archive of exposures, environmental, and operating conditions logged by the Canada-France-Hawaii Telescope, we construct a probabilistic data-driven model that accurately predicts image quality. We demonstrate that, by optimizing the opening and closing of twelve vents placed on the dome of the telescope, we can reduce dome-induced turbulence and improve telescope image quality by (0.05-0.2 arc-seconds). This translates to a reduction in exposure time (and hence cost) of $\sim 10-15\%$. Our study is the first step toward data-based optimization of the multi-million dollar operations of current and next-generation telescopes., Comment: 4 pages, 3 figures. Accepted to Machine Learning and the Physical Sciences Workshop at the 34th Conference on Neural Information Processing Systems (NeurIPS)

SITELLE is a novel integral field unit spectroscopy instrument that has an impressive spatial (11 by 11 arcmin), spectral coverage, and spectral resolution (R=1-20000). SIGNALS is anticipated to obtain deep observations (down to 3.6x10-17ergs s-1cm-2) of 40 galaxies, each needing complex and substantial time to extract spectral information. We present a method that uses Convolution Neural Networks (CNN) for estimating emission line parameters in optical spectra obtained with SITELLE as part of the SIGNALS large program. Our algorithm is trained and tested on synthetic data representing typical emission spectra for HII regions based on Mexican Million Models database(3MdB) BOND simulations. The network's activation map demonstrates its ability to extract the dynamical (broadening and velocity) parameters from a set of 5 emission lines (e.g. H��, N[II] doublet, and S[II] doublet) in the SN3 (651-685 nm) filter of SITELLE. Once trained, the algorithm was tested on real SITELLE observations in the SIGNALS program of one of the South West fields of M33. The CNN recovers the dynamical parameters with an accuracy better than 5 km s-1 in regions with a signal-to-noise ratio greater than 15 over the H��line. More importantly, our CNN method reduces calculation time by over an order of magnitude on the spectral cube with native spatial resolution when compared with standard fitting procedures. These results clearly illustrate the power of machine learning algorithms for the use in future IFU-based missions. Subsequent work will explore the applicability of the methodology to other spectral parameters such as the flux of key emission lines., 14 pages, 11 figures Accepted in ApJ

We present a new fully data-driven algorithm that uses photometric data from the Canada-France-Imaging-Survey (CFIS; $u$), Pan-STARRS 1 (PS1; $griz$), and Gaia ($G$) to discriminate between dwarf and giant stars and to estimate their distances and metallicities. The algorithm is trained and tested using the SDSS/SEGUE spectroscopic dataset and Gaia photometric/astrometric dataset. At [Fe/H]$, Comment: 27 pages. 21 Figures. Accepted for publication in AAS. Training/testing sample available at: http://www.canfar.net/storage/list/gthomas/dwarfOrGiants.fits