# Uncertainty-aware learning for improvements in image quality of the Canada-France-Hawaii Telescope

Abstract : We leverage state-of-the-art machine learning methods and a decade's worth of archival data from Canada-France-Hawaii Telescope (CFHT) to predict observatory image quality (IQ) from environmental conditions and observatory operating parameters. Specifically, we develop accurate and interpretable models of the complex dependence between data features and observed IQ for CFHT's wide-field camera, MegaCam. Our contributions are several-fold. First, we collect, collate, and reprocess several disparate data sets gathered by CFHT scientists. Second, we predict probability distribution functions of IQ and achieve a mean absolute error of ~0.07 arcsec for the predicted medians. Third, we explore the data-driven actuation of the 12 dome 'vents' installed in 2013-14 to accelerate the flushing of hot air from the dome. We leverage epistemic and aleatoric uncertainties in conjunction with probabilistic generative modelling to identify candidate vent adjustments that are in-distribution (ID); for the optimal configuration for each ID sample, we predict the reduction in required observing time to achieve a fixed signal-to-noise ratio. On average, the reduction is $\sim 12{{\ \rm per\ cent}}$. Finally, we rank input features by their Shapley values to identify the most predictive variables for each observation. Our long-term goal is to construct reliable and real-time models that can forecast optimal observatory operating parameters to optimize IQ. We can then feed such forecasts into scheduling protocols and predictive maintenance routines. We anticipate that such approaches will become standard in automating observatory operations and maintenance by the time CFHT's successor, the Maunakea Spectroscopic Explorer, is installed in the next decade.
Keywords :
Document type :
Journal articles

https://hal-insu.archives-ouvertes.fr/insu-03656923
Contributor : Nathalie POTHIER Connect in order to contact the contributor
Submitted on : Monday, May 2, 2022 - 2:55:18 PM
Last modification on : Tuesday, May 17, 2022 - 9:38:01 AM

### Citation

Sankalp Gilda, Stark C. Draper, Sébastien Fabbro, William Mahoney, Simon Prunet, et al.. Uncertainty-aware learning for improvements in image quality of the Canada-France-Hawaii Telescope. Monthly Notices of the Royal Astronomical Society, Oxford University Press (OUP): Policy P - Oxford Open Option A, 2022, 510, pp.870-902. ⟨10.1093/mnras/stab3243⟩. ⟨insu-03656923⟩

Record views