In the above animation: The moving circular mark is where the telescope is pointed to at any given moment. Those parts of the sky that are covered during the same night are star-like colored marks, and the color reflects the filter with which the observation is performed. The gray areas are where the sky is bright and generally no observation is allowed, for instance, the halo around the moon. The white areas show where the clouds are based on a realistic model of the cloud covers at the LSST site in Cerro Pachon. Finally, the light-orange areas, which do not change as the time goes by, indicate the four main sky regions (Galactic Plane Region, Universal or Wide Fast Deep, South Celestial Pole, North Ecliptic Spur).

We showed that traditional operational schemes cannot optimally utilize the new generation of fast astronomical instruments. Then we introduced an approximate Markovian Decision Process (MDP) to model the hybrid system of telescope-environment. Given the MDP model, we presented an adaptive decision-making strategy to optimally operate a ground-based instrument. Our strategy is a framework that can be adopted and customized for a wide variety of astronomical missions. It can be automatically and efficiently trained with different sets of mission objectives and constraints. In addition to our theoretical work, we developed, based on the proposed decision-making framework, an open-source software that will be used to schedule the Large Synoptic Survey Telescope (LSST).

[github; my prototype] [github; LSST's official implementation of the Feature-Based scheduler