Segmentation and Celestial Mapping of Unobservable Regions in Nighttime All-sky Images for the Mephisto Observations

TL;DR

This paper introduces a deep learning segmentation framework that accurately identifies unobservable sky regions in nighttime all-sky images, enabling real-time, celestial coordinate mapping for improved autonomous telescope scheduling.

Contribution

The paper presents a novel deep learning-based pixel-level segmentation method for unobservable sky regions, supported by a manually annotated dataset, and maps these regions to celestial coordinates for real-time observation planning.

Findings

High-precision detection of cloud- and moonlight-affected regions

Seamless integration with observation control systems for real-time scheduling

Framework generalizable to other wide-field robotic observatories

Abstract

Accurate identification of unobservable regions in nighttime is essential for autonomous scheduling and data quality control in observations.Traditional methods-such as infrared sensing or photometric extinction-provide only coarse,non-spatial estimates of sky clarity,making them insufficient for real-time decision-making.This not only wastes observing time but also introduces contamination when telescopes are directed toward cloud-covered or moonlight-affected regions.To address these limitations,we propose a deep learning-based segmentation framework that provides pixel-level masks of unobservable areas using all-sky images.Supported by a manually annotated dataset of nighttime images,our method enables precise detection of cloud- and moonlight-affected regions.The segmentation results are further mapped to celestial coordinates through Zenithal Equal-Area projection,allowing seamless integration with observation control systems (OCS) for real-time cloud-aware scheduling.While developed for the Mephisto telescope,the framework is generalizable and applicable to other wide-field robotic observatories equipped with all-sky monitoring.