Cosmic-CoNN: A Cosmic Ray Detection Deep-Learning Framework, Dataset, and Toolkit

Rejecting cosmic rays (CRs) is essential for the scientific interpretation of CCD-captured data, but detecting CRs in single-exposure images has remained challenging. Conventional CR detectors require experimental parameter tuning for different instruments, and recent deep learning methods only produce instrument-specific models that suffer from performance loss on telescopes not included in the training data. In this work, we present Cosmic-CoNN, a generic CR detector deployed for 24 telescopes at the Las Cumbres Observatory (LCO). We first leverage thousands of images from LCO's global telescope network to build a large, diverse ground-based CR dataset for rich coverage of instruments and CR features. We then optimize a neural network and propose a novel Median-Weighted loss function for CR detection to train a generic model that achieves a 99.91% true-positive detection rate on LCO imaging data and maintains over 96.40% on unseen data from Gemini GMOS-N/S, with a false-positive rate of 0.01%. We also build a suite of tools including an interactive CR mask visualization and editing interface, console commands, and Python APIs to make automatic, robust CR detection widely accessible by the community of astronomers. Our dataset, open-source codebase, and trained models are available at https://github.com/cy-xu/cosmic-conn.