Cosmic Ray Rejection with Attention Augmented Deep Learning
arXiv:2207.10411 · doi:10.1016/j.ascom.2022.100625
Abstract
Cosmic Ray (CR) hits are the major contaminants in astronomical imaging and spectroscopic observations involving solid-state detectors. Correctly identifying and masking them is a crucial part of the image processing pipeline, since it may otherwise lead to spurious detections. For this purpose, we have developed and tested a novel Deep Learning based framework for the automatic detection of CR hits from astronomical imaging data from two different imagers: Dark Energy Camera (DECam) and Las Cumbres Observatory Global Telescope (LCOGT). We considered two baseline models namely deepCR and Cosmic-CoNN, which are the current state-of-the-art learning based algorithms that were trained using Hubble Space Telescope (HST) ACS/WFC and LCOGT Network images respectively. We have experimented with the idea of augmenting the baseline models using Attention Gates (AGs) to improve the CR detection performance. We have trained our models on DECam data and demonstrate a consistent marginal improvement by adding AGs in True Positive Rate (TPR) at 0.01% False Positive Rate (FPR) and Precision at 95% TPR over the aforementioned baseline models for the DECam dataset. We demonstrate that the proposed AG augmented models provide significant gain in TPR at 0.01% FPR when tested on previously unseen LCO test data having images from three distinct telescope classes. Furthermore, we demonstrate that the proposed baseline models with and without attention augmentation outperform state-of-the-art models such as Astro-SCRAPPY, Maximask (that is trained natively on DECam data) and pre-trained ground-based Cosmic-CoNN. This study demonstrates that the AG module augmentation enables us to get a better deepCR and Cosmic-CoNN models and to improve their generalization capability on unseen data.
arXiv comment21 pages, 23 figures. Accepted in Astronomy and Computing
References in corpus (30)
- Adam: A Method for Stochastic Optimization
- SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
- Array Programming with NumPy
- Astropy: A Community Python Package for Astronomy
- scikit-image: Image processing in Python
- Attention U-Net: Learning Where to Look for the Pancreas
- A systematic study of the class imbalance problem in convolutional neural networks
- Cosmic-Ray Rejection by Laplacian Edge Detection
- Las Cumbres Observatory Global Telescope Network
- The Dark Energy Camera
- Noise2Noise: Learning Image Restoration without Clean Data
- Drizzle: A Method for the Linear Reconstruction of Undersampled Images
- The Dark Energy Survey Data Release 1
- Data Mining and Machine Learning in Astronomy
- The Blanco Cosmology Survey: Data Acquisition, Processing, Calibration, Quality Diagnostics and Data Release
- Dark Energy Survey Year 3 Results: Photometric Data Set for Cosmology
- A Fast Algorithm for Cosmic Rays Removal from Single Images
- Separation of pulsar signals from noise with supervised machine learning algorithms
- Cosmic Ray Rejection by Linear Filtering of Single Images
- deepCR: Cosmic Ray Rejection with Deep Learning
- Implementation of robust image artifact removal in SWarp through clipped mean stacking
- Learning what to look in chest X-rays with a recurrent visual attention model
- MaxiMask and MaxiTrack: two new tools for identifying contaminants in astronomical images using convolutional neural networks
- Detection and Removal of Artifacts in Astronomical Images
- On the efficiency of techniques for the reduction of impulsive noise in astronomical images
- Evaluation of cosmic ray rejection algorithms on single-shot exposures
- CosmoDM and its application to Pan-STARRS data
- Cosmic Ray Removal in Fiber Spectroscopic Image
- A Machine Learning Approach to the Detection of Ghosting and Scattered Light Artifacts in Dark Energy Survey Images
- Cosmic-CoNN: A Cosmic Ray Detection Deep-Learning Framework, Dataset, and Toolkit