MAXIMASK and MAXITRACK: Two new tools for identifying contaminants in astronomical images using convolutional neural networks
Bibliographic record
Abstract
In this work, we propose two convolutional neural network classifiers for detecting contaminants in astronomical images. Once trained, our classifiers are able to identify various contaminants, such as cosmic rays, hot and bad pixels, persistence effects, satellite or plane trails, residual fringe patterns, nebulous features, saturated pixels, diffraction spikes, and tracking errors in images. They encompass a broad range of ambient conditions, such as seeing, image sampling, detector type, optics, and stellar density. The first classifier, MAXIMASK, performs semantic segmentation and generates bad pixel maps for each contaminant, based on the probability that each pixel belongs to a given contaminant class. The second classifier, MAXITRACK, classifies entire images and mosaics, by computing the probability for the focal plane to be affected by tracking errors. We gathered training and testing data from real data originating from various modern charged-coupled devices and near-infrared cameras, that are augmented with image simulations. We quantified the performance of both classifiers and show that MAXIMASKachieves state-of-the-art performance for the identification of cosmic ray hits. Thanks to a built-in Bayesian update mechanism, both classifiers can be tuned to meet specific science goals in various observational contexts.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".