Machine-learning identification of galaxies in the WISE
Bibliographic record
Abstract
Context. The two currently largest all-sky photometric datasets, WISE and SuperCOSMOS, have been recently cross-matched to construct a novel photometric redshift catalogue on 70% of the sky. Galaxies were separated from stars and quasars through colour cuts, which may leave imperfections because different source types may overlap in colour space. Aims. The aim of the present work is to identify galaxies in the WISE × SuperCOSMOS catalogue through an alternative approach of machine learning. This allows us to define more complex separations in the multi-colour space than is possible with simple colour cuts, and should provide a more reliable source classification. Methods. For the automatised classification we used the support vector machines (SVM) learning algorithm and employed SDSS spectroscopic sources that we cross-matched with WISE × SuperCOSMOS to construct the training and verification set. We performed a number of tests to examine the behaviour of the classifier (completeness, purity, and accuracy) as a function of source apparent magnitude and Galactic latitude. We then applied the classifier to the full-sky data and analysed the resulting catalogue of candidate galaxies. We also compared the resulting dataset with the one obtained through colour cuts. Results. The tests indicate very high accuracy, completeness, and purity (>95%) of the classifier at the bright end; this deteriorates for the faintest sources, but still retains acceptable levels of ~85%. No significant variation in the classification quality with Galactic latitude is observed. When we applied the classifier to all-sky WISE × SuperCOSMOS data, we found 15 million galaxies after masking problematic areas. The resulting sample is purer than the one produced by applying colour cuts, at the price of a lower completeness across the sky. Conclusions. The automatic classification is a successful alternative approach to colour cuts for defining a reliable galaxy sample. The identifications we obtained are included in the public release of the WISE × SuperCOSMOS galaxy catalogue.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".