A machine learning approach to galactic emission-line region classification
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Diagnostic diagrams of emission-line ratios have been used extensively to categorize extragalactic emission regions; however, these diagnostics are occasionally at odds with each other due to differing definitions. In this work, we study the applicability of supervised machine-learning techniques to systematically classify emission-line regions from the ratios of certain emission lines. Using the Million Mexican Model database, which contains information from grids of photoionization models using cloudy, and from shock models, we develop training and test sets of emission line fluxes for three key diagnostic ratios. The sets are created for three classifications: classic H ii regions, planetary nebulae, and supernova remnants. We train a neural network to classify a region as one of the three classes defined above given three key line ratios that are present both in the SITELLE and MUSE instruments’ band-passes: [O iii]λ5007/H β, [N ii]λ6583/H α, ([S ii]λ6717+[S ii]λ6731)/H α. We also tested the impact of the addition of the [O ii]λ3726, 3729/[O iii]λ5007 line ratio when available for the classification. A maximum luminosity limit is introduced to improve the classification of the planetary nebulae. Furthermore, the network is applied to SITELLE observations of a prominent field of M33. We discuss where the network succeeds and why it fails in certain cases. Our results provide a framework for the use of machine learning as a tool for the classification of extragalactic emission regions. Further work is needed to build more comprehensive training sets and adapt the method to additional observational constraints.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it