Efficient identification of broad absorption line quasars using dimensionality reduction and machine learning
Bibliographic record
Abstract
Abstract Broad Absorption Line Quasars (BALQSOs) represent a significant phenomenon in the realm of quasar astronomy, displaying distinct blueshifted broad absorption lines. These enigmatic objects serve as invaluable probes for unraveling the intricate structure and evolution of quasars, shedding light on the profound influence exerted by supermassive black holes on galaxy formation. The proliferation of large-scale spectroscopic surveys such as LAMOST (the Large Sky Area Multi-Object Fiber Spectroscopic Telescope), SDSS (the Sloan Digital Sky Survey), and DESI (the Dark Energy Spectroscopic Instrument) has exponentially expanded the repository of quasar spectra at our disposal. In this study, we present an innovative approach to streamline the identification of BALQSOs, leveraging the power of dimensionality reduction and machine-learning algorithms. Our dataset is meticulously curated from the SDSS Data Release 16 (DR16), amalgamating quasar spectra with classification labels sourced from the DR16Q quasar catalog. We employ a diverse array of dimensionality-reduction techniques, including principal component analysis (PCA), t-Distributed stochastic neighbor embedding (t-SNE), locally linear embedding (LLE), and isometric mapping (ISOMAP), to distill the essence of the original spectral data. The resultant low-dimensional representations serve as inputs for a suite of machine-learning classifiers, including the robust XGBoost and Random Forest models. Through rigorous experimentation, we unveil PCA as the most effective dimensionality-reduction methodology, adeptly navigating the intricate balance between dimensionality reduction and preservation of vital spectral information. Notably, the synergistic fusion of PCA with the XGBoost classifier emerges as the pinnacle of efficacy in the BALQSO classification endeavor, boasting impressive accuracy rates of $97.60\%$ by 10-cross validation and $96.92\%$ on the outer test sample. This study not only introduces a novel machine-learning-based paradigm for quasar classification but also offers invaluable insights transferrable to a myriad of spectral classification challenges pervasive in the realm of astronomy.
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 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 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".