REVIEW 6 cited by
Using Active Learning to Improve Quasar Identification for the DESI Spectra Processing Pipeline
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Using Active Learning to Improve Quasar Identification for the DESI Spectra Processing Pipeline
read the original abstract
The Dark Energy Spectroscopic Instrument (DESI) survey uses an automatic spectral classification pipeline to classify spectra. QuasarNET is a convolutional neural network used as part of this pipeline originally trained using data from the Baryon Oscillation Spectroscopic Survey (BOSS). In this paper we implement an active learning algorithm to optimally select spectra to use for training a new version of the QuasarNET weights file using only DESI data, specifically to improve classification accuracy. This active learning algorithm includes a novel outlier rejection step using a Self-Organizing Map to ensure we label spectra representative of the larger quasar sample observed in DESI. We perform two iterations of the active learning pipeline, assembling a final dataset of 5600 labeled spectra, a small subset of the approx 1.3 million quasar targets in DESI's Data Release 1. When splitting the spectra into training and validation subsets we meet or exceed the previously trained weights file in completeness and purity calculated on the validation dataset with less than one tenth of the amount of training data. The new weights also more consistently classify objects in the same way when used on unlabeled data compared to the old weights file. In the process of improving QuasarNET's classification accuracy we discovered a systemic error in QuasarNET's redshift estimation and used our findings to improve our understanding of QuasarNET's redshifts.
Forward citations
Cited by 6 Pith papers
-
DESI DR2 Results II: Measurements of Baryon Acoustic Oscillations and Cosmological Constraints
DESI DR2 BAO data exhibits 2.3 sigma tension with CMB in Lambda-CDM but prefers evolving dark energy (w0 > -1, wa < 0) at 3.1 sigma with CMB and 2.8-4.2 sigma when including supernovae.
-
DESI DR2 Results IV: Alcock-Paczy\'nski Measurements from the Lyman Alpha Forest and Cosmological Constraints
The full shape of DESI DR2 Lyman-alpha forest correlations constrains the distance ratio DM/DH at z=2.33 to 1.0%, twice as precise as BAO alone.
-
DESI DR2 Results IV: Alcock-Paczy\'nski Measurements from the Lyman Alpha Forest and Cosmological Constraints
DESI DR2 Lyman-alpha forest full-shape correlations yield a 1% Alcock-Paczyński measurement at z=2.33 and 0.8% distance ratio constraints.
-
Early results in the search for extreme coronal line emitters with the Dark Energy Spectroscopic Instrument
A DESI early-data search found three tidal-disruption-event-linked extreme coronal line emitters, giving a galaxy-normalized rate of 5 (+5/-3) × 10^-6 galaxy^-1 yr^-1 at z ≈ 0.2.
-
Validation of the DESI DR2 Ly$\alpha$ forest full-shape analysis
The DESI DR2 Lyman-alpha full-shape analysis passes validation for BAO and Alcock-Paczynski parameters on 400 mocks and blinded data, while f-sigma-8 is rejected due to a roughly 10% mock bias.
-
DESI DR2 Results I: Baryon Acoustic Oscillations from the Lyman Alpha Forest
DESI DR2 delivers 0.65% precision BAO measurements from the LyA forest at z_eff=2.33, with D_H/r_d = 8.632 ± 0.098 ± 0.026 and D_M/r_d = 38.99 ± 0.52 ± 0.12.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.