• Home
  • Search
  • Optimised sampling of SDSS-IV MaStar spectra for stellar classification using supervised models
  • https://doi.org/10.1051/0004-6361/202451309Copy DOI Icon

Optimised sampling of SDSS-IV MaStar spectra for stellar classification using supervised models

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Supervised machine learning models are increasingly being used for solving the problem of stellar classification of spectroscopic data. However, training these models calls for a large number of labelled instances, whereas their collection is usually costly in both time and expertise. Active learning (AL) algorithms minimise training dataset sizes by keeping only the most informative instances. This paper explores the application of AL to sampling stellar spectra using data from a highly class-imbalanced dataset. We utilised the MaStar Stellar Library from the SDSS DR17, along with its associated stellar parameter catalogue. A preprocessing pipeline that includes feature selection, scaling, and dimensionality reduction was applied to the data. Using different AL algorithms, we iteratively queried instances where the model or committee of models exhibits the highest uncertainty or disagreement, respectively. We assessed the effectiveness of the sampling techniques by comparing several performance metrics of supervised-learning models trained on the queried samples with randomly sampled counterparts. Evaluation metrics included specificity, sensitivity, and the area under the curve. In addition, we used Matthew's correlation coefficient, which accounts for class imbalance. We applied this procedure to the effective temperature, surface gravity, and iron metallicity, separately. Our results demonstrate the effectiveness of AL algorithms in selecting samples that produce performance metrics that are superior to random sampling and even stratified samples, with fewer training instances. We find AL is recommended for prioritising instance labelling for astronomical-survey data by experts or crowdsourcing to mitigate the high time cost. Its effectiveness can be further exploited in selecting targets for follow-up observations in automated astronomical surveys.

Similar Papers
  • Research Article
  • Citations2

Efficient Exploration of Chemical Compound Space Using Active Learning for Prediction of Thermodynamic Properties of Alkane Molecules.

  • Oct 19, 2023
  • Journal of Chemical Information and Modeling
  • Yan Xiang +6
  • Research Article

Data-efficient learning for accurate identification of MAPK1 inhibitors using an active meta-deep learning framework.

  • Feb 03, 2026
  • Journal of cheminformatics
  • Darlene Nabila Zetta +1
  • Book Chapter
  • Citations6

Selecting Training Samples from Large-Scale Remote-Sensing Samples Using an Active Learning Algorithm

  • Jan 01, 2016
  • Yan Guo +3
  • Research Article
  • Citations19

Active Learning for Crowdsourced QoE Modeling

  • Dec 01, 2018
  • IEEE Transactions on Multimedia
  • Haw-Shiuan Chang +3
  • Research Article
  • Citations32

Cost-aware active learning for named entity recognition in clinical text.

  • Jul 11, 2019
  • Journal of the American Medical Informatics Association
  • Qiang Wei +10
  • Research Article
  • Citations11

Active learning based on minimization of the expected path-length of random walks on the learned manifold structure

  • Jun 06, 2017
  • Pattern Recognition
  • Chin-Chun Chang +1
  • Research Article

Algorithms for Active Learning

  • Dec 19, 2011
  • Burr Settles
  • PDF
  • Research Article

Comparison of active learning algorithms in classifying head computed tomography reports using bidirectional encoder representations from transformers

  • Jan 08, 2025
  • International Journal of Computer Assisted Radiology and Surgery
  • Tomohiro Wataya +12
  • Conference Article
  • Citations1

Diversity-based active learning: creating a representative object detection dataset in 3D point clouds

  • Jun 16, 2023
  • Aimee Moses +4
  • Book Chapter
  • Citations18

Warm Start Active Learning with Proxy Labels and Selection via Semi-supervised Fine-Tuning

  • Jan 01, 2022
  • Vishwesh Nath +3
  • Research Article
  • Citations19

Employing unlabeled data to improve the classification performance of SVM, and its application in audio event classification

  • Feb 17, 2016
  • Knowledge-Based Systems
  • Yan Leng +7
  • Research Article

Abstract 1121: Patient-centric Discovery by Active Learning (PeDAL) platform to predict drug response in a heterogeneous patient population

  • Apr 04, 2023
  • Cancer Research
  • Robert J Montgomery +4
  • Book Chapter
  • Citations17

Multi-Class Probabilistic Active Learning

  • Jan 01, 2016
  • Frontiers in artificial intelligence and applications
  • Kottke Daniel +4
  • Conference Article
  • Citations14

Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice

  • Aug 01, 2018
  • Kunkun Pang +3
  • Research Article
  • Citations29

Active Machine Learning for Chemical Engineers: A Bright Future Lies Ahead!

  • Aug 01, 2023
  • Engineering
  • Yannick Ureel +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.