Uncover: Toward Interpretable Models for Detecting New Star Cluster Members

Publications: Contribution to journalArticlePeer Reviewed


In this design study, we present Uncover, an interactive tool aimed at astronomers to find previously unidentified member stars in stellar clusters. We contribute data and task abstraction in the domain of astronomy and provide an approach for the non-trivial challenge of finding a suitable hyper-parameter set for highly flexible novelty detection models. We achieve this by substituting the tedious manual trial and error process, which usually results in finding a small subset of passable models with a five-step workflow approach. We utilize ranges of a priori defined, interpretable summary statistics models have to adhere to. Our goal is to enable astronomers to use their domain expertise to quantify model goodness effectively. We attempt to change the current culture of blindly accepting a machine learning model to one where astronomers build and modify a model based on their expertise. We evaluate the tools' usability and usefulness in a series of interviews with domain experts.

Original languageEnglish
Pages (from-to)3855-3872
Number of pages18
JournalIEEE Transactions on Visualization and Computer Graphics
Issue number9
Early online date5 May 2022
Publication statusPublished - 1 Sep 2023

Austrian Fields of Science 2012

  • 103003 Astronomy
  • 103004 Astrophysics
  • 102019 Machine learning
  • 102001 Artificial intelligence


  • Anomaly detection
  • Computational modeling
  • Data models
  • Data science
  • Extraterrestrial measurements
  • Interpretable models
  • model selection
  • novelty detection
  • Predictive models
  • star clusters
  • Stars


Dive into the research topics of 'Uncover: Toward Interpretable Models for Detecting New Star Cluster Members'. Together they form a unique fingerprint.

Cite this