Skip to content
AsteriaStar
Data-engineering workflow

Model Evaluation

Measuring honestly how well a model performs — its accuracy, completeness, and purity, whether its confidences are calibrated, and how it behaves on data unlike its training set. Careful evaluation is what separates a genuinely useful model from one that has merely memorised its examples.

Highlights

  • Completeness, purity, calibration — and guarding against overfitting

Used across astro-ML

Knowledge connections

Sources

The primary and reference sources this topic draws on.

  • NASANational Aeronautics and Space Administration

    Mission data, planetary science, space telescopes, and public-domain imagery.

    Most NASA-produced imagery is in the public domain; individual items are checked for usage terms before publication.