Skip to content
AsteriaStar
Learning path

Understanding Machine Learning in Astronomy

How astronomy keeps up with the flood of survey data — the machine-learning methods that classify and discover at scale, the applications where they meet the sky, the brokers that triage the alert stream in real time, and the data engineering that keeps it honest. Built on real methods, brokers, and benchmark datasets; nothing is fabricated.

Beginner
  1. 1.1Astronomy at data scaleHow astronomy keeps up with the flood of data.
  2. 1.2Machine-learning methodsThe techniques astronomy borrows and adapts.
  3. 1.3ClassificationSorting millions of objects into kinds.
  4. 1.4Applications on the skyWhere ML meets real astronomy.
Intermediate
  1. 2.1Photometric redshiftsRedshifts for hundreds of millions of galaxies.
  2. 2.2Galaxy morphologyClassifying galaxies by their shape.
  3. 2.3Anomaly detectionFinding the objects nobody expected.
  4. 2.4Real-time alert classificationMillions of alerts a night, classified live.
Advanced
  1. 3.1Alert brokersALeRCE, ANTARES, Fink, and Lasair.
  2. 3.2Self-supervised learningLearning from abundant data without labels.
  3. 3.3Benchmark datasetsComparing methods on equal footing.
  4. 3.4Model evaluationCompleteness, purity, and guarding against overfitting.

Continue learning