A textbook

Statistical Machine Learning for Astronomy

A consistently Bayesian, first-principles treatment of machine learning for astronomy — deriving each method from the ground up, with uncertainty quantification and statistical rigor at its core. Sixteen chapters for final-year undergraduates and graduate students, each paired with a hands-on tutorial on real astronomical data.

Chapters

Tutorials

Runnable

Code & Outputs

Start reading Table of contents Read on arXiv ↗

About this book

Statistical Machine Learning for Astronomy gives a systematic, consistently Bayesian treatment of machine learning for astronomical research — deriving each method from first principles and revealing how modern techniques connect to their classical statistical foundations. This site presents it as an interactive reader, placing each chapter next to the tutorial(s) that put it into practice on real astronomical data.

Bayesian by design — inference, priors, and posteriors as the organizing principle, not an afterthought.
Uncertainty quantification woven through regression, classification, and modern methods.
Real astronomical applications — APOGEE spectra, Gaia photometry, JWST images, light curves, and more.
From foundations to frontier — probability and regression through MCMC, Gaussian processes, and neural networks.

Table of Contents