Astrophysical and Cosmological Applications of Machine Learnings

• This is Jun, 2019, and an ADS search of “machine learning” in the abstract of referred astronomy journals result in 711 papers, so it is almost too late to try to “read everything”…but at least we can try:
• And, again, this list only reflects one person’s taste.

---

Galaxy Morphology

• Morpheus: A Deep Learning Framework For Pixel-Level Analysis of Astronomical Image Data
  • By Ryan Hausen & Brant Robertson. Based on the work here. Source code is on Github.
  • Morpheus is a neural network model used to generate pixel-level morphological classifications for astronomical sources. This model can be used to generate segmentation maps or to inform other photometric measurements with granular morphological information. Built on Tensorflow.
  • Online document is here; and this notebook is a good place to get started.
• Rotation-invariant convolutional neural networks for galaxy morphology prediction

Photometric Redshift

• TPZ: photometric redshift PDFs and ancillary information by using prediction trees and random forests
  • Decision tree and random forest.

Cosmology

• ml-in-cosmology - a comprehensive list of published machine learning applications to cosmology
  • A beautiful list compiled by George Stein
  • “Each entry contains the paper title, a simple summary of the machine learning methods used in the work, and the arxiv link”
• MiSTree - Beyond two-point statistics: using the Minimum Spanning Tree as a tool for cosmology
  • The public code can be found here