Machine Learning in Astronomy#
Machine learning techniques are used for both observational and theoretical applications.
Overviews:
Machine Learning in Astronomy: A Practical Overview by D. Baron.
Machine Learning and Cosmology by C. Dvorkin et al.
Some observational examples:
Photometric redshifts with machine learning, lights and shadows on a complex data science use case by Brescia et al.
Machine and Deep Learning Applied to Galaxy Morphology – A Comparative Study by Barchi et al.
Identifying Exoplanets with Machine Learning Methods: A Preliminary Study by Jin et al.
Stellar classification from single-band imaging using machine learning by Kuntzer et al.
Stellar Objects Classification Using Supervised Machine Learning Techniques by Omat et al.
Some theoretical examples:
Physics-informed Machine Learning for Modeling Turbulence in Supernovae by Karpov et al.
Fast and realistic large-scale structure from machine-learning-augmented random field simulations by Piras et al.
Neural Networks for Nuclear Reactions in MAESTROeX by Fan et al.
Machine Learning for Conservative-to-Primitive in Relativistic Hydrodynamics by Dieselhorst et al.
Machine learning moment closure models for the radiative transfer equation I: Directly learning a gradient based closure by Huang et al.
Deep Learning of the Eddington Tensor in Core-collapse Supernova Simulation by Harada et al.
Example notebooks:#
Hello Universe: A framework for testing and benchmarking machine learning methods on astronomical data.
astroML has a set of examples that work with scikit-learn.