Astronomical Data Science
Faculteit  Science and Engineering 
Jaar  2022/23 
Vakcode  WMAS00705 
Vaknaam  Astronomical Data Science 
Niveau(s)  master 
Voertaal  Engels 
Periode  semester II b 
ECTS  5 
Rooster  rooster.rug.nl 
Uitgebreide vaknaam  Astronomical Data Science  
Leerdoelen  At the end of the course, the student is able to:


Omschrijving  This course will examine the landscape of Big Data information systems, machine learning and deep learning methods in astronomy. The first part of the course will focus on Data Science Systems. We will introduce the basic challenges in Data Science and Data Science Systems in astronomy. This is followed by lectures on the basics of Data Science Systems, and more indepth description of systems for observational Big Data astronomy, Big Data visualisation and for large astrophysical simulations. The second part of the course will focus on Data Science algorithms. We will begin by an introduction to the fundamentals of machine learning, followed by more indepth lectures on some of the most popular machine learning methods and their applications in astronomy. The last part of the course will be focused on deep learning which has emerged as one of the most exciting areas in machine learning. We will also specifically focus on convolutional neural networks as a classification tool in astronomy. Throughout the course a number of practical exercises will be given and a key aim is to enable the student to reach a level where (s)he can apply the tools to their own research problems. At the end of the course the student should be able to plan the optimal data processing during own research, to select necessary tools, to use Virtual Observatory for the data mining and know the basic concepts for publishing her/his own results, for creating a system for managing and developing code and to check code quality. The ultimate goal is to enable students to perform a simple endtoend research exercise from retrieving data, to preprocessing data, to develop a machine/deep learning Python code, to analyse the results and eventually draw up scientific conclusions.  
Uren per week  140  
Onderwijsvorm  Hoorcollege (LC), Werkcollege (T)  
Toetsvorm 
Opdracht (AST), Practisch werk (PR), Verslag (R)
(Assignment (AST) 30%, Final project and report (R) 70%) 

Vaksoort  master  
Coördinator  L. Wang  
Docent(en)  dr. G.A. Verdoes Kleijn , L. Wang  
Entreevoorwaarden  This course is set up such that it is intended not to require any specific prerequisites for any students with a BSc Astronomy. For students with a BSc Astronomy from a university other than the University of Groningen and for nonastronomy students: it is assumed that you possess basic scales in programming and computational methods, such as taught in Introduction to Programming and Computational Methods (WBAS01305). For example, this course will make extensive use of the Python programming language. Therefore a minimum requirement for this course is a good general knowledge of Python and its main scientific libraries (e.g., NumPy, Pandas, Matplotlib). 

Opmerkingen  Text book: the course does not follow a specific text book. Note that there are many resources available online to learning about machine learning and deep learning (e.g., from Stanford University available on YouTube). This course will make use of some chapters in the book, HandsOn Machine Learning with ScikitLearn & TensorFlow (Concepts, Tools and Techniques to Build Intelligent Systems) by Aurélien Géron, published by O’Reilly. Part of the course content will also be drawn from recent publications in astronomy that features the use of machine learning and deep learning. This course was registered previously with course code WMAS16000 

Opgenomen in 
