Universität Wien

280356 VU Fundamentals of Machine Learning in Meteorology (2023S)

5.00 ECTS (3.00 SWS), SPL 28 - Erdwissenschaften, Meteorologie - Geophysik und
Continuous assessment of course work
Moodle

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 15 participants
Language: English

Lecturers

Classes (iCal) - next class is marked with N

UZA II: Friday 2G542

Lectures:

March
Mo 06.03.2023
Mo 20.03.2023
Mo 27.03.2023

April
Mo 17.04.2023
Mo 24.04.2023

May
Mo 08.05.2023
Mo 15.05.2023
Mo 29.05.2023

June
Mo 05.06.2023
Mo 12.06.2023
Mo 19.06.2023
Mo 26.06.2023 Examination

Excercises
Fr 28.04.2023
Fr 26.05.2023
Fr 23.06.2023

  • Monday 06.03. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II
  • Monday 20.03. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II
  • Monday 27.03. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II
  • Monday 17.04. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II
  • Monday 24.04. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II
  • Friday 28.04. 13:00 - 17:00 Ort in u:find Details
  • Monday 08.05. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II
  • Monday 15.05. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II
  • Friday 26.05. 13:00 - 17:00 Ort in u:find Details
  • Monday 05.06. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II
  • Monday 12.06. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II
  • Monday 19.06. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II
  • Friday 23.06. 13:00 - 17:00 Ort in u:find Details
  • Monday 26.06. 17:15 - 18:45 Praktikumsraum Meteorologie 2F513 5.OG UZA II

Information

Aims, contents and method of the course

Objectives:

To understand and apply machine learning methods in the field of meteorology.

Contents:

Overview of machine learning methods
Concepts of Machine Learning
Regressions and classifications
Clustering and dimension reduction
Decision trees
Artificial Neural Networks
Reinforcement learning

Teaching via lecture (Powerpoint) and computer exercises

Assessment and permitted materials

Multiple Choice Test for Lecture Topics in last Lecture Unit (Proportion of total evaluation: 40 %)
One Test with Programming Tasks at end of last exercise block (Proportion of total evaluation: 30 %)
One Presentation on a meteorological machine learning topic from literature (Proportion of total evaluation: 30 %)

In multiple-choice tests no tools are allowed, in computer tasks any tools are allowed

Minimum requirements and assessment criteria

Multiple Choice Test for Lecture Topics in last Lecture Unit (Proportion of total evaluation: 40 %)
One Test with Programming Tasks at end of last exercise block (Proportion of total evaluation: 30 %)
One Presentation on a meteorological machine learning topic from literature (Proportion of total evaluation: 30 %)

Points of the individual partial performances are weighted, added up, standardized to the maximum points to be achieved and converted into a grade with the following key:

Score Key: 0-49.99%: 5, 50.00-62.49%: 4, 62.50-74.99%: 3, 75:00-87.49%: 2, > 87.50%: 1

Examination topics

Lecture content will be tested via multiple choice test

In addition, students must present a paper on a meteorological AI application from the literature.

The material from the exercises must be applied in the form of Python computer exercises.

Reading list

The Elements of Statistical Learning (Trevor Hastie, Robert Tibshirani, Jerome Friedman)
An Introduction to statistical Learning (Gareth James, Daniela Witten, Robert Tibshirani, Jerome Friedman)
Python Machine Learning (Sebastian Raschka, Vahid Mirjalili)
Python Machine Learning by Example (Yuxi Hayden Liu)
Deep Learning for The Earth Sciences (Gustau Camps-Valls )

Association in the course directory

WM-AdvComMet

Last modified: Tu 03.12.2024 00:16