Durée
30h Th, 15h Pr
Nombre de crédits
| Master en science des données, à finalité spécialisée | 5 crédits | |||
| Master : ingénieur civil en science des données, à finalité spécialisée | 5 crédits |
Enseignant
Langue(s) de l'unité d'enseignement
Langue anglaise
Organisation et évaluation
Enseignement au premier quadrimestre, examen en janvier
Horaire
Unités d'enseignement prérequises et corequises
Les unités prérequises ou corequises sont présentées au sein de chaque programme
Contenus de l'unité d'enseignement
This Master's-level course explores the application of machine learning to problems in space science through lectures, guided discussions and practical work using Python and Jupyter notebooks.
The lists below indicate the range of applications and methods from which course topics will be selected. The selection and depth of coverage may vary according to students' prior knowledge, course progression and available time. Not all listed topics will necessarily be covered.
Learning activities may also include guided critical review of scientific explanations, code and results, including LLM-generated material, with attention to accuracy, underlying assumptions and limitations.
Space science topics to be covered (tentative and subject to change):
* Exoplanet Detection and Characterization
* Cosmic Microwave Background Analysis
* Gravitational Wave Detection and Analysis
* Stellar Evolution and Classification
* Galaxy Morphology and Classification
* Dark Matter and Dark Energy Studies
* Black Hole Imaging and Event Horizon Studies
* Solar Activity and Space Weather Prediction
* Astronomical Surveys and Sky Mapping
* Astroparticle Physics and Neutrino Detection
Machine learning techniques to be covered (tentative and subject to change):
* Random Forests
* Convolutional Neural Networks (CNNs)
* Long Short-Term Memory (LSTM) Networks
* Principal Component Analysis (PCA)
* Support Vector Machines (SVM)
* Recurrent Neural Networks (RNNs)
* K-Means Clustering
* Gaussian Mixture Models (GMMs)
* Transfer Learning with Pre-trained Models
* Generative Adversarial Networks (GANs)
Acquis d'apprentissage (objectifs d'apprentissage) de l'unité d'enseignement
By the end of the course, students should be able to:
- Formulate a space science problem as a machine learning task.
- Prepare and explore scientific datasets, identifying relevant limitations in the data.
- Implement and evaluate selected machine learning methods using Python and Jupyter notebooks.
- Interpret model outputs in their scientific context and identify limitations in the methods and conclusions.
- Explain and justify methodological choices, and critically assess scientific explanations, code and results.
Savoirs et compétences prérequis
///
Activités d'apprentissage prévues et méthodes d'enseignement
This course combines lectures with discussion sessions in which students solve problems under the instructor's guidance.
During this academic year, the instructor will pilot the use of large language models (LLMs), with the aim of providing each student with personalised presentations and notebooks based on the instructor's course materials. The approach will be reviewed throughout the year and may be adapted or discontinued in response to student feedback, its educational effectiveness and the availability of technical resources.
Mode d'enseignement (présentiel, à distance, hybride)
Cours donné exclusivement en présentiel
Explications complémentaires:
Face-to-face if possible, depending on the COVID situation.
Supports de cours, lectures obligatoires ou recommandées
Statistics, Data Mining, and Machine Learning for Astronomy, Ivezic et al.
Modalités d'évaluation et critères
Examen(s) en session
Toutes sessions confondues
- En présentiel
évaluation orale
Travail à rendre - rapport
Explications complémentaires:
The exam will consist of several questions concerning the theory as seen during the lectures.
Regarding the Machine Learning application, a take-home exam on a subject discussed together with the lecturer will be assigned to assess students' comprehension and practical application of machine learning techniques in space science.
Stage(s)
Remarques organisationnelles et modifications principales apportées au cours
Sessions will typically combine an introduction to the relevant astrophysical concepts with practical exploration of machine learning methods using Jupyter notebooks, guided problem solving and discussion of results.
Contacts
Maxime Fays
(maxime.fays@uliege.be)
Room 4.43 Bât. B5A
Inter. fondamentales en physique et astrophysique (IFPA)
Quartier Agora allée du six Août 19
4000 Liège
Téléphone de service: +32 4 3663643