Vorlesung: Deep Learning for Weather Forecasting (Lecture) - Details

Allgemeine Informationen

Veranstaltungsname	Vorlesung: Deep Learning for Weather Forecasting (Lecture)
Veranstaltungsnummer	INF-3067
Semester	SS 2026
Aktuelle Anzahl der Teilnehmenden	39
erwartete Teilnehmendenanzahl	30
Heimat-Einrichtung	Intelligente und multimodale Energiesysteme
Veranstaltungstyp	Vorlesung in der Kategorie Lehre
Nächster Termin	Montag, 17.08.2026 09:00 - 16:00
Veranstaltung findet in Präsenz statt / hat Präsenz-Bestandteile	Ja
Hauptunterrichtssprache	englisch
ECTS-Punkte	5

Lehrende

• Prof.Dr. Nicole Ludwig

Räume und Zeiten

Keine Raumangabe

Montag, 17.08.2026 09:00 - 16:00
Dienstag, 18.08.2026 09:00 - 16:00
Mittwoch, 19.08.2026 09:00 - 16:00
Donnerstag, 20.08.2026 09:00 - 16:00
Freitag, 21.08.2026 09:00 - 16:00

Studienbereiche

• Fakultät für Angewandte Informatik > Informatik

Modulzuordnungen

• Informatik und Multimedia M.Sc. Informatik und Multimedia, PO 2018, 16. Version gültig ab SS 2026 > Multimedia > INF-3067 - Deep Learning for Weather Forecasting > Deep Learning for Weather Forecasting (Lecture)
• Informatik M.Sc. Informatik, PO 2018, 16. Version gültig ab SS 2026 > Praktische Informatik > INF-3067 - Deep Learning for Weather Forecasting > Deep Learning for Weather Forecasting (Lecture)
• Medizinische Informatik M.Sc. Medizinische Informatik, PO 2021, 10. Version gültig ab SS 2026 > Informatik > INF-3067 - Deep Learning for Weather Forecasting > Deep Learning for Weather Forecasting (Lecture)
• Medizinische Informatik M.Sc. Medizinische Informatik, PO 2021, 10. Version gültig ab SS 2026 > Wahlbereich > INF-3067 - Deep Learning for Weather Forecasting > Deep Learning for Weather Forecasting (Lecture)
• Informatik M.Sc. Informatik, PO 2018, 16. Version gültig ab SS 2026 > Wahlbereich Informatik > INF-3067 - Deep Learning for Weather Forecasting > Deep Learning for Weather Forecasting (Lecture)
• Informatik und Multimedia M.Sc. Informatik und Multimedia, PO 2018, 16. Version gültig ab SS 2026 > Wahlbereich Informatik und Multimedia > INF-3067 - Deep Learning for Weather Forecasting > Deep Learning for Weather Forecasting (Lecture)

Kommentar/Beschreibung

This is a block course in the summer term 2026, from Monday, 17th of August until Friday, 21st of August. Each day, several lectures and exercise sessions will take place with breaks in between (roughly 9am to 4pm). You'll be graded based on a short paper (4 pages) detailing the results of a weather forecasting coding project.

This course provides an advanced treatment of modern deep learning architectures for numerical weather prediction, tracing the rapid shift from classical physics-based models towards data-driven and hybrid approaches. Starting from the foundations of atmospheric modelling and the structure of weather data, students progressively engage with the family of architectures that have come to define the current state of the art, including transformer-based models, graph neural networks, neural operators, diffusion models, and hybrid physics-ML systems. The course places particular emphasis on global medium-range forecasting and situates each model within the broader landscape of operational weather prediction.