Uw huidige browser heeft updates nodig. Zolang u niet update zullen bepaalde functionaliteiten op de website niet beschikbaar zijn.
Let op: het geselecteerde rooster heeft overlappende bijeenkomsten.
Volgens onze gegevens heb je nog geen vakken behaald.
Je planning is nog niet opgeslagen
Let op! Uw planning heeft vakken in dezelfde periode met overlappend timeslot
Tipping Phenomena in the Climate-Society System (2024/2025: Periode 4)
Cursusdoel
Course goals
1. Get familiar with the theory behind modern machine learning techniques
2. Practice machine learning techniques on standard computer science problems
3. Get an overview of the application of these techniques in climate research
4. Practice the application of machine learning techniques to several climate science problems
1. Get familiar with the theory behind modern machine learning techniques
2. Practice machine learning techniques on standard computer science problems
3. Get an overview of the application of these techniques in climate research
4. Practice the application of machine learning techniques to several climate science problems
Vakinhoudelijk
Motivation
There has been an exponential increase of observational climate system data since the first weather satellite has been put in orbit. An even faster growth of modelling data from simulations with models of increasing resolution and complexity has occurred. Big data and the associated algorithms (Machine Learning, ML) provides the opportunity to learn about quantities related to the climate system in ways and with an amount of detail that were infeasible only a few years ago. The opportunity for descriptive inference creates the chance for climate scientists to ask causal questions and create new theories or validate old ones. Furthermore, when paired with modeling experiments or robust research in model parameterizations, big data can provide data-driven answers to vexing questions.
Overview
The course will be divided into four parts. During the first part, basic ML techniques will be discussed, with applications to standard (more computer science oriented) problems such as image recognition. Here, we will deal for example with applications of Feedforward Neural Networks, Convolutional Neural Networks and Reservoir Computers to classification and regression problems. Also unsupervised ML methods, such as clustering methods, will be presented. The three following parts of the course will deal with applications of so-called 'soft' (ML is more efficient), 'medium' (ML replaces part of a model) and 'hard' (fully data-based) ML approaches to climate problems/modeling, covering topics in the areas of downscaling, parameterization and prediction.
There has been an exponential increase of observational climate system data since the first weather satellite has been put in orbit. An even faster growth of modelling data from simulations with models of increasing resolution and complexity has occurred. Big data and the associated algorithms (Machine Learning, ML) provides the opportunity to learn about quantities related to the climate system in ways and with an amount of detail that were infeasible only a few years ago. The opportunity for descriptive inference creates the chance for climate scientists to ask causal questions and create new theories or validate old ones. Furthermore, when paired with modeling experiments or robust research in model parameterizations, big data can provide data-driven answers to vexing questions.
Overview
The course will be divided into four parts. During the first part, basic ML techniques will be discussed, with applications to standard (more computer science oriented) problems such as image recognition. Here, we will deal for example with applications of Feedforward Neural Networks, Convolutional Neural Networks and Reservoir Computers to classification and regression problems. Also unsupervised ML methods, such as clustering methods, will be presented. The three following parts of the course will deal with applications of so-called 'soft' (ML is more efficient), 'medium' (ML replaces part of a model) and 'hard' (fully data-based) ML approaches to climate problems/modeling, covering topics in the areas of downscaling, parameterization and prediction.
Werkvormen
Hoorcollege
Werkcollege
Werkcollege
Toetsing
Eindresultaat
Verplicht | Weging 100% | ECTS 7,5
- Projects (50%), Exercises (25%) and Presentations (25%)
Ingangseisen en voorkennis
Ingangseisen
Je moet een geldige toelatingsbeschikking hebben
Voorkennis
Er is geen informatie over benodigde voorkennis bekend.
Voertalen
- Engels
Cursusmomenten
Gerelateerde studies
Tentamens
Er is geen tentamenrooster beschikbaar voor deze cursus
Verplicht materiaal
Er is geen informatie over de verplichte literatuur bekend
Aanbevolen materiaal
-
ARTIKELENSee Blackboard
Coördinator
| prof. dr. ir. H.A. Dijkstra | H.A.Dijkstra@uu.nl |
Docenten
Inschrijving
Deze cursus is open voor bijvakkers. Controleer wel of er aanvullende ingangseisen gelden.
Inschrijving
Van maandag 27 januari 2025 tot en met vrijdag 7 februari 2025
Na-inschrijving
Van maandag 31 maart 2025 tot en met dinsdag 1 april 2025
Inschrijving niet geopend
Permanente link naar de cursuspagina
Laat in de Cursus-Catalogus zien
Laat in MyTimetable zien
klikt, stop je een vak in je rugzak, zodat je dit vak door de rest van de CursusPlanner mee kunt nemen.