ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Predicting the evolution of Arctic sea ice with data science

Dupont, Clément
(2024)

Files

Dupont_26931500_2024.pdf
  • Closed access
  • Adobe PDF
  • 1.72 MB

Details

Supervisors
Delvenne, Jean-Charles ; Massonnet, François
Faculty
Ecole polytechnique de Louvain
Degree label
Master [120] : ingénieur civil en mathématiques appliquées, à finalité spécialisée
Abstract
Both attempting to protect the Arctic’s diversity in fauna and flora and taking advantage of new economical opportunities created by the shifting ice landscape will be in the centre of interest of many. In this regard, getting better at predicting the dynamics of Arctic sea ice could very well be matter of utmost importance in the near future, if it is not already. With the large amount of satellites, sensors and machine-generated datasets providing a panoramic view of the Arctic environment, resorting to data science and machine learning appears to be a potential solution to help us predict the changes happening in the Arctic. In this paper, we will explore different approaches on how we could possibly try to forecast the evolution of Arctic sea ice. However, sea ice dynamics are complex to understand and model and being able to reduce this complex problem to a simple solution would be one of our goals.