Spatial and statistical modelling of air pollution in Belgium

Details

Supervisors

Hafner, Christian

Faculty

Faculté des sciences

Degree label

Master [120] en science des données, orientation statistique, à finalité spécialisée

Abstract

In this master thesis, a case study is carried out using air pollution data. The data are analysed and modelled in time and space. Different statistical modelling methods are used in the study. Interpolation methods are applied to the studied data (kriging, spatio-temporal kriging). In particular, a spatio-temporal kriging is performed which combines a multiple linear regression and a spatio-temporal kriging of the regression residuals. The study shows how the spatio-temporal dependence in the data can affect model predictions.