Averaging Atmospheric Gas Concentration Data using Wasserstein Barycenters

Mathieu Barré (1) , Clément Giron (2) , Matthieu Mazzolini (2) , Alexandre d'Aspremont (3, 4, 1, 5)

1 SIERRA - Statistical Machine Learning and Parsimony
2 Kayrros
3 LIENS - Laboratoire d'informatique de l'école normale supérieure
4 CNRS - Centre National de la Recherche Scientifique
5 PSL - Université Paris Sciences et Lettres

Hyperspectral satellite images report greenhouse gas concentrations worldwide on a daily basis. While taking simple averages of these images over time produces a rough estimate of relative emission rates, atmospheric transport means that simple averages fail to pinpoint the source of these emissions. We propose using Wasserstein barycenters coupled with weather data to average gas concentration data sets and better concentrate the mass around significant sources.

Domaines: Machine Learning [stat.ML]; Recherche opérationnelle [math.OC]

Mathieu Barré, Clément Giron, Matthieu Mazzolini, Alexandre d'Aspremont. Averaging Atmospheric Gas Concentration Data using Wasserstein Barycenters. 2021. ⟨hal-03165617⟩