Uncertainty Quantification

Schematic of the surrogate-based ensemble data assimilation system.

Surrogate-based ensemble data assimilation for reducing uncertainty in large-eddy simulation of microscale pollutant dispersion

This paper introduces and evaluates a novel data assimilation framework for atmospheric pollutant dispersion. The use of a surrogate model reduces the computational burden and makes it possible to inestigate in-depth the system observability.

Reliability diagrams of the surrogate uncertainty estimates.

Uncertainty-aware surrogate modeling for urban air pollutant dispersion prediction

This paper tells the construction and validation of a surrogate model for atmospheric pollutant dispersion. We show that the selected approach is able to embed accurately the uncertainty at stakes.