Abstract:
Recovering the time profile and even the source location of a pollutant from sparse measurements requires a careful approach, especially when no additional prior information is available. In this talk, I will introduce two methods, both built on a commonly used linear model with a source–receptor sensitivity (SRS) matrix: one for estimating the spatio-temporal source of emissions, and the other for correcting the SRS coefficients.
The first method is based on deep learning: it leverages the structure of a neural network as prior information to obtain a meaningful estimate of the spatio-temporal source term. The second method corrects a linear model describing particle transport by introducing a prior in the form of a Gaussian process. The main advantage of this prior is its ability to interpolate between measurements and provide predictions at new locations.
What is the Joint Oslo Seminar (JOS):
- Atmospheric and climate sciences have a stronghold in Oslo among the four institutions University of Oslo, the Meteorological Institute, CICERO and NILU.
- This joint seminar invites renowned international experts to contribute to an informal series of lectures, meant to create interaction with the Oslo atmospheric and climate science community on recent highlights and analysis in the field.
- Normally seminars will be held on Thursdays (12:15 pm -1pm).