Michael Mommert

Computer Vision and Earth Observation


18 November 2021

Estimation of Surface Level NO2 from Remote Sensing Data

Air pollution is a major health issue and often also contributes to climate change. Measuring air pollution is costly and therefore only available in some countries. We investigated whether freely available remote sensing data can be utilized to estimate air pollution on the surface level.

deep learning remote sensing pollution research

Estimation of Surface Level NO2 from Remote Sensing Data

Exposure to air pollution has been shown to lead to adverse health effects. A major air pollutant is NO2, which, at the surface level, directly affects human health, and, at higher elevations, contributes to acidic rain and represents a precursor to greenhouse gases. While NO2 column densities in the atmosphere can be measured with satellite observations as provided by Sentinel-5P, it requires in-situ measurements from ground stations to measure NO2 concentrations on the surface level, which is relevant to human exposure.

Our student Linus Scheibenreif investigated whether it would be possible to approximate surface level NO2 from remote sensing observations only, providing a tool to estimate human exposure to NO2 on a useful spatial and temporal scale. In his two publications, Linus showed that

Exemplary NO2 predictions based on Sentinel-2 and Sentinel-5P input data from Scheibenreif et al. 2021b.
Exemplary NO2 predictions based on Sentinel-2 and Sentinel-5P input data from Scheibenreif et al. 2021b.

Learn more about Linus’ projects in these blog articles: A Novel Dataset for the Prediction of Surface NO2 Concentrations from Remote Sensing Data and Estimation of Air Pollution with Remote Sensing Data: Revealing Greenhouse Gas Emissions from Space.