Articles | Volume 15, issue 3
https://doi.org/10.5194/amt-15-721-2022
https://doi.org/10.5194/amt-15-721-2022
Research article
 | 
09 Feb 2022
Research article |  | 09 Feb 2022

Automated detection of atmospheric NO2 plumes from satellite data: a tool to help infer anthropogenic combustion emissions

Douglas P. Finch, Paul I. Palmer, and Tianran Zhang

Data sets

Copernicus Sentinel-5P, TROPOMI Level 2 Nitrogen Dioxide total column products European Space Agency https://doi.org/10.5270/S5P-s4ljg54

ODIAC Fossil Fuel CO2 Emissions Dataset T. Oda and S. Maksyutov https://doi.org/10.17595/20170411.001

The New VIIRS 375 m active fire detection data product: algorithm description and initial assessment (https://firms.modaps.eosdis.nasa.gov/download/) W. Schroeder, P. Oliva, L. Giglio, and I. A. Csiszar https://doi.org/10.1016/j.rse.2013.12.008

Download
Short summary
We developed a machine learning model to detect plumes of nitrogen dioxide satellite observations over 2 years. We find over 310 000 plumes, mainly over cities, industrial regions, and areas of oil and gas production. Our model performs well in comparison to other datasets and in some cases finds emissions that are not included in other datasets. This method could be used to help locate and measure emission hotspots across the globe and help inform climate policies.