Predicting the Effect of European Air Traffic on Cirrus Cloud Cover

TL;DR

This study investigates how European air traffic influences cirrus cloud cover by combining satellite data and machine learning models, revealing the impact of aviation on cloud formation under different atmospheric saturation conditions.

Contribution

It introduces an integrated framework combining satellite data and machine learning to assess aviation's effect on cirrus clouds, considering meteorological factors and saturation levels.

Findings

A correlation between air traffic and cirrus cloud cover was identified.

Meteorology significantly influences cirrus formation and lifetime.

Different impacts were observed in saturated versus sub-saturated air.

Abstract

The purpose of this study is to provide more insight into the role of anthropogenic cirrus formation through air traffic, by investigating the high-density European airspace over a period spanning several recent years including the start of the COVID-19 pandemic (2015-2020). Several data resources are combined, exploiting the strengths of each product within an all-encompassing framework on a high spatio-temporal resolution. Data from METEOSAT SEVIRI have been combined and validated with CALIPSO's CALIOP data to deduce temporal cirrus cloud cover variability over a rectangular region bound by (10 degrees W - 35 degrees N) and (40 degrees E - 60 degrees N). Cirrus clouds are correlated with air traffic. Meteorology was incorporated into the analysis as it is of major influence on the formation and lifetime of cirrus. Both a logistic regression model and a Random Forest model were built to assess cirrus cloud cover variability imposed by meteorology. The impact of aviation on cirrus cover in 1) super-saturated an 2) sub-saturated air have been evaluated separately. A description of all the datasets involved, including the main research methodology and main results, are presented.