Back to Search Start Over

Understanding cirrus clouds using explainable machine learning

Understanding cirrus clouds using explainable machine learning

Authors :
Kai Jeggle
David Neubauer
Gustau Camps-Valls
Ulrike Lohmann
Source :
Environmental Data Science, Vol 2 (2023)
Publication Year :
2023
Publisher :
Cambridge University Press, 2023.

Abstract

Cirrus clouds are key modulators of Earth’s climate. Their dependencies on meteorological and aerosol conditions are among the largest uncertainties in global climate models. This work uses 3 years of satellite and reanalysis data to study the link between cirrus drivers and cloud properties. We use a gradient-boosted machine learning model and a long short-term memory network with an attention layer to predict the ice water content and ice crystal number concentration. The models show that meteorological and aerosol conditions can predict cirrus properties with R2 = 0.49. Feature attributions are calculated with SHapley Additive exPlanations to quantify the link between meteorological and aerosol conditions and cirrus properties. For instance, the minimum concentration of supermicron-sized dust particles required to cause a decrease in ice crystal number concentration predictions is 2 × 10−4 mg/m3. The last 15 hr before the observation predict all cirrus properties.

Details

Language :
English
ISSN :
26344602
Volume :
2
Database :
Directory of Open Access Journals
Journal :
Environmental Data Science
Publication Type :
Academic Journal
Accession number :
edsdoj.4d041b0346ae4350a3ab8f20327ab65d
Document Type :
article
Full Text :
https://doi.org/10.1017/eds.2023.14