Open access
Date
2023Type
- Journal Article
ETH Bibliography
yes
Altmetrics
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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000624717Publication status
publishedExternal links
Journal / series
Environmental Data ScienceVolume
Pages / Article No.
Publisher
Cambridge University PressSubject
cirrus clouds; eXplainable AI; explainable machine learning; machine learning; SHAP; Shapley valuesOrganisational unit
03690 - Lohmann, Ulrike / Lohmann, Ulrike
Funding
860100 - innovative MachIne leaRning to constrain Aerosol-cloud CLimate Impacts (EC)
More
Show all metadata
ETH Bibliography
yes
Altmetrics