An aerosol classification scheme for global simulations using the K-means machine learning method

Li, Jingmin; Hendricks, Johannes; Righi, Mattia; Beer, Christof G.

doi:https://doi.org/10.5194/gmd-15-509-2022

Articles | Volume 15, issue 2

https://doi.org/10.5194/gmd-15-509-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-15-509-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 15, issue 2

Methods for assessment of models

|

25 Jan 2022

Methods for assessment of models |

| 25 Jan 2022

An aerosol classification scheme for global simulations using the K-means machine learning method

Jingmin Li, Johannes Hendricks, Mattia Righi, and Christof G. Beer

Supplement

https://doi.org/10.5194/gmd-15-509-2022-supplement

Data sets

Model simulation data used in "Modelling mineral dust emissions and atmospheric dispersion with MADE3 in EMAC v2.54" (Beer et al., Geosci. Model Dev., 2020) Christof Gerhard Beer https://doi.org/10.5281/zenodo.3941462

Model code and software

Cluster analysis data and code for global aerosol simulations using the K-means machine learning method Jingmin Li https://doi.org/10.5281/zenodo.5582338

Short summary

The growing complexity of global aerosol models results in a large number of parameters that describe the aerosol number, size, and composition. This makes the analysis, evaluation, and interpretation of the model results a challenge. To overcome this difficulty, we apply a machine learning classification method to identify clusters of specific aerosol types in global aerosol simulations. Our results demonstrate the spatial distributions and characteristics of these identified aerosol clusters.