Preprints
https://doi.org/10.5194/egusphere-2023-531
https://doi.org/10.5194/egusphere-2023-531
25 Jul 2023
 | 25 Jul 2023

A machine learning approach for evaluating Southern Oceancloud-radiative biases in a global atmosphere model

Sonya L. Fiddes, Marc D. Mallet, Alain Protat, Matthew T. Woodhouse, Simon P. Alexander, and Kalli Furtado

Abstract. The evaluation and quantification of Southern Ocean cloud-radiation interactions simulated by climate models is essential in understanding the sources and magnitude of the radiative bias that persists in climate models for this region. To date, most evaluation methods focus on specific synoptic or cloud type conditions and are unable to quantitatively define the impact of cloud properties on the radiative bias whilst considering the system as a whole. In this study, we present a new method of model evaluation, using machine learning, that can at once identify complexities within a system and individual contributions.

To do this, we use an XGBoost model to predict the radiative bias within a nudged version of the Australian Community Climate and Earth System Simulator – Atmosphere-only Model, using cloud property biases as predictive features. We find that the XGBoost model can explain up to 55 % of the radiative bias from these cloud properties alone. We then apply SHapley Additive exPlanations feature importance analysis to quantify the role each cloud property bias plays in predicting the radiative bias. We find that biases in liquid water path is the largest contributor to the cloud radiative bias over the Southern Ocean, though important regional and cloud-type dependencies exist. We then test the usefulness of this method in evaluating model perturbations and find that it can clearly identify complex responses, including cloud property and cloud-type compensating errors.

Sonya L. Fiddes et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2023-531', Anonymous Referee #1, 02 Sep 2023
  • RC2: 'Comment on egusphere-2023-531', Anonymous Referee #2, 19 Sep 2023

Sonya L. Fiddes et al.

Data sets

ACCESS-AM2 Southern Ocean cloud and radiation data and code for SHAP analysis Sonya Fiddes https://doi.org/10.5281/zenodo.7196622

Sonya L. Fiddes et al.

Viewed

Total article views: 300 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
226 65 9 300 1 2
  • HTML: 226
  • PDF: 65
  • XML: 9
  • Total: 300
  • BibTeX: 1
  • EndNote: 2
Views and downloads (calculated since 25 Jul 2023)
Cumulative views and downloads (calculated since 25 Jul 2023)

Viewed (geographical distribution)

Total article views: 281 (including HTML, PDF, and XML) Thereof 281 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 30 Sep 2023
Download
Short summary
This study uses XGBoost, a machine learning algorithm, to predict the simulated Southern Ocean shortwave radiation bias in the ACCESS model. We used cloud property biases within ACCESS as predictors, and can explain up to 55 % of the variance in the shortwave radiation bias. We then used a novel feature importance analysis to quantify the role that each cloud bias plays in predicting the radiative bias, laying the foundations for better understanding future developments of Earth System Models.