A machine learning approach for evaluating Southern Oceancloud-radiative biases in a global atmosphere model
The evaluation and quantification of Southern Ocean cloud–radiation interactions simulated by climate models are 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...
Main Authors: | , , , , , |
---|---|
Format: | Text |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://doi.org/10.5194/egusphere-2023-531 https://egusphere.copernicus.org/preprints/2023/egusphere-2023-531/ |
id |
ftcopernicus:oai:publications.copernicus.org:egusphere110296 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:egusphere110296 2024-06-23T07:56:55+00:00 A machine learning approach for evaluating Southern Oceancloud-radiative biases in a global atmosphere model Fiddes, Sonya L. Mallet, Marc D. Protat, Alain Woodhouse, Matthew T. Alexander, Simon P. Furtado, Kalli 2024-04-11 application/pdf https://doi.org/10.5194/egusphere-2023-531 https://egusphere.copernicus.org/preprints/2023/egusphere-2023-531/ eng eng doi:10.5194/egusphere-2023-531 https://egusphere.copernicus.org/preprints/2023/egusphere-2023-531/ eISSN: Text 2024 ftcopernicus https://doi.org/10.5194/egusphere-2023-531 2024-06-13T01:23:50Z The evaluation and quantification of Southern Ocean cloud–radiation interactions simulated by climate models are 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 that do not consider the entirety of the Southern Ocean's cloud regimes at once. Furthermore, it is difficult to directly quantify the complex and non-linear role that different cloud properties have on modulating cloud radiative effect. 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 (eXtreme Gradient Boosting) 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 SHAP (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 the liquid water path are 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. Text Southern Ocean Copernicus Publications: E-Journals Southern Ocean |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
The evaluation and quantification of Southern Ocean cloud–radiation interactions simulated by climate models are 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 that do not consider the entirety of the Southern Ocean's cloud regimes at once. Furthermore, it is difficult to directly quantify the complex and non-linear role that different cloud properties have on modulating cloud radiative effect. 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 (eXtreme Gradient Boosting) 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 SHAP (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 the liquid water path are 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. |
format |
Text |
author |
Fiddes, Sonya L. Mallet, Marc D. Protat, Alain Woodhouse, Matthew T. Alexander, Simon P. Furtado, Kalli |
spellingShingle |
Fiddes, Sonya L. Mallet, Marc D. Protat, Alain Woodhouse, Matthew T. Alexander, Simon P. Furtado, Kalli A machine learning approach for evaluating Southern Oceancloud-radiative biases in a global atmosphere model |
author_facet |
Fiddes, Sonya L. Mallet, Marc D. Protat, Alain Woodhouse, Matthew T. Alexander, Simon P. Furtado, Kalli |
author_sort |
Fiddes, Sonya L. |
title |
A machine learning approach for evaluating Southern Oceancloud-radiative biases in a global atmosphere model |
title_short |
A machine learning approach for evaluating Southern Oceancloud-radiative biases in a global atmosphere model |
title_full |
A machine learning approach for evaluating Southern Oceancloud-radiative biases in a global atmosphere model |
title_fullStr |
A machine learning approach for evaluating Southern Oceancloud-radiative biases in a global atmosphere model |
title_full_unstemmed |
A machine learning approach for evaluating Southern Oceancloud-radiative biases in a global atmosphere model |
title_sort |
machine learning approach for evaluating southern oceancloud-radiative biases in a global atmosphere model |
publishDate |
2024 |
url |
https://doi.org/10.5194/egusphere-2023-531 https://egusphere.copernicus.org/preprints/2023/egusphere-2023-531/ |
geographic |
Southern Ocean |
geographic_facet |
Southern Ocean |
genre |
Southern Ocean |
genre_facet |
Southern Ocean |
op_source |
eISSN: |
op_relation |
doi:10.5194/egusphere-2023-531 https://egusphere.copernicus.org/preprints/2023/egusphere-2023-531/ |
op_doi |
https://doi.org/10.5194/egusphere-2023-531 |
_version_ |
1802650311028899840 |