ACCESS-AM2 Southern Ocean cloud and radiation data and code for SHAP analysis

The ACCESS-AM2 (Australian Community Climate and Earth-System Simulator - Atmospheric Model Version 2) and SHAP analysis code and data used for the study described in Fiddes et al. (2024) 'A machine learning approach for evaluating Southern Ocean cloud-radiative biases over the Southern Ocean in a global atmosphere model' accepted in Geoscientific Model Development Included files: - code.zip, inc: - pre-process_modis.ipynb: process the modis data, described in Fiddes et al. 2022 (https://doi.org/10.5194/acp-22-14603-2022) - pre-process.ipynb: organises model and modis data for analysis. Produces the files: COSP_vars_MODIS_2015-2019.nc, COSP_vars_cg207_2015-2019.nc and COSP_vars_bx400_2015-2019.nc - run_XGBoost+SHAP_control.ipynb: run the XGBoost model and SHAP analysis for the control run (bx400). Produces the files: SHAP_values_SWCRE_2015-2019_bx4002.nc, XGBoost_predicted_SWCRE_2015-2019_bx4002.nc, SHAP_interactions_bx400.nc - run_XGBoost+SHAP_ice.ipynb: run the XGBoost model and SHAP analysis for the ice experiment run (cg207). Produces the files: SHAP_values_SWCRE_2015-2019_cg2072.nc, XGBoost_predicted_SWCRE_2015-2019_cg2072.nc - analysis+plots_ML.ipynb: plots and stats presented in paper - COSP_vars_MODIS_2015-2019.nc - COSP_vars_cg207_2015-2019.nc - COSP_vars_bx400_2015-2019.nc - SHAP_values_SWCRE_2015-2019_bx4002.nc - SHAP_values_SWCRE_2015-2019_cg2072.nc - XGBoost_predicted_SWCRE_2015-2019_cg2072.nc - XGBoost_predicted_SWCRE_2015-2019_bx4002.nc - SHAP_interaction_bx400.nc The cloud types used in this work can be found at https://doi.org/10.5281/zenodo.6004061本数据集包含用于Fiddes等人2024年被《Geoscientific Model Development》（《地球科学模式发展》）收录的研究"A machine learning approach for evaluating Southern Ocean cloud-radiative biases over the Southern Ocean in a global atmosphere model"（《全球大气模式中基于机器学习方法评估南大洋云辐射偏差》）所用的ACCESS-AM2（Australian Community Climate and Earth-System Simulator - Atmospheric Model Version 2，澳大利亚社区气候与地球系统模拟器——大气模式版本2）以及SHAP分析代码与数据。 包含文件： - code.zip，内含： - pre-process_modis.ipynb：用于处理MODIS数据，相关说明见Fiddes等人2022年的研究（https://doi.org/10.5194/acp-22-14603-2022） - pre-process.ipynb：整理用于分析的模式与MODIS数据，生成以下文件：COSP_vars_MODIS_2015-2019.nc、COSP_vars_cg207_2015-2019.nc与COSP_vars_bx400_2015-2019.nc - run_XGBoost+SHAP_control.ipynb：针对对照试验（bx400）运行XGBoost模型与SHAP分析，生成以下文件：SHAP_values_SWCRE_2015-2019_bx4002.nc、XGBoost_predicted_SWCRE_2015-2019_bx4002.nc与SHAP_interactions_bx400.nc - run_XGBoost+SHAP_ice.ipynb：针对海冰试验（cg207）运行XGBoost模型与SHAP分析，生成以下文件：SHAP_values_SWCRE_2015-2019_cg2072.nc、XGBoost_predicted_SWCRE_2015-2019_cg2072.nc - analysis+plots_ML.ipynb：用于生成论文中展示的图表与统计结果 - COSP_vars_MODIS_2015-2019.nc - COSP_vars_cg207_2015-2019.nc - COSP_vars_bx400_2015-2019.nc - SHAP_values_SWCRE_2015-2019_bx4002.nc - SHAP_values_SWCRE_2015-2019_cg2072.nc - XGBoost_predicted_SWCRE_2015-2019_cg2072.nc - XGBoost_predicted_SWCRE_2015-2019_bx4002.nc - SHAP_interaction_bx400.nc 本研究所用的云类型数据可通过https://doi.org/10.5281/zenodo.6004061 获取。