Meta-modelling of carbon fluxes from crop and grassland multi-model outputs

Abstract. We evaluated four stacking-based meta-models – Multiple Linear Regression, Random Forest, XGBoost, and XGBoost with environmental covariates (XGB+) – against the multi-model median (MMM) and best individual process-based models for gross primary production (GPP), ecosystem respiration (RECO) and net ecosystem exchange (NEE) at two cropland and two grassland sites. All meta-models were associated with improved RMSE, bias and correlation, with explained variance gains of ~10–38.5 % over MMM, largest for RECO in croplands and smallest for NEE in grasslands. Bias was nearly eliminated except at one cropland site. SHAP analysis showed that diverse individual models, not always the top performers, contributed most, and that temperature – especially for RECO in croplands and NEE in grasslands – was the dominant environmental driver, while precipitation had minor effects. These findings highlight the predictive and diagnostic advantages of stacking-based approaches over equal-weight MMM, with potential applications across agroecosystem, Earth system and environmental model ensembles.