| Abstrakt: |
In this study, we evaluated the performance of machine learning (ML) models (XGBoost) in predicting low‐cloud fraction (LCF), compared to two generations of the community atmospheric model (CAM5 and CAM6) and ERA5 reanalysis data, each having a different cloud scheme. ML models show a substantial enhancement in predicting LCF regarding root mean squared errors and correlation coefficients. The good performance is consistent across the full spectrums of atmospheric stability and large‐scale vertical velocity. Employing an explainable ML approach, we revealed the importance of including the amount of available moisture in ML models for representing spatiotemporal variations in LCF in the midlatitudes. Also, ML models demonstrated marked improvement in capturing the LCF variations during the stratocumulus‐to‐cumulus transition (SCT). This study suggests ML models' great potential to address the longstanding issues of "too few" low clouds and "too rapid" SCT in global climate models. Plain Language Summary: Low clouds impose a strong radiative cooling effect on Earth's climate. Predicting low‐cloud fraction (LCF) is, however, challenging in global climate models (GCMs), partly due to some deficiencies in cloud parameterization schemes. Machine learning (ML) models might fill this gap as it is recognized as an efficient, economical, and accurate method to make predictions. In this study, we find that ML models (XGBoost) exhibit superior proficiency in predicting LCF regarding root mean squared errors and correlation coefficients compared to two generations of the community atmospheric model (CAM5 and CAM6) and ERA5 reanalysis data, each having a different cloud scheme. This improvement helps address one important issue of "too few" low clouds in GCMs. Furthermore, ML models demonstrate marked improvement in representing LCF variations when stratocumulus clouds transition to cumulus clouds, as opposed to too rapid decreases in LCF simulated by two CAMs and ERA5. Such findings testify to the unique role of ML models in refining the parameterization of LCF within GCMs. Key Points: Machine learning (ML) models substantially improve "too few" low‐cloud problems in the subtropics compared to traditional cloud schemesThey also show marked improvement in representing low‐cloud fraction (LCF) variations during the stratocumulus‐to‐cumulus transitionIncluding the effect of moisture source in ML models is crucial to representing spatiotemporal variations in LCF in the midlatitudes [ABSTRACT FROM AUTHOR] |
Plný text