Demystifying the complex nature of stratocumulus clouds with machine learning

Stratocumulus clouds play a key role in the Earth's energy budget, but large uncertainties persist in model predictions of how they will respond to anthropogenic emissions and warming. This is because stratocumulus clouds are complex systems made up of many interacting processes that present challenges for modellers. A machine learning technique, called statistical emulation, is demonstrated here to be a vital tool for cloud modelling and reducing these large uncertainties.