Recent  

Uncertainty with respect to cloud phases over the Southern Ocean and Arctic marine regions leads to large uncertainties in the radiation budget of weather and climate models. This study investigates the phases of low-base and mid-base clouds using satellite-based remote sensing data. A comprehensive analysis of the correlation of cloud phase with various parameters, such as temperature, aerosols, sea ice, vertical and horizontal cloud extent, and cloud radiative effect, is presented.

Climate models are crucial for predicting climate change in detail. This paper proposes a balanced approach to improving their accuracy by combining traditional process-based methods with modern artificial intelligence (AI) techniques while maximizing the resolution to allow for ensemble simulations. The authors propose using AI to learn from both observational and simulated data while incorporating existing physical knowledge to reduce data demands and improve climate prediction reliability.