CloudCast—Total Cloud Cover Nowcasting with Machine Learning

Abstract Cloud cover plays a critical role in weather prediction and impacts several sectors, including agriculture, solar power generation, and aviation. Despite advancements in numerical weather prediction (NWP) models, forecasting total cloud cover remains challenging due to the small-scale nature of cloud formation processes. In this study, we introduce CloudCast, a convolutional neural network (CNN) based on the U-Net architecture, designed to predict total cloud cover (TCC) up to 5 h ahead. Trained on 5 years of satellite data, CloudCast significantly outperforms traditional NWP models and optical flow methods. Compared to a reference NWP model, CloudCast achieves a 24% lower mean absolute error and reduces multicategory prediction errors by 46%. The model demonstrates strong performance, particularly in capturing the large-scale structure of cloud cover in the first few forecast hours, though later predictions are subject to blurring and underestimation of cloud formation. Model selection was performed using sensitivity experiments which identified the optimal input features and loss functions, with mean absolute error (MAE)-based models performing the best. CloudCast has been integrated into the Finnish Meteorological Institute’s operational nowcasting system, where it improves cloud cover forecasts used by public and private sector clients. While CloudCast is limited by a relatively short skillful lead time of about 3 h, future work aims to extend this through more complex network architectures and higher-resolution data. CloudCast code is available online ( https://github.com/fmidev/cloudcast ).