Abstract:
Accurate forecasts of radiation fog are an objective of significant relevance due to its impact on traffic, aviation, and transportation. This
study will explore the adaptation and enhancement of a previously developed Machine Learning-based nowcasting framework for
radiation fog events. The objective is to explore the expansion potential to a spatial scale and model accuracy improvements through
application at three distinct weather station locations that experience radiation fog. Further, the effectiveness of Numerical Weather
Prediction (NWP) data as additional predictor variable source on model performance will be assessed. This will be performed through
integration of datasets from German Weather Service (DWD) stations, Meteosat Second Generation (MSG) channel properties and
regional reanalysis variables from COSMO NWP model. Distinct model variants based on different dataset combinations (Station,
MSG+COSMO, Station+MSG+COSMO, Visibility-Only) will be evaluated. Using eXtreme Gradient Boosting (XGBoost) algorithm,
the framework forecasts absolute visibility with 60-minute lead time. A persistence model serves as benchmark. Performance will be
assessed using scoring metrics (Accuracy, Correlation, Percentage bias, Mean Absolute Error) across the full visibility range and three
visibility threshold bounds (2 km, 1.1 km, 0.4 km). Temporal accuracy of fog formation and dissipation will be determined through
evaluation of fog formation and dissipation time shifts. XGBoost models mostly outperform PM, with tendencies of
Station+MSG+COSMO variant performing best and MSG+COSMO variant worst. Prediction difficulties arise in the 0.4 km threshold
segment due to measurement resolution limitations and value imbalance of visibility data. The model variants reliably predict fog event
transitions, with the majority forecasted with deviations < 30 minutes and only few events overseen. A consistent tendency towards
delayed prediction is observed. Variability in model performances across station locations suggests that small-scale environmental
characteristics contribute to different model robustness at distinct sites. The results indicate strong potential for further spatial framework
extension. COSMO variables partially contribute to improved model performance. The framework marks a solid foundation for future
exploitation.
