Laboratory for
Climatology and Remote Sensing

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.

Abstract:

Two schemes for the determination of fog horizontal visibility using AVHRR data both, day and night, are presented. Ground truth has been performed by the comparison of calculated visibilities and simultaneous transmissometer measurements. The daytime approach is based on the calculation of fog albedo from AVHRR #1 and the relation of fog optical depth and geometrical thickness to spectral extinction and horizontal visibility. The mean deviation between observed and calculated visibilities is about 56 m. The nighttime approach uses the relation between fog and air temperature derived from AVHRR # 4 and 5 and a simple model for the approximation of the fog droplet distribution. The resulting fog extinction is directly related to horizontal visibility. Because fog optical depth is not available at night, the calculation of horizontal visibility using the nighttime approach is only valid if fog extinction is nearly homogeneous over the whole fog layer. Mean deviations between observed and calculated visibilities therefore slightly increase to about 61 m.