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:

There are many uncertainties in radiation fog forecast. Continuous effort is being made to improve the forecast. A supplementary and increasingly popular approach to numerical weather forecast is the forecast with machine learning (ML) algorithms. While numerical weather forecast is based on mathematical models with partial differential equations, ML algorithms take a more heuristic approach. The latter strategy calls for three steps. Precise data preprocessing is the initial step. This implies that after preprocessing, the dataset must contain the forecast-relevant information in a way that the algorithm can learn from it. This is not a trivial step because it necessitates a thorough understanding of the fundamental principles underlying radiation fog. Even when the relevant information is contained in the data, it is not always evident, especially in severely unbalanced fog datasets. The best strategy to achieve a pleasing result may therefore not be to simply feed the algorithm all the data and variables that are available. So that the appropriate dynamics may be detected by the algorithm, the data and information should be adjusted accordingly. The second step is the data splitting into training, validation and test datasets. The ability to predict fog is driven by the temporally linked process that describes the ongoing change in atmospheric state but in order to guarantee constant independence between the training, validation and test dataset, the data splitting method must consider this temporally linked information between the individual datapoints. Otherwise, the algorithm’s forecast accuracy can be based on the temporally correlated information content of the individual data points. The third step is the interpretation of the model scores. When looking at the forecast score alone, it is a very abstract number that does not directly allow a statement about the forecast performance of the model. In order to evaluate the model performance, two baselines are of relevance: algorithm complexity and dataset complexity. A baseline for algorithm complexity justifies the chosen algorithm and also classifies the model performance. A baseline for dataset complexity also classifies the model performance and enables a better comparability of different datasets. Following these principles, our current objective is to improve the ML based fog forecast with XGBoost for a forecasting period up to four hours for the station in Linden-Leihgestern (Germany). The training and evaluation are based on the Expanding Window Approach (Vorndran et al. 2022) that considers the autocorrelation of a fog time series and maintains the temporal order during both training and evaluation. The evaluation is based on a score for each of the following categories: Overall performance, fog formation, and fog dissipation. The results are set in relation to different baselines to evaluate the performance and the dataset complexity. Building on this scheme, newly preprocessed data led to an improvement in the prediction of radiation fog for the station in Linden-Leihgestern. We will present the most recent findings from our research.

Abstract:

This study investigates the temporal dynamics of the drop size distribution (DSD) and its influence on the relationship between the liquid water content (LWC) and the radar reflectivity (Z) in fogs. Data measured during three radiation fog events at the Marburg Ground Truth and Profiling Station in Linden-Leihgestern, Germany, form the basis of this analysis. Specifically, we investigated the following questions: (1) Do the different fog life cycle stages exhibit significantly different DSDs? (2) Is it possible to identify characteristic DSDs for each life cycle stage? (3) Is it possible to derive reliable Z-LWCrelationships by means of a characteristic DSD? The results showed that there were stage-dependent differences in the fog life cycles, although each fog event was marked by unique characteristics, and a general conclusion about the DSD during the different stages could not be made. A large degree of variation within each stage also precludes the establishment of a representative average spectrum.

Abstract:

An objective classification of radiation fog in distinct evolutionary stages during its life cycle based on reliable criteria is essential for various applications, for example for numerical fog modelling and fog forecasting. However, there have been  up to now  merely qualitative approaches for the distinction of different evolutionary stages in radiation fog. Measurements of the microphysical fog properties with an optical particle counter obtained from droplet measurement technologies together with recordings of the horizontal visibility (VIS) are statistically analyzed to determine individual evolutionary stages of radiation fog with consistent microphysical properties. The developed three-stage approach is based on a statistical change point analysis of the double sum curves of the VIS, the liquid water content, the droplet concentration and the mean radius of the drop size distributions. It could be shown that each of the three recorded radiation fog occurrences could be split into three consecutive phases from formation to dissipation, regardless whether the VIS or the microphysical properties were considered. Having featured consistent microphysical patterns, it could be assumed that the three separated phases of the single fog occurrence could be aggregated for radiation fog. Although this classification is statistically reliable, the dataset still has to be extended for a generalization concerning the separated evolutionary stages.