Wednesday, 13 January 2016
Fifteen years of data from the National Oceanic and Atmospheric Administration Second-Generation Global Medium-Range Ensemble Reforecast (GEFS/R) Dataset was used to develop a statistical model which generates probabilistic predictions of flight rule conditions (FRCs), as determined by cloud ceiling and visibility. Four major airports- KSEA, KDEN, KSFO, and KIAH- were selected for model training and analysis. Numerous statistical model configurations were explored, including the use of several different machine learning algorithms: random forests, gradient boosting, k-nearest neighbors, and support vector machines. Different input model predictors and internal machine learning parameters were also examined and verified through cross-validation to develop skillful forecasts at each station. The final model was then compared with both probabilistic climatology-based forecasts and deterministic operational guidance. Results indicated statistically significantly enhanced skill in both deterministic and probabilistic frameworks from the model trained in this study relative to both operational guidance and climatology at all stations. Probabilistic forecasts also showed substantially higher skill in the framework used than any deterministic forecast. Dew point depression and cloud cover forecast fields from the GEFS/R model were typically found to have the highest correspondence with observed flight rule conditions of the atmospheric fields examined. Often forecast values nearest the prediction station were not found to be the most important flight rule condition predictors, with forecast values along coastlines and immediately offshore, where applicable, often serving as superior predictors. The effect of training data length on model performance was also examined; it was determined that approximately three years of training data from a dynamical model was required for the statistical model to robustly capture the relationships between model variables and observed FRCs.
![](images/flag.png)
![](images/blue_ribbon.png)