Examined in this work were data sets of Kunsan surface observations, upstream upper air data, sea surface temperatures over the Yellow Sea, and other model analysis data over the Yellow Sea. A complete ten year period of record was examined for inclusion into data mining models to find predictive patterns. The data were first examined using standard statistical regression techniques, followed by classification and regression tree analysis (CART) for exploring possible concealed predictors. Regression revealed weak relationships between the target variable (sea fog) and upper air predictors, with stronger relationships between the target and sea surface temperatures. CART results yielded several relationships between the target and upstream upper air predictors. The results of the regression and CART data mining analyses are summarized as forecasting guidelines to aid forecasters in predicting the evolution of sea fog events and advection over the area.
Supplementary URL: