Fog Forecast Experiment of Single Station Based on LVQ Neural Network

The generating and dissolving of fogs are too complex for empirical and linear s ystems methods to forecast and these methods cannot meet the needs of flight tra ining. To meet this end, a new fog predicting model is proposed based on learnin g vector quantization neural network. The forecasting model of fog weather event s is established using sequential forecast idea, adopting principal component an alysis (PCA) and learning vector quantization network too. 186 cases of heavy fo g, mist or fog free weather events on a certain airport is studied. Temperature, pressure, moisture, wind and other elements observed at 08:00, 14:00, and 20:0 0 the day before the foggy weather are selected as prediction factors. Based on Learning Vector Quantization neural network, the prediction model of airport fog gy weather events is established using sequential forecast idea (fog versus fog free, heavy fog versus mist), and the prediction factors can be simplified usi ng the principal component analysis.In the network training process, the model forecasting capability is improved in accordance with fitting accuracy to dynamically adjust neurons scaling paramete rs of the network. Adopting "to stop" technology of the timely termination tra ining in accordance with testing the accuracy, generalization ability of the mod el is effectively improved. Forecasting experiments show that, the proposed mode l can effectively distinguish fog, mist and fog. Both the fitting rate and the f orecasting accuracy are satisfactory so the model is practical.