Wind Speed Forecasting of High Plateau Airport Based on Informer

The wind is a critical meterological factor that affects flight operations. Accurate medium-to-short-term wind speed forecasting will contribute to an efficient flight departure system, which is significant to civil aviation industry. In this paper, a novel model based on Informer algorithm is proposed to improve the capacity of wind speed forecasting in high plateau airport. The proposed method can achieve more remarkable performance than traditional algorithms due to the multidimensional time-scale relationship between meteorological factors can be captured more precisely by Informer algorithm. To estimate the performance of the proposed model, several state-of-the-art algorithms for time-series forecasting are conducted as benchmarks. Experiment result demonstrate that the proposed model shows the optimal effect in terms of the mean square error, mean absolute error, root mean square error and mean absolute percentage error for each forecasting horizon.