| 刊名 | Meteorological and Environmental Research |
| 作者 | Tianhang ZHANG, Changqi YANG, Fei YAN, Shanshan HU, Xuening WANG |
| 作者单位 | Civil Aviation Flight University of China, Civil Aviation Flight University of China, Guanghan 618399, China |
| DOI | 10.19547/j.issn2152-3940.2025.06.010 |
| 年份 | 2025 |
| 刊期 | 6 |
| 页码 | 39~44 |
| 关键词 | SVR algorithm; High plateau airport; Prediction of wind speed |
| 摘要 | Prediction of wind speed at high plateau airports can not only provide certain theoretical basis for the safe and efficient operation of the airports, but also save cost and time for their flight scheduling. In this paper, based on the data of average wind speed and related meteorological factors at the meteorological station of Lhasa Gonggar airport from 1964 to 2019, a prediction model of wind speed was constructed based on the support vector regression (SVR) algorithm. After the analysis of correlations between various meteorological features, significant features were selected by the random forest algorithm, thereby further improving the prediction performance of the model. The results indicate that both visibility and temperature having high correlations with wind speed are key features determining the final accuracy of the prediction model. Meanwhile, compared with other machine learning algorithms, the SVR algorithm represents more highlighted prediction performance for small sample data. |
