At present, most studies on airport runways focus on icing thickness prediction and temperature prediction,to further improve the safety and efficiency of airport operations, a prediction model for snow thickness on airport runways based on a parallel architecture of Transformer and long short-term memory (LSTM) networks was proposed by integrating meteorological data and runway surface condition monitoring data. The LSTM branch was adopted to extracted the local temporal dynamics of meteorological data and capture short-term contextual relationships, while the Transformer branch was used to accurately captured the nonlinear coupling relationships among meteorological factors through the self-attention mechanism, with suitable weights assigned to different meteorological factors under different conditions. Finally, the different features captured by the two branches are weighted and fused through an adaptive weight module to complete the prediction. Comparative results show that the parallel Transformer-LSTM model achieves satisfactory prediction performance in both single-step and multi-step predictions on two different datasets. Accordingly, snow removal scheduling arrangements can be made by airports based on the prediction results.
FENG Gen-yuan, WANG Hong-liang, HUANG Guo-yong.
Snow Thickness Prediction of Airport Runway Based on Parallel Transformer-LSTM[J].
Science Technology and Engineering, 2026, 26(23): 10021-10030 DOI:10.12404/j.issn.1671-1815.2505528
CuiYanyu, ZhaoQi, ChenYuanyuan, et al. Experimental study on effect of snow on friction characteristics of runway surface[J]. Journal of Civil Aviation, 2023, 7(3): 38-42, 32.
GengTong, ZhangShengkai, XiaoFeng, et al. Comparison and evaluation of snow depth estimation methods for arctic sea ice using satellite altimetry[J]. Geomatics and Information Science of Wuhan University. (2026-07-07)[2026-07-26]. https://doi.org/10.13203/j.whugis20240459.
ChenBin, LiuYue, YinKailang, et al. Runway temperature data mechanism joint prediction based on LSTM under ice and snow[J]. Journal of Beijing University of Aeronautics and Astronautics, 2024, 50(7): 2184-2194.
GaoBo, HaoXiaohua, HeDongcai, et al. Reconstruction of high spatiotemporal resolution snow cover remotesensing range data from multiple sources based on deep learning model: a case study in the Qilian Mountains[J]. National Remote Sensing Bulletin, 2025, 29(4): 867-882.
TaoXingyu, LiuJinbao, LaZhen, et al. Research on snow depth simulation of Crocus model[J]. Journal of Glaciology and Geocryology, 2024, 46(4): 1184-1196.
[16]
HuY X, CheT, DaiL Y, et al. Snow depth fusion based on machine learning methods for the northern hemisphere[J]. Remote Sensing, 2021, 13(7): 1250.
MaLei, HuZhixuan, WeiZhenxun, et al. A dimensionality reduction assessment model for blowing snow disasters on mountain highways based on GA_XGBoost[J]. Journal of Glaciology and Geocryology, 2025, 47(4): 1112-1124.
HuZhidong, WuSong, LuLili. A CLT composite model based prediction method for aeration amount in wastewater treatment[J]. Science Technology and Engineering, 2025, 25(26): 11418-11425.
[21]
YuZ C, LiB. Reinforced concrete beam full response prediction with hybrid feature-orientation transformer-LSTM model[J]. Engineering Structures, 2025, 332: 120040.
LiShiwan, YuanMingdao, XuYunqian, et al. A seepage flow prediction model for earth-rock dams using CNN-LSTM with attention mechanism[J]. Science Technology and Engineering, 2025, 25(21): 9102-9108.
XiangWenqiang, ShaoWei, LuoShaohui, et al. Simulation of soil moisture in permafrost regions of the Qinghai-Tibet Plateau based on LSTM model[J]. Science Technology and Engineering, 2025, 25(31): 13236-13245.
GongXuanlin, TaoQing, SuNa, et al. A recognition method for steady-state visual evoked potential EEG signals based on CNN-CBAM-LSTM[J]. Science Technology and Engineering, 2025, 25(10): 4175-4182.
ZhouZhiwei, TaoQing, SuNa, et al. Lower limb motion recognition based on surface electromyography and a CNN-LSTM fusion model[J]. Science Technology and Engineering, 2025, 25(7): 2841-2848.
PengHuangguo, ChenLiang. A hybrid Transformer gaze estimation model combining multi-scale fusion and attention mechanism[J]. Science Technology and Engineering, 2025, 25(29): 12579-12585.
[32]
ZhouL, ZhangR H. A self-attention-based neural network for three-dimensional multivariate modeling and its skillful ENSO predictions[J]. Science Advances, 2023, 9(10): eadf2827.
LuoGuohui, PengXiaolong, YangChen, et al. Composite time production decline model of shale gas based on adaptive PSO parameter optimization[J]. Science Technology and Engineering. 2025, 25(18): 7583-7589.
ZhuGuangping, LiMeng, WangCheng, et al. Algorithm for pre-modulation of excitation signals using a three-spline interpolation parameter matrix[J]. Journal of Harbin Engineering University, 2025, 46(3): 513-520.