An Airspace Capacity Estimation Model based on Spatio-Temporal Graph Convolutional Networks Considering Weather Impact

Estimating airspace capacity under the impact of severe weather is a crucial method to guarantee efficiency and safety of air traffic operation. It is also of vital importance to understand the spatial and temporal dependencies of adjacent airspace in the process of estimation. Therefore, in this paper, considering this spatio-temporal dependencies, a two-step airspace capacity estimation method is proposed to evaluate terminal areas' capacity including airport and terminal sectors. The first step is to translate different types of meteorological conditions into operation features depending on the type of target airspace. Maxflow/Mincut theorem and Gradient Boosting Regression are adopted for sectors and airports, respectively. Based on the extracted features, an improved Spatio-temporal Graph Convolution Networks via Initial residual (STGCNI) is developed aiming to fit the characteristics in air traffic field. Finally, through experiments with real data of Chengdu Terminal Area (ZUUUAP), both the validity and enhanced estimation accuracy of the method are verified by comparisons with other models, which exclude spatial and temporal characteristics.