The ground delay program (GDP) is a commonly used tool in air traffic management. Developing a departure flight delay prediction model based on GDP can aid airlines and control authorities in better flight planning and adjusting air traffic control strategies. A model that combines the improved sparrow search algorithm (ISSA) and Multilayer Perceptron (MLP) has been proposed to minimise prediction errors. The ISSA uses tent chaotic mapping, dynamic adaptive weights, and Levy flight strategy to enhance the algorithm’s accuracy for the sparrow search algorithm (SSA). The MLP model’s hyperparameters are optimised using the ISSA to improve the model’s prediction accuracy and generalisation performance. Experiments were performed using actual GDP-generated departure flight delay data and compared with other machine learning techniques and optimisation algorithms. The results of the experiments show that the mean absolute error (MAE) and root mean square error (RMSE) of the ISSA-MLP model are 16.8 and 24.2, respectively. These values are 5.61%, 6.3% and 1.8% higher in MAE and 4.4%, 5.1% and 2.5% higher in RMSE compared to SSA, particle swarm optimisation (PSO) and grey wolf optimisation (GWO). The ISSA-MLP model has been verified to have good predictive and practical value.

Effective ground delay programs (GDP) are needed to intervene when there are bad weather or airport capacity issues. This paper proposes a new methodology for predicting the incidence of effective ground delay programs by utilizing machine learning techniques, which can improve the safety and economic benefits of flights. We use the combination of local weather and flight operation data along with the ATM airport performance (ATMAP) algorithm to quantify the weather and to generate an ATMAP score. We then compared the accuracy of three machine learning models, Support Vector Machine, Random Forest, and XGBoost, to estimate the probability of GDPs. The results of the weather analysis, performed by the ATMAP algorithm, indicated that the ceiling was the most critical weather factor. Lastly, we used two linear regression models (ridge and LASSO) and a non-linear regression model (decision tree) to predict departure flight delays during GDP. The predictive accuracy of the regression models was enhanced by an increase in ATMAP scores, with the decision tree model outperforming the other models, resulting in an improvement of 8.8% in its correlation coefficient ($R^2$).

Air traffic system experiences more and more severe jams. Bad weather conditions add to the uncertainties. Maintaining the precondition of safety, the volume of inbound traffic and outbound traffic were simulated by scientifically allocating the holding time of aircraft both in the air as well as on ground. Minimizing the overall cost of the system is also the focus of the research. The paper also puts forward the improved ATFM holding model for uncertainties along with minimum overall holding cost (including the delay cost both in the air and on the ground) as the target function. Applying this improved model to Guangzhou airport, and taking into account both inbound and outbound flights, we find out the system value maximized under optimized strategy. The result of this model can also give the number of inbound/outbound flights at each time period, which help air traffic controllers in making decisions.

The improvement of the accuracy and real-time performance of sector traffic flow prediction is of great significance to air traffic management decision-making. Sectors operate under complex spatial structures and time dimensions. Some neural network methods adopt sequence order to gradually transmit information, which makes it difficult to achieve complete parallel training. Not only does it take too long to train, resulting in low training efficiency, but it is also easy to lose the effective correlation information of long sequence data. To this end, a sector traffic flow prediction method based on attention-improved graph convolutional transformer (AGC-T) network is proposed to improve the current traffic prediction problem for sectors. First, the graph structure information and historical traffic data of the sector are input into the graph convolutional network improved based on the attention mechanism to fully capture the spatial relationship with sectors as nodes. Combined with the transformer’s multi-head self-attention mechanism, it can directly focus on the sequence data at any position without gradually transmitting information. Not only does it improve efficiency through parallel training, but the encoder-decoder structure can also mine the information features in the traffic data, focus on the traffic data features of key nodes and more accurately predict sector traffic. Finally, the operation traffic data of sectors in typical areas in central and southern China are taken as an example to analyse the model. The results show that compared with other prediction models, the AGC-T model $RSME$ , $MAE$ and ${R^2}$ are 45.16%, 46.78% and 2.63% higher than the GCN model in the 15-min single-day traffic prediction task, and 41.74%, 35.27% and 1.20% higher than the GRU model. In the single-week traffic prediction task, $RSME$ , $MAE$ and ${R^2}$ are 37.12%, 40.54% and 3.55% higher than the GCN model, and 35.15%, 35.17% and 0.65% higher than the GRU model, respectively, showing better prediction performance. This study will help air navigation service providers (ANSP) to make sector traffic predictions more accurately, thereby implementing more scientific and reasonable traffic management measures.