This paper proposes a new methodology for predicting aggregate flight departure delays in airports by exploring supervised learning methods. Individual flight data and meteorological information were processed to obtain four types of airport-related aggregate characteristics for prediction modeling. The expected departure delays in airports is selected as the prediction target while four popular supervised learning methods: multiple linear regression, a support vector machine, extremely randomized trees and LightGBM are investigated to improve the predictability and accuracy of the model. The proposed model is trained and validated using operational data from March 2017 to February 2018 for the Nanjing Lukou International Airport in China. The results show that for a 1-h forecast horizon, the LightGBM model provides the best result, giving a 0.8655 accuracy rate with a 6.65 min mean absolute error, which is 1.83 min less than results from previous research. The importance of aggregate characteristics and example validation are also studied.

Flow corridors are a new class of trajectory-based airspace which derives from the next generation air transportation system concept of operations. Reducing the airspace complexity and increasing the capacity are the main purposes of the en-route corridor. This paper analyzes the collision risk-capacity tradeoff using a combined discrete–continuous simulation method. A basic two-dimensional en-route flow corridor with performance rules is designed as the operational environment. A second-order system is established by combining the point mass model and the proportional derivative controller together to simulate the self-separation operations of the aircrafts in the corridor and the operation performance parameters from the User Manual for the Base of Aircraft Data are used in this research in order to improve the reliability. Simulation results indicate that the aircrafts can self-separate from each other efficiently by adjusting their velocities, and rationally setting the values of some variables can improve the rate and stability of the corridor with low risks of loss of separation

To cope with the environmental impact of aviation and pollution problems in the future, airlines need to assess environmental impacts and offer countermeasures in advance. In order to measure the influence of environment on the airlines’ operational costs, this paper establishes an aircraft green direct operating cost (GDOC) model to quantify adverse environmental effects, such as air pollution and greenhouse effects, into the direct operating cost (DOC). Furthermore, fuel consumption, flight time, and distance in the cruising stage account for about 80% of the entire flight mission, and optimizing cruise flight performance can contribute greatly to reduce GDOC. Therefore, this paper sets up an optimal control model to minimize GDOC, establishes a discrete time dynamic system for optimizing the cruise altitude and speed profiles, and searches the optimal results by using dynamic programming. Besides, as meteorological conditions affect aircraft aerodynamics, fuel flow rate, contrail formation, and so on, this paper analyzes meteorological uncertainty by using historic meteorological data. Finally, a route is selected as an example, and the rationality of the optimal results is proven by comparing GDOC with DOC. The results and discussion of the numerical test also show that environmental effects on aircraft operation can be reduced significantly by adopting GDOC as the optimization objective, especially the contrail cost, and the step-climb cruise mode can further reduce GDOC effectively.

In order to reduce the environmental impact of aircraft operation in the terminal area, this paper researched the route optimization method. Firstly, this paper constructed the air pollutant emission and noise assessment model, and the flight performance model. Secondly, aiming at reducing air emissions and noise level, the multi-objective terminal area route optimization model is established based on the principles of flight safety and flight procedure construction. Then this paper puts forward the path optimization method of emission and noise reduction of terminal area route network, through the research on the priority setting method of terminal area approach and departure route planning. The route segmentation method and NSGA-II algorithm are employed to solve the problem. Finally, a numerical case study is carried out for the Shanghai terminal area, and yields the following results: (1) Compared with the original route network, the optimized route network in the terminal area can significantly reduce emission and noise by reducing pollutant emission by 51.4% and noise influence by 21.5%; (2) The method can also reduce fuel consumption by 60.5% and the total route length by 21.1%.

Air traffic flow management (ATFM) is a collaborative process between the airspace provider and the airspace users. The result of the collaboration should be an outcome that maximizes the utility of the system without excessively penalizing any of the agents. This paper develops a discrete-event simulation model which consists of aggregate departure/arrival airports, flight routes, and sectors for evaluating the alternative collaborative route selection strategy. Given the different perspectives from air traffic control center (ACC) and airlines, eight performance-metrics and five alternative route selection strategies represent the past, current and proposed air traffic flow management operations that were evaluated. The Monte Carlo method combined with the Optimal Computing Budget Allocation (OCBA) simulation optimization technique is employed to assess the performance of different strategies. A case study of the upper air routes in central and southern China shows that the proposed model can be readily implemented to simulate different kinds of air traffic flow management strategies and predict the effect of changes on the airspace system. It also shows that the proposed alternative collaborative route selection strategy is an effective way in alleviating the en-route traffic congestion