The objective of this research is to predict the delays in the departure of scheduled commercial flights through a methodology that uses predictive tools based on machine learning/deep learning (ML/DL), with supervised training in regression, based on the available flight datasets. Since the novel contribution of this work is, first, to make the comparison of the predictions in terms of means and statistical variance of the different ML/DL models implemented and, second, to determine the coefficients of the importance of the features or flight attributes, using ML methods known as permutation importance, it is possible to rank the importance of flight attributes by their influence in determining the delay time and reduce the problem of selecting the most important flight attributes. From the results obtained, it is worth mentioning that the model that presents the best performance is the ensemble or combinatorial method of random forest regressor models, with an acceptable prediction range (measured with the root-mean-square-error).

The satellite constellation with automatic dependent surveillance-broadcast on-board is of great importance for air traffic surveillance due to its multiple advantages compared with traditional methods. Although some research has been conducted on satellite constellation design based on coverage performance, the findings cannot entirely satisfy all the requirements of air traffic surveillance owing to the lack of analysis on inter-satellite links and network transmission. This paper presents a novel design of a low earth orbit satellite constellation network to solve this problem. Based on the requirements of space-based surveillance, an evaluation model of constellation performance is proposed concerning coverage, link and transmission. The simulation results show that the evaluation model can reflect the performance of a satellite constellation network designed for a space-based surveillance system, and a 55-satellite constellation design scheme with fairly good performance can fulfil the function of global real-time air traffic surveillance.

This study is aimed at establishing a linear holding (LH) procedure instead of a conventional air holding stack to minimize the effects of airborne delays in terms of air traffic management and fuel consumption. This paper uses both actual flight data and the Base of Aircraft Database (BADA) model to obtain fuel consumption for level flight and descent segments, separately.

The total fuel savings obtained by using actual flight data (16%) and the BADA model (10%) indicate that the LH is found to be more advantageous compared to a conventional holding procedure. Furthermore, the recommended LH procedure could be a promising solution for keeping aircraft in a narrow area that could be considered to be an effective method for airspace usage.

One of the important tasks that air traffic management services are faced with today is the task of maximising airport capacity. This can be achieved at the tactical level through proper organisation of air traffic around an airport. In recent years, many methods and algorithms for scheduling aircraft landings have been developed; they take into account various optimisation goals. The aim of this paper was to create a method that would allow one to evaluate landing aircraft sequences resulting from these control algorithms, especially in the presence of random disturbances. This method involves modelling the landing aircraft sequence by using Petri nets. The model and the computer tool that have been developed make it possible to take into account different kinds of disturbances and examine the effectiveness of various control strategies under these conditions. This paper presents two experiments that test disturbances with different characteristics and of different intensities. It has been shown that small but more frequent disturbances lead to the worsening of evaluation scores for a given sequence to a lesser extent than rare but larger disturbances. This is particularly important for control algorithms in which the focus is on high aircraft density. If the type of particular disturbances is properly assessed, then it will be possible to assist the decision-maker (air traffic controller) by providing him/her with quantitative evaluations of possible solutions.