People and companies today are connected around the world, which has led to a growing importance of the aviation industry. As flight delays are a big challenge in aviation, machine learning algorithms can be used to forecast those. This paper investigates the prediction of the occurrence of flight arrival delays with three prominent machine learning algorithms for a data set of domestic flights in the USA. The task is regarded as a classification problem. The focus lies on the investigation of the influence of short-term features on the quality of the results. Therefore, three scenarios are created that are characterised by different input feature sets. When forgoing the inclusion of short-term information in order to shift the prediction timing to an early point in time, an accuracy of 69.5% with a recall of 68.2% is achieved. By including information on the delay that the aircraft had on its previous flight, the prediction quality increases slightly. Hence, this is a compromise between the early prediction timing of the first model and the good prediction quality of the third model, where the departure delay of the aircraft is added as an input feature. In this case, an accuracy of 89.9% with a recall of 83.4% is obtained. The desired timing of prediction therefore determines which features to use as inputs since short-term features significantly improve the prediction quality.

European airspace is marked by fragmentation, and from fragmentation originated congestion. As an answer to congestion, flexible use of airspace is created to fulfil all users’ requirements optimally, and at its very core lies civil-military cooperation and the coordination of airspace use. Such an approach is enabled by collaborative decision-making, which presumes timely and complete exchange of complete relevant information between airspace users. To participate in the process, the military should be transparent regarding its restrictions and capabilities of adaptation to other airspace users’ demands. Flight training syllabus structure and its specific impact on proactive planning of high-performance military aircraft pilot training operations in flexible airspace structures is the subject of this research. Significant diversity in the hourly distribution of civil traffic demand in flexible airspace structures in Zagreb FIR proves them applicable for a proactive approach to high-performance aircraft pilot training operations planning and management. Noticeable reduction in the number of civil aircraft affected by high-performance aircraft pilot training operations in flexible airspace structures at congested flight levels is corroborated. Simulations of proactive planning of high-performance aircraft pilot training operations reveal indications of flight syllabus structure’s impact on pilot flight training duration, as well as the possibility to manage its restrictions.

Data-driven forecasting methods have the problems of complex calculations, poor portability and need a large amount of training data, which limits the application of data-driven methods in small cities. This paper proposes a traffic flow forecasting method using a Nonlinear AutoRegressive model with eXogenous variables (NARX model), which uses a dynamic neural network Focused Time-Delay Neural Network (FTDNN) with a Tapped Delay Line (TDL) structure as a nonlinear function. The TDL structure enables the FTDNN to have short-term memory capabilities. At the same time, before the data is input into the FTDNN, the use of trend decomposition or differential calculation on the traffic data sequence can make the NARX model maintain long-term predictive capabilities. Compared with common nonlinear models, the FTDNN has structural advantages. It uses a simple TDL structure without the memory mechanism and the gated structure, which can reduce the parameters of the model and reduce the scale of data. Through the four-day data of Guilin City, the traffic volume forecast for five minutes is verified, and the performance of the NARX model is better than that of the SARIMA model and the Holt-Winters model.

With the rapid growth of flight volume, the impact of convective weather on flight operations in the terminal area has become more and more serious. In this paper, the typical flight paths (TFPs) are used to replace flight procedures as the routine flight paths in the terminal area, and the TFP of each flight is predicted by Random Forest (RF), Boosting Tree (BT) and K-Nearest Neighbour (KNN) algorithms based on the weather and flight plan characteristics. A multi-flight rerouting optimisation model by bi-level programming is established, which contains a flight flow optimisation model in the upper layer and a single flight path optimisation model in the lower layer. The simulated annealing algorithm and the bidirectional A* algorithm are used to solve the upper and lower models. This paper uses the terminal area of Guangzhou Baiyun Airport (ZGGG) and Wuhan Tianhe Airport (ZHHH) for case analysis. The RF algorithm has better performance in predicting TFPs compared with the BT and KNN algorithms. Compared to the historical radar trajectory, the flight path optimisation results show that for the Guangzhou terminal area, while meeting the Terminal Airspace Availability (TAA) as constraint, the flight flow increases and the flight distance reduces, effectively improving the operational efficiency within the terminal.

The article reviews qualitative and quantitative indicators to measure transport demand. After the review of the indicators and taking into account the specificity of the analysed region and the availability of data, the selected indicators were divided into five indicators groups: demographic, public transport usage description, public transport service and infrastructure, automobilisation and economics. A database of relevant indicators has been developed to execute the evaluation. The study yielded three separate results: data of city municipalities, circular municipalities and regional municipalities. The purpose of this article is to identify the most important indicators that influence the passenger flows in regional public transport and to identify the interfaces between the indicators. The main raised hypothesis was that different groups of municipalities will have different key indicators influencing the use of public transport and that public transport planning cannot follow the same methods. Multiple Variable Analysis and Simple Regression Analysis were chosen to test the hypotheses and clarify the most important indicators. The analysis shows that unemployment has the greatest impact on the number of passengers on suburban routes, while bus mileage on suburban routes has the smallest impact. The number of buses also has an impact on suburban passenger flows.

Establishing the desired quality of service (QoS) of the airport passenger terminal in order to improve operational performance is a challenge for every airport. Recent international research indicates a gradual recovery in air transport and, accordingly, the need to develop additional transport infrastructure. If the passenger terminal design in terms of infrastructure and operational capacity is not approached correctly, the level of service provided to passengers may decline. This research will focus on how the IATA Level of Service (LoS), which is provided to airport users can contribute to the optimisation of the level of service of the passenger terminal. Additionally, the impact of level of service on passenger terminal capacity assessment in relation to the diversity of air carrier business model will be analysed. Since there is no common link to uniformly describe and solve this problem, this paper will review the relevant literature in the field of passenger terminal capacity research and will analyse different approaches to solving this problem with the aim to develop a new unified concept in observing and optimising the capacity of the airport passenger terminal taking into account the types of air carrier business models.

Modern environmental and economic challenges in waste management require transition from linear to circular economic flow. In practice, this entails considerable challenges that include the change of material circle flux, the application of mathematical modelling and the use of life cycle thinking – also in the field of recovered wood (RW). To this end, the reverse logistics process model CATWOOD (CAscade Treatment of WOOD) with mechanistic modelling for detailed planning of the RW reverse flow with regular collection, innovative (cascade) sorting based on RW quality and environmentally sound recovery has been designed. As a decision support, the quantitative methods of life-cycle assessment (LCA) and societal life-cycle costing (SLCC) have been incorporated into the CATWOOD, which can choose among a few alternative scenarios. A case study has been performed in the Posavje region in Slovenia, which has discovered that reverse logistics scenarios for reuse are environmentally friendlier than those for recycling or energy recovery, but also more costly, mainly because of extensive manual labour needed and less heavy technology involved in sorting and recovery processes. Sensitivity analysis has exposed that modifying the values of the input parameters may change the final LCA and SLCC results in scenarios observed.

Air traffic complexity indicators play an essential role in measuring operational performance and controller workload. However, current studies mainly depend on the manual scoring method to scale performance or workload. This paper focuses on arrival operations and presents a data-driven strategy to establish the correlation between complexity and performance to avoid the subjectivity of the currently used manual scoring method. Firstly, we present twenty-six indicators for describing air traffic complexity and two indicators for arrival operational performance. Secondly, the clustering method distinguishes peak and off-peak situations for arrival operation. Moreover, clustering results are compared to investigate the correlation between complexity and performance initially. Thirdly, the classification method is adopted to determine such correlation further. In addition, we also identify the affecting factors which could influence operational performance. Finally, trajectories of arrival aircraft landing at Guangzhou Baiyun International Airport (ZGGG) are used for case validation. The results indicate that there is a strong correlation between complexity and performance. The accuracy and precision of classification are approximately 90%. Furthermore, the number of aircraft significantly impacts the arrival operational performance within TMA.

Few existing research studies have explored the relationship of road section level, local area level and vehicle level risks within the highway traffic safety system, which can be important to the formation of an effective risk event prediction. This paper proposes a framework of multi-level risks described by a set of carefully selected or designed indicators. The interrelationship among these latent multi-level risks and their observable indicators are explored based on vehicle trajectory data using the structural equation model (SEM). The results show that there exists significant positive correlation between the latent risk constructs that each have adequate convergent validity, and it is difficult to completely separate the local traffic level risk from both the road section level risk and vehicle level risk. The local and road level indicators are also found to be of more importance when risk prediction time gets earlier based on feature importance scoring of the LightGBM. The proposed conceptual multi-level indicator based latent risk framework generally fits with the observed results and emphasises the importance of including multi-level indicators for risk event prediction in the future.

Vehicular and flying ad hoc networks (VANETs and FANETs) are becoming increasingly important with the development of smart cities and intelligent transportation systems (ITSs). The high mobility of nodes in these networks leads to frequent link breaks, which complicates the discovery of optimal route from source to destination and degrades network performance. One way to overcome this problem is to use machine learning (ML) in the routing process, and the most promising among different ML types is reinforcement learning (RL). Although there are several surveys on RL-based routing protocols for VANETs and FANETs, an important issue of integrating RL with well-established modern technologies, such as software-defined networking (SDN) or blockchain, has not been adequately addressed, especially when used in complex ITSs. In this paper, we focus on performing a comprehensive categorisation of RL-based routing protocols for both network types, having in mind their simultaneous use and the inclusion with other technologies. A detailed comparative analysis of protocols is carried out based on different factors that influence the reward function in RL and the consequences they have on network performance. Also, the key advantages and limitations of RL-based routing are discussed in detail.