All major airport operators face a similar challenge, namely ensuring maximum throughput and maintaining high runway utilisation. A key part of this is accurately planning aircraft movements on the ground to avoid queueing and associated delays. A primary indicator of the operator performance in this area is the Taxi-Out Time. The research objective of this article is to review whether the application of machine learning can be used to model the departure process in such a way as to provide accurate prediction of TXOT taking into account a wide range of variables. A regression tree type machine learning model is developed using actual data from Vienna Airport and a selected set of significant predictor variables. The taxi-out times of the test set of flights are closely predicted with an RMSE of 2.03 minutes for normal taxi-out and 3.75 minutes for extended taxi-out.

Wild_res have always been a problem; but, with human migration all around the world, this problem has signi_- cantly increased its importance and impact. The mounting challenges facing wild_re management, together with its increasing demand, have necessitated research into technological advancements and methods to increase wild_re management ef_cacy. As Unmanned Aerial Vehicles (UAVs) become more and more widespread, development has skyrocketed and is applied to all kinds of areas, such as surveillance, military, and commercial _lming. Fire surveillance is the area of interest for this project. The main goal of this report is to offer a concise overview of the preliminary design of the _re monitoring swarm system. This report will touch upon the main problems encountered while working on the design and the solutions of these problems. The report ends with some recommendations for the future. Forest _res happen all over Europe; however, the Mediterranean region is most affected by these forest _res. Combined with global warming, the occurrence of forest _res will increase, which will lead to an increase of the annual economic and environmental damage caused by these _res. Both _re _ghters and operational centres have been searching for years to effectively combat forest _res, thereby minimising the damage done by forest _res. Different systems have been used in the past, some as simple as _re lookout towers and some as complex as optical-based smoke detection systems. However, none of these systems has been able to provide real-time data to _re_ghters. This is where this _re monitoring swarm comes into play. The swarm system is composed of a searching and a tracking element. The searching element has 5 Penguin B UAVs and has two operating modes. The _rst mode is detection of _res and con_rming upon detection, while the second mode consists of acting as a mothership for that speci_c _re. The tracking element has 10 Albatross UAVs which can perform three functions, namely high altitude tracking; low altitude tracking; and scouting. Members of the swarm will have a communication system for communication among swarm members and for communication with the operational centres. All UAVs will be launched using a catapult and are capable of a fully autonomous landing...