Prediction of aircraft performances based on data collected by air traffic control centers

Accurate prediction of aircraft position is becoming more and more important for the future of air traffic. Currently, the lack of information about flights prevents us to fulfill future demands for the needed accuracy in 4D trajectory prediction. Until we get the necessary information from aircraft and until new more accurate methods are implemented and used, we propose an alternative method for predicting aircraft performances using machine learning from historical data about past flights collected in a multidimensional database. In that way, we can improve existing applications by providing them better inputs for their trajectory calculations. Our method uses flight plan data to predict performance values, which are suited individually for each flight. The results show that based on recorded past aircraft performances and related flight data we can effectively predict performances for future flights based on how similar flights behaved in the past.     

Probabilistic multi-aircraft conflict detection approach for trajectory-based operation

Conflict detection (CD) is one of the key functions used to ensure air transport safety and efficiency. In trajectory-based operation (TBO), aircraft are provided with more flexibility in en route trajectory planning and more responsibility for self-separation. The high flexibility in trajectory planning enables random changes in pilot intent, thus increasing the uncertainty in trajectory prediction and CD. This study proposes a novel probabilistic CD approach for TBO in which the uncertainty of pilot intent is taken into account by quantifying the aircraft reachable domain constrained by the flight plan. First, a probabilistic model for aircraft trajectory prediction is developed using the truncated Brownian bridge method. Based on this model, a novel conflict probability estimation method is developed. Finally, the performance of the proposed probabilistic CD approach is demonstrated through an illustrative air traffic scenario.     

Aircraft trajectory forecasting using local functional regression in Sobolev space

This paper considers the problem of short to mid-term aircraft trajectory prediction, that is, the estimation of where an aircraft will be located over a 10–30 min time horizon. Such a problem is central in decision support tools, especially in conflict detection and resolution algorithms. It also appears when an air traffic controller observes traffic on the radar screen and tries to identify convergent aircraft, which may be in conflict in the near future. An innovative approach for aircraft trajectory prediction is presented in this paper. This approach is based on local linear functional regression that considers data preprocessing, localizing and solving linear regression using wavelet decomposition. This algorithm takes into account only past radar tracks, and does not use any physical or aeronautical parameters. This approach has been successfully applied to aircraft trajectories between several airports on the data set that is one year air traffic over France. The method is intrinsic and independent from airspace structure.     

Online calibration for microscopic traffic simulation and dynamic multi-step prediction of traffic speed

Simulating driving behavior in high accuracy allows short-term prediction of traffic parameters, such as speeds and travel times, which are basic components of Advanced Traveler Information Systems (ATIS). Models with static parameters are often unable to respond to varying traffic conditions and simulate effectively the corresponding driving behavior. It has therefore been widely accepted that the model parameters vary in multiple dimensions, including across individual drivers, but also spatially across the network and temporally. While typically on-line, predictive models are macroscopic or mesoscopic, due to computational and data considerations, nowadays microscopic models are becoming increasingly practical for dynamic applications. In this research, we develop a methodology for online calibration of microscopic traffic simulation models for dynamic multi-step prediction of traffic measures, and apply it to car-following models, one of the key models in microscopic traffic simulation models. The methodology is illustrated using real trajectory data available from an experiment conducted in Naples, using a well-established car-following model. The performance of the application with the dynamic model parameters consistently outperforms the corresponding static calibrated model in all cases, and leads to less than 10% error in speed prediction even for ten steps into the future, in all considered data-sets.     

Operating cost sensitivity to required time of arrival commands to ensure separation in optimal aircraft 4D trajectories

Trajectory optimisation has shown good potential to reduce environmental impact in aviation. However, a recurring problem is the loss in airspace capacity that fuel optimal procedures pose, usually overcome with speed, altitude or heading advisories that lead to more costly trajectories. This paper aims at the quantification in terms of fuel and time consumption of implementing suboptimal trajectories in a 4D trajectory context that use required times of arrival at specific navigation fixes. A case study is presented by simulating conflicting Airbus A320 departures from two major airports in Catalonia. It is shown how requiring an aircraft to arrive at a waypoint early or late leads to increased fuel burn. In addition, the efficiency of such methods to resolve air traffic conflicts is studied in terms of both fuel burn and resulting aircraft separations. Finally, various scenarios are studied reflecting various airline preferences with regards to cost and fuel burn, as well as different route and conflict geometries for a broader scope of study.     

Calculation of aircraft fuel consumption and CO2 emissions based on path profile estimation by clustering and registration

In this paper, typical flight paths, fuel burn and carbon dioxide (CO₂) emissions are computed using a rich data set and two estimation approaches: (i) a clustering and landmark registration technique and (ii) a method based on the EUROCONTROL’s Base of Aircraft Data (BADA) performance model. Clustering is employed to extract flight characteristics and organize altitude profiles accordingly. Our flight path and CO₂ emissions analysis focuses on the Climb-Cruise-Descent (CCD) cycle, since different operational conditions during the Landing and Take-off cycle may result in significant deviations in terms of fuel burn and CO₂ emissions and different modeling assumptions and approaches should be adopted. The key features of the CCD cycle are the flight distance, the aircraft type and the flight direction. Path segmentation and landmark registration are employed for path representation and smoothening of discontinuities. The paths estimated by the above method are compared to those obtained by the point mass BADA model. Noticeable deviations in the resulting estimates of the operational characteristics are found. Higher deviations in prediction errors are found in the climb and descent duration and the rate of climb and descent. The typical altitude profiles obtained by the two methods are used to determine fuel burn and CO₂ emissions. The difference in the resulting estimates are less stark; on a fleet-wide level the fuel burn of the relevant typical profiles differ by 7%. Emission maps of the U.S. airspace enabling the identification of critical emission spots including routes, airports, seasons and aircraft type are constructed.     

A hybrid machine learning model for short-term estimated time of arrival prediction in terminal manoeuvring area

4D trajectory prediction is the core element of future air transportation system, which is intended to improve the operational ability and the predictability of air traffic. In this paper, we introduce a novel hybrid model to address the short-term trajectory prediction problem in Terminal Manoeuvring Area (TMA) by application of machine learning methods. The proposed model consists of two parts: clustering-based preprocessing and Multi-Cells Neural Network (MCNN)-based prediction. Firstly, in the preprocessing part, after data cleaning, filtering and data re-sampling, we applied principal Component Analysis (PCA) to reduce the dimension of trajectory vector variable. Then, the trajectories are clustered into several patterns by clustering algorithm. Using nested cross validation, MCNN model is trained to find out the appropriate prediction model of Estimated Time of Arrival (ETA) for each individual cluster cell. Finally, the predicted ETA for each new flight is generated in different cluster cells classified by decision trees. To assess the performance of MCNN model, the Multiple Linear Regression (MLR) model is proposed as the comparison learning model, and K-means++ and DBSCAN are proposed as two comparison clustering models in preprocessing part. With real 4D trajectory data in Beijing TMA, experimental results demonstrate that our proposed model MCNN with DBSCAN in preprocessing is the most effective and robust hybrid machine learning model, both in trajectory clustering and short-term 4D trajectory prediction. In addition, it can make an accurate trajectory prediction in terms of Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) with regards to comparison models.     

Estimation of aircraft taxi fuel burn using flight data recorder archives

This paper builds a model for estimating the fuel consumption of a taxiing aircraft using flight data recorder information from operational aircraft. The taxi fuel burn is modeled as a linear function of several potential explanatory variables including the taxi time, number of stops, number of turns and number of acceleration events, and the coefficients are estimated using least-squares regression. The statistical significance of each potential factor is investigated. Our analysis shows that in addition to the taxi time, the number of acceleration events is a significant factor in determining taxi fuel consumption. Since the model parameters are estimated using data from operational aircraft, they provide more accurate estimates of fuel burn than methods that use idealized physical models of fuel consumption based on aircraft velocity profiles, or the baseline fuel consumption estimates provided by the International Civil Aviation Organization.     

Accuracy of reinforcement learning algorithms for predicting aircraft taxi-out times: A case-study of Tampa Bay departures

Taxi-out delay is a significant portion of the block time of a flight. Uncertainty in taxi-out times reduces predictability of arrival times at the destination. This in turn results in inefficient use of airline resources such as aircraft, crew, and ground personnel. Taxi-out time prediction is also a first step in enabling schedule modifications that would help mitigate congestion and reduce emissions. The dynamically changing operation at the airport makes it difficult to accurately predict taxi-out time. In this paper we investigate the accuracy of taxi out time prediction using a nonparametric reinforcement learning (RL) based method, set in the probabilistic framework of stochastic dynamic programming. A case-study of Tampa International Airport (TPA) shows that on an average, with 93.7% probability, on any given day, our predicted mean taxi-out time for any given quarter, matches the actual mean taxi-out time for the same quarter with a standard error of 1.5 min. Also, for individual flights, the taxi-out time of 81% of them were predicted accurately within a standard error of 2 min. The predictions were done 15 min before gate departure. Gate OUT, wheels OFF, wheels ON, and gate IN (OOOI) data available in the Aviation System Performance Metric (ASPM) database maintained by the Federal Aviation Administration (FAA) was used to model and analyze the problem. The prediction accuracy is high even without the use of detailed track data.     

Aircraft initial mass estimation using Bayesian inference method

Aircraft mass is a crucial piece of information for studies on aircraft performance, trajectory prediction, and many other topics of aircraft traffic management. However, It is a common challenge for researchers, as well as air traffic control, to access this proprietary information. Previously, several studies have proposed methods to estimate aircraft weight based on specific parts of the flight. Due to inaccurate input data or biased assumptions, this often leads to less confident or inaccurate estimations. In this paper, combined with a fuel-flow model, different aircraft initial masses are computed independently using the total energy model and reference model at first. It then adopts a Bayesian approach that uses a prior probability of aircraft mass based on empirical knowledge and computed aircraft initial masses to produce the maximum a posteriori estimation. Variation in results caused by dependent factors such as prior, thrust and wind are also studied. The method is validated using 50 test flights of a Cessna Citation II aircraft, for which measurements of the true mass were available. The validation results show a mean absolute error of 4.3% of the actual aircraft mass.     

Analysis of air traffic control operational impact on aircraft vertical profiles supported by machine learning

The Air Traffic Management system is under a paradigm shift led by NextGen and SESAR. The new trajectory-based Concept of Operations is supported by performance-based trajectory predictors as major enablers. Currently, the performance of ground-based trajectory predictors is affected by diverse factors such as weather, lack of integration of operational information or aircraft performance uncertainty.Trajectory predictors could be enhanced by learning from historical data. Nowadays, data from the Air Traffic Management system may be exploited to understand to what extent Air Traffic Control actions impact on the vertical profile of flight trajectories.This paper analyses the impact of diverse operational factors on the vertical profile of flight trajectories. Firstly, Multilevel Linear Models are adopted to conduct a prior identification of these factors. Then, the information is exploited by trajectory predictors, where two types are used: point-mass trajectory predictors enhanced by learning the thrust law depending on those factors; and trajectory predictors based on Artificial Neural Networks.Air Traffic Control vertical operational procedures do not constitute a main factor impacting on the vertical profile of flight trajectories, once the top of descent is established. Additionally, airspace flows and the flight level at the trajectory top of descent are relevant features to be considered when learning from historical data, enhancing the overall performance of the trajectory predictors for the descent phase.     

Three-dimensional conflict count models for unstructured and layered airspace designs

This paper presents analytical models that describe the safety of unstructured and layered en route airspace designs. Here, ‘unstructured airspace’ refers to airspace designs that offer operators complete freedom in path planning, whereas ‘layered airspace’ refers to airspace concepts that utilize heading-altitude rules to vertically separate cruising aircraft based on their travel directions. With a focus on the intrinsic safety provided by an airspace design, the models compute instantaneous conflict counts as a function of traffic demand and airspace design parameters, such as traffic separation requirements and the permitted heading range per flight level. While previous studies have focused primarily on conflicts between cruising aircraft, the models presented here also take into account conflicts involving climbing and descending traffic. Fast-time simulation experiments used to validate the modeling approach indicate that the models estimate instantaneous conflict counts with high accuracy for both airspace designs. The simulation results also show that climbing and descending traffic caused the majority of conflicts for layered airspaces with a narrow heading range per flight level, highlighting the importance of including all aircraft flight phases for a comprehensive safety analysis. Because such trends could be accurately predicted by the three-dimensional models derived here, these analytical models can be used as tools for airspace design applications as they provide a detailed understanding of the relationships between the parameters that influence the safety of unstructured and layered airspace designs.     

Daily activity pattern recognition by using support vector machines with multiple classes

The focus of this paper is to learn the daily activity engagement patterns of travelers using Support Vector Machines (SVMs), a modeling approach that is widely used in Artificial intelligence and Machine Learning. It is postulated that an individual’s choice of activities depends not only on socio-demographic characteristics but also on previous activities of individual on the same day. In the paper, Markov Chain models are used to study the sequential choice of activities. The dependencies among activity type, activity sequence and socio-demographic data are captured by employing hidden Markov models. In order to learn model parameters, we use sequential multinomial logit models (MNL) and multiclass Support Vector Machines (K-SVM) with two different dependency structures. In the first dependency structure, it is assumed that type of activity at time ‘t’ depends on the last previous activity and socio-demographic data, whereas in the second structure we assume that activity selection at time ‘t’ depends on all of the individual’s previous activity types on the same day and socio-demographic characteristics. The models are applied to data drawn from a set of California households and a comparison of the accuracy of estimation of activity types and their sequence in the agenda, indicates the superiority of K-SVM models over MNL. Additionally, we show that accuracy in estimating activity patterns increases using different sets of explanatory variables or tuning parameters of the kernel function in K-SVM.     

Integrated sequencing and merging aircraft to parallel runways with automated conflict resolution and advanced avionics capabilities

Congestion in Terminal Maneuvering Area (TMA) in hub airports is the main problem in Chinese air transportation. In this paper we propose a new system to integrated sequence and merge aircraft to parallel runways at Beijing Capital International Airport (BCIA). This system is based on the advanced avionics capabilities. Our methodology integrates a Multi-Level Point Merge (ML-PM) system, an economical descent approaches procedure, and a tailored heuristic algorithm to find a good, systematic, operationally-acceptable solution. First, Receding Horizontal Control (RHC) technique is applied to divide the entire 24 h of traffic into several sub-problems. Then in each sub-problem, it is optimized on given objectives (conflict, deviation from Estimated Time of Arrival (ETA) on the runway and makespan of the arrival flow). Four decision variables are designed to control the trajectory: the entry time, the entry speed, the turning time on the sequencing leg, and the landing runway allocation. Based on these variables, the real time trajectories are generated by the simulation module. Simulated Annealing (SA) algorithm is used to search the best solution for aircraft to execute. Finally, the conflict-free, least-delay, and user-preferred trajectories from the entry point of TMA to the landing runway are defined. Numerical results show that our optimization system has very stable de-conflict performance to handle continuously dense arrivals in transition airspace. It can also provide the decision support to assist flow controllers to handle the asymmetric arrival flows on different runways with less fuel consumption, and to assist tactical controllers to easily re-sequence aircraft with more relaxed position shifting. Moreover, our system can provide the fuel consumption prediction, and runway assignment information to assist airport and airlines managers for optimal decision making. Theoretically, it realizes an automated, cooperative and green control of routine arrival flows. Although the methodology defined here is applied to the airport BCIA, it could also be applied to other airports in the world.     

Urban traffic flow prediction: a spatio‐temporal variable selection‐based approach

Short‐term traffic flow prediction in urban area remains a difficult yet important problem in intelligent transportation systems. Current spatio‐temporal‐based urban traffic flow prediction techniques trend aims to discover the relationship between adjacent upstream and downstream road segments using specific models, while in this paper, we advocate to exploit the spatial and temporal information from all available road segments in a partial road network. However, the available traffic states can be high dimensional for high‐density road networks. Therefore, we propose a spatio‐temporal variable selection‐based support vector regression (VS‐SVR) model fed with the high‐dimensional traffic data collected from all available road segments. Our prediction model can be presented as a two‐stage framework. In the first stage, we employ the multivariate adaptive regression splines model to select a set of predictors most related to the target one from the high‐dimensional spatio‐temporal variables, and different weights are assigned to the selected predictors. In the second stage, the kernel learning method, support vector regression, is trained on the weighted variables. The experimental results on the real‐world traffic volume collected from a sub‐area of Shanghai, China, demonstrate that the proposed spatio‐temporal VS‐SVR model outperforms the state‐of‐the‐art. Copyright © 2015 John Wiley & Sons, Ltd.     

What are the implications of climate change for trans-Atlantic aircraft routing and flight time?

The effect of wind changes on aircraft routing has been identified as a potential impact of climate change on aviation. This is of particular interest for trans-Atlantic flights, where the pattern of upper-level winds over the north Atlantic, in particular the location and strength of the jet stream, strongly influences both the optimal flight route and the resulting flight time. Eastbound trans-Atlantic flights can often be routed to take advantage of the strong tailwinds in the jet stream, shortening the flight time and reducing fuel consumption. Here we investigate the impact of climate change on upper-level winds over the north Atlantic, using five climate model simulations from the Fifth Coupled Model Intercomparison Project, considering a high greenhouse-gas emissions scenario. The impact on aircraft routing and flight time are quantified using flight routing software. The climate models agree that the jet stream will be on average located 1° further north, with a small increase in mean strength, by 2100. However daily variations in both its location and speed are significantly larger than the magnitude of any changes due to climate change. The net effect of climate change on trans-Atlantic aircraft routes is small; in the annual-mean eastbound routes are 1 min shorter and located further north and westbound routes are 1 min longer and more spread out around the great circle. There are, however, seasonal variations; route time changes are larger in winter, while in summer both eastbound and westbound route times increase.     

Quantifying uncertainty in short-term traffic prediction and its application to optimal staffing plan development

In this paper, we aim to quantify uncertainty in short-term traffic volume prediction by enhancing a hybrid machine learning model based on Particle Swarm Optimization (PSO) and Extreme Learning Machine (ELM) neural network. Different from the previous studies, the PSO-ELM models require no statistical inference nor distribution assumption of the model parameters, but rather focus on generating the prediction intervals (PIs) that can minimize a multi-objective function which considers two criteria, reliability and interval sharpness. The improved PSO-ELM models are developed for an hourly border crossing traffic dataset and compared to: (1) the original PSO-ELMs; (2) two state of the art models proposed by Zhang et al. (2014) and Guo et al. (2014) separately; and (3) the traditional ARMA and Kalman filter models. The results show that the improved PSO-ELM can always keep the mean PI length the lowest, and guarantee that the PI coverage probability is higher than the corresponding PI nominal confidence, regardless of the confidence level assumed. The study also probes the reasons that led to a few points being not covered by the PIs of PSO-ELMs. Finally, the study proposes a comprehensive optimization framework to make staffing plans for border crossing authority based on bounds of PIs and point predictions. The results show that for holidays, the staffing plans based on PI upper bounds generated much lower total system costs, and that those plans derived from PI upper bounds of the improved PSO-ELM models, are capable of producing the lowest average waiting times at the border. For a weekday or a typical Monday, the workforce plans based on point predictions from Zhang et al. (2014) and Guo et al. (2014) models generated the smallest system costs with low border crossing delays. Moreover, for both holiday and normal Monday scenarios, if the border crossing authority lacked the required staff to implement the plans based on PI upper bounds or point predictions, the staffing plans based on PI lower bounds from the improved PSO-ELMs performed the best, with an acceptable level of service and total system costs close to the point prediction plans.     

Multiple fleet aircraft schedule recovery following hub closures

This paper presents three multi-commodity network-type models for determining a recovery schedule for all aircraft operated by a large carrier following a hub closure. The first is a pure network with side constraints, the second is a generalized network, and the third is a pure network with side constraints in which the time horizon is discretized. Each model allows for cancellations, delays, ferry flights, and substitution between fleets and subfleets. In the first two cases, the objective is to maximize a “profit” function which includes an incentive to maintain as much of the original aircraft routings as possible. In the third case, the objective is to minimize the sum of cancellation and delay costs.After comparing solution quality and computation times for each of the three models, the first was seen to outperform the others and was singled out for further analysis. Results for a comprehensive set of scenarios are presented along with ideas for continuing work.     

Interactive image-based information visualization for aircraft trajectory analysis

Objectives: The objective of the presented work is to present novel methods for big data exploration in the Air Traffic Control (ATC) domain. Data is formed by sets of airplane trajectories, or trails, which in turn records the positions of an aircraft in a given airspace at several time instants, and additional information such as flight height, speed, fuel consumption, and metadata (e.g. flight ID). Analyzing and understanding this time-dependent data poses several non-trivial challenges to information visualization.Materials and methods: To address this Big Data challenge, we present a set of novel methods to analyze aircraft trajectories with interactive image-based information visualization techniques.As a result, we address the scalability challenges in terms of data manipulation and open questions by presenting a set of related visual analysis methods that focus on decision-support in the ATC domain. All methods use image-based techniques, in order to outline the advantages of such techniques in our application context, and illustrated by means of use-cases from the ATC domain.Results: For each considered use-case, we outline the type of questions posed by domain experts, data involved in addressing these questions, and describe the specific image-based techniques we used to address these questions. Further, for each of the proposed techniques, we describe the visual representation and interaction mechanisms that have been used to address the above-mentioned goals. We illustrate these use-cases with real-life datasets from the ATC domain, and show how our techniques can help end-users in the ATC domain discover new insights, and solve problems, involving the presented datasets.     

Emissions from auxiliary power units and ground power units during intraday aircraft turnarounds at European airports

It is widely known that emissions from aircraft engines, Auxiliary Power Units (APU) and ground handling equipment contribute to air pollution at airports. During the aircraft turnaround process, the main source of emissions is the APU. The use of the APU can be significantly reduced if the aircraft stand is equipped to supply external electrical power and pre-conditioned air to the cabin. This paper analyses the actual duration of APU and external power usage during intraday aircraft turnarounds at 125 airports during June 2015. The data is derived from flight data recording units of more than 200 short-haul, narrow-body jet aircraft, conducting some 25,195 aircraft turnarounds and thus provides the most detailed assessment of aircraft power usage available. A common practice is for the APU to be running for a short period on arrival at the stand (arrival-cycle) and then again for a short period prior to departure (departure-cycle). It is identified in this study that departure-cycle emissions are three times greater than arrival-cycle emissions. These emissions could be reduced if more accurate forecasts of departure times are available to flight crew. The provision of external ground power is found to reduce emissions by up to 47.6%. However, the study also highlights that when the source of external power is a diesel-fuelled mobile Ground Power Unit (GPU), there is a net doubling in emissions of hydrocarbons. APU usage is also observed to vary with outside air temperature (OAT) leading to possible increases in emissions of up to 6%.