Trajectory Clustering within the Terminal Airspace Utilizing a Weighted Distance Function

Corrado, Samantha J.; Puranik, Tejas G.; Pinon, Oliva J.; Mavris, Dimitri N.

doi:10.3390/proceedings2020059007

Cited by 21 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A trajectory clustering task is generally defined as a process partitioning a collection of trajectories into similar groups [109]. The trajectory clustering task, which is typically formulated as an unsupervised machine learning problem, has been widely used in various engineering areas such as civil and aerospace engineering.…”

Section: Flight Trajectory Clusteringmentioning

confidence: 99%

Data-Driven Approach Using Machine Learning for Real-Time Flight Path Optimization

Kim

Justin

Mavris

et al. 2022

Journal of Aerospace Information Systems

View full text Add to dashboard Cite

Date approved: April 23, 2021 So, whether you eat or drink, or whatever you do, do all to the glory of God. Corinthians 10:31For the glory of God ACKNOWLEDGMENTSAs I am now rounding the last corner before the end of my academic journey, I would like to take a few moments to sincerely thank all of those who have supported me in numerous different ways. Honestly, as there are so many people to list, this section has been one of the hardest parts of this dissertation for me. This journey would have not been possible without the dedication and support of my advisor, committee members, colleagues, friends, mentors, and family. First of all, I would like to express my sincere gratitude to my advisor, Prof. Dimitri Mavris. He has been an excellent mentor since I joined the Aerospace Systems Design Laboratory (ASDL) as a Ph.D. student in Fall 2015. I am grateful for the opportunities he has provided me -for teaching me the process of research, for recruiting me as a graduate research/teaching assistant, for allowing me to have summer internship experiences, for making me participate in various research projects, and, most importantly, for trusting me to complete this dissertation. I would not have succeeded in completing my academic goals without his continuous guidance and support. I could not have asked for a more supportive advisor in my life. I have been truly blessed to work with the best advisor. Thanks Doc for your guidance, patience, encouragement, and support. I will never forget what you have done for me.I would also like to express my profound appreciation to my committee members: Prof.

show abstract

Section: Flight Trajectory Clusteringmentioning

confidence: 99%

Data-Driven Approach Using Machine Learning for Real-Time Flight Path Optimization

Kim

Justin

Mavris

et al. 2022

Journal of Aerospace Information Systems

View full text Add to dashboard Cite

show abstract

“…A good number of studies address the trajectory clustering in the TMA. In some cases, the goal is identification of the flows in the TMA (for example, [14]). In other cases, the goal is the trajectory prediction.…”

Section: Related Workmentioning

confidence: 99%

Trajectory Clustering for Air Traffic Categorisation

et al. 2022

View full text Add to dashboard Cite

Availability of different types of data and advances in data-driven techniques open the path to more detailed analyses of various phenomena. Here, we examine the insights that can be gained through the analysis of historical flight trajectories, using data mining techniques. The goal is to learn about usual (or nominal) choices airlines make in terms of routing, and their relation with aircraft types and operational flight costs. The clustering is applied to intra-European trajectories during one entire summer season, and a statistical test of independence is used to evaluate the relations between the variables of interest. Even though about half of all flights are less than 1000 km long, and mostly operated by one airline, along one trajectory, the analysis shows that, for longer flights, there exists a clear relation between the trajectory clusters and the operating airlines (in about 49% of city pairs) and/or the aircraft types (30%), and/or the flight costs (45%).

show abstract

“…While real-time application is not the focus of this work, aviation organizations have set goals to ultimately deploy novel anomaly detection methods in real-time or near-realtime [6]. Corrado et al [48] proposed the utilization of a weighted Euclidean distance function to cluster trajectories and demonstrated that certain weighting schemes resulted in a more accurate clustering. The weighted Euclidean distance computation proceeds as:…”

Section: Spatial Anomaly Detectionmentioning

confidence: 99%

“…Clustering algorithms rely on the definition of a distance function. In previous work by the authors [48]), the effectiveness of a weighted Euclidean distance function to identify air traffic flows is demonstrated. The results indicated a more robust identification of outliers.…”

Section: Spatial Anomaly Detectionmentioning

confidence: 99%

“…Additionally, a weighting scheme was selected for the utilization of the weighted Euclidean distance with HDBSCAN. Corrado et al [48] demonstrated the success of their "Weighting 1" weighting scheme on a data set including flights at KSFO between June 1 st , 2019 and September 30 th 2019. Therefore, this "Weighting 1" scheme was selected.…”

Section: Spatial Anomaly Detectionmentioning

confidence: 99%

See 1 more Smart Citation

A clustering-based quantitative analysis of the interdependent relationship between spatial and energy anomalies in ADS-B trajectory data

Corrado

Puranik

Fischer

et al. 2021

Transportation Research Part C: Emerging Technologies

Self Cite

View full text Add to dashboard Cite

As air traffic demand grows, robust, data-driven anomaly detection methods are required to ensure that aviation systems become safer and more efficient. The terminal airspace is identified as the most critical airspace for both individual flight-level and system-level safety and efficiency. As such, developing data-driven anomaly detection methods to analyze terminal airspace operations is paramount. With the expansion of ADS-B technology, open-source flight tracking data has become more readily available to enable larger-scale analyses of aircraft operations. This paper makes a distinction between spatial metrics in ADS-B trajectory data and energy metrics derived from ADS-B trajectory data. Motivated by the limited number of approaches that simultaneously consider both spatial and energy metrics, this paper introduces the concepts of spatial anomalies and energy anomalies. In particular, it proposes a novel, unified framework for detection of spatial and energy anomalies in ADS-B trajectory data (and associated derived metrics). The framework consists of three main parts -a data processing procedure, a spatial anomaly detection method, and an energy anomaly detection method. The framework is demonstrated utilizing four months of ADS-B trajectory data associated with arrivals at San Francisco International Airport, and the relationship between the spatial and energy anomalies in this terminal airspace is explored. The results that stem from the implementation of this framework indicate that if an aircraft is spatially not conforming to an identified set of air traffic flows representing standard spatial operations, then this aircraft is more likely to experience non-conformance to standard operations in its energy metrics. Aviation operators, such as air traffic controllers, may benefit from this observation, as it may factor into decision-making in instances where there is the potential to instruct an aircraft to spatially deviate from standard operations. Additionally, this research revealed underlying differences between trajectories that are spatially nominal yet energy-anomalous and those trajectories that are spatially anomalous and energy-anomalous. Focusing solely on energy anomaly detection does not provide insight into potential spatial-related decisions that may have been made to result in off-nominal energy behavior.

show abstract

Trajectory Clustering within the Terminal Airspace Utilizing a Weighted Distance Function

Cited by 21 publications

References 14 publications

Data-Driven Approach Using Machine Learning for Real-Time Flight Path Optimization

Data-Driven Approach Using Machine Learning for Real-Time Flight Path Optimization

Trajectory Clustering for Air Traffic Categorisation

A clustering-based quantitative analysis of the interdependent relationship between spatial and energy anomalies in ADS-B trajectory data

Contact Info

Product

Resources

About