Automated identification of terminal area air traffic flows and weather related deviations
Author(s)
Ng, Tony M. Eng. Massachusetts Institute of Technology![Thumbnail](/bitstream/handle/1721.1/46010/355829114-MIT.pdf.jpg?sequence=5&isAllowed=y)
DownloadFull printable version (15.53Mb)
Other Contributors
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Advisor
Richard DeLaura and Patrick H. Winston.
Terms of use
Metadata
Show full item recordAbstract
Air traffic in terminal air space is very complex, making it very difficult to identify air traffic flows. Finding air traffic flows and flow boundaries are very helpful in analyzing how air traffic would react to weather. This thesis created the Terminal Traffic Flow Identifier algorithm to solve this problem. The algorithm was demonstrated to work in the Atlanta by quickly processing 20,000 sample trajectories and returning accurate flows with tight boundaries. This thesis also created techniques to extract weather features that occur inside the identified flows and demonstrated that training upon these features give good results. The algorithms and software created in this thesis may soon be incorporated into larger traffic managements systems developed at MIT Lincoln Laboratory.
Description
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008. Includes bibliographical references (p. 47).
Date issued
2008Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.