CLASSIFICATION OF BOLIDES AND METEORS IN DOPPLER RADAR WEATHER DATA USING UNSUPERVISED MACHINE LEARNING

Simple item page
dc.contributor.advisorKarpenko, Mark
dc.contributor.advisorAbell, Paul, NASA Johnson Space Center
dc.contributor.authorSmeresky, Brendon P.
dc.contributor.departmentMechanical and Aerospace Engineering (MAE)
dc.contributor.secondreaderWhitaker, Lyn R.
dc.dateDec-19
dc.date.accessioned2020-02-20T01:30:27Z
dc.date.available2020-02-20T01:30:27Z
dc.date.issued2019-12
dc.description.abstractThis thesis presents a method for detecting outlier meteors and bolides within Doppler radar data using unsupervised machine learning. Principal Component Analysis (PCA), k-means Clustering, and t-Distributed Statistical Neighbor Embedding (t-SNE) algorithms are introduced as existing methods for outlier detection. A combined PCA and t-SNE method that uses a Nearest Neighbor Density Pruning method for dataset size reduction is also described. These methods are implemented to classify unlabeled radar data from four radar data sites from two bolide events: the KFWS radar for the Ash Creek bolide and the KDAX, KRGX, and KBBX radars for the Sutter’s Mill bolide. The combined PCA + t-SNE method gives an accuracy rate of 99.7% and can classify the data in less than 8 minutes for a 121,000 return sized dataset. However, the classifier’s recall and precision rates remained low due to difficulties in correctly classifying true positive bolides. Some ideas for improving algorithm accuracy, speed, and related follow-on applications are proposed. Overall, the algorithm presented in this research is a viable method to help NASA scientists with bolide detection and meteorite recovery.en_US
dc.description.distributionstatementApproved for public release; distribution is unlimited.
dc.description.recognitionOutstanding Thesisen_US
dc.description.serviceLieutenant Commander, United States Navyen_US
dc.description.urihttp://archive.org/details/classificationof1094564069
dc.identifier.thesisid31945
dc.identifier.urihttps://hdl.handle.net/10945/64069
dc.publisherMonterey, CA; Naval Postgraduate Schoolen_US
dc.relation.ispartofseriesNPS Outstanding Theses and Dissertations
dc.rightsThis publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.en_US
dc.subject.authorasteroidsen_US
dc.subject.authorbolidesen_US
dc.subject.authormeteorsen_US
dc.subject.authorartificial intelligenceen_US
dc.subject.authormachine learningen_US
dc.subject.authorunsupervised machine learningen_US
dc.subject.authorprincipal component analysisen_US
dc.subject.authorclusteringen_US
dc.subject.authort-SNEen_US
dc.subject.authorDoppler radaren_US
dc.subject.authornearest neighborsen_US
dc.titleCLASSIFICATION OF BOLIDES AND METEORS IN DOPPLER RADAR WEATHER DATA USING UNSUPERVISED MACHINE LEARNINGen_US
dc.typeThesisen_US
dspace.entity.typePublication
etd.thesisdegree.disciplineAstronautical Engineeringen_US
etd.thesisdegree.grantorNaval Postgraduate Schoolen_US
etd.thesisdegree.levelMastersen_US
etd.thesisdegree.nameMaster of Science in Astronautical Engineeringen_US
relation.isSeriesOfPublicationc5e66392-520c-4aaf-9b4f-370ce82b601f
relation.isSeriesOfPublication.latestForDiscoveryc5e66392-520c-4aaf-9b4f-370ce82b601f
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
19Dec_Smeresky_Brendon.pdf
Size:
6.1 MB
Format:
Adobe Portable Document Format
Download
Collections
Theses