Machine Learning and Data Fusion of Simulated Remote Sensing Data

Simple item page
dc.contributor.authorHiggins, Erik Tracyen
dc.contributor.committeechairPaterson, Eric G.en
dc.contributor.committeechairFreeman, Laura J.en
dc.contributor.committeememberPitt, Jonathanen
dc.contributor.committeememberXiao, Hengen
dc.contributor.committeememberEngland, Scott L.en
dc.contributor.departmentAerospace and Ocean Engineeringen
dc.date.accessioned2023-07-28T08:04:17Zen
dc.date.available2023-07-28T08:04:17Zen
dc.date.issued2023-07-27en
dc.description.abstractModeling and simulation tools are described and implemented in a single workflow to develop a means of simulating a ship wake followed by simulated synthetic aperture radar (SAR) and infra-red (IR) images of these ship wakes. A parametric study across several different ocean environments and simulated remote sensing platforms is conducted to generate a preliminary data set that is used for training and testing neural network--based ship wake detection models. Several different model architectures are trained and tested, which are able to provide a high degree of accuracy in classifying whether input SAR images contain a persistent ship wake. Several data fusion models are explored to understand how fusing data from different SAR bands may improve ship wake detection, with some combinations of neural networks and data fusion models achieving perfect or near-perfect performance. Finally, an outline for a future study into multi-physics data fusion across multiple sensor modalities is created and discussed.en
dc.description.abstractgeneralThis dissertation focuses on using computer simulations to first simulate the wakes of ships on the ocean surface, and then simulate airborne or satellite-based synthetic aperture radar (SAR) and infra-red (IR) images of these ship wakes. These images are used to train machine learning models that can be given a SAR or IR image of the ocean and determine whether or not the image contains a ship wake. The testing shows good preliminary results and some models are able to detect ship wakes in simulated SAR images with a high degree of accuracy. Data fusion models are then created which seeks to fuse data sources together in order to improve ship wake detection. These data fusion models are tested using the simulated SAR images, and some of these data fusion models show a positive impact on ship wake detection. Next steps for future research are documented, such as data fusion of SAR and IR data in order to study how fusion of these sensors impacts ship wake detection compared to just a single SAR sensor or multiple SAR sensors fused together.en
dc.description.degreeDoctor of Philosophyen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:37294en
dc.identifier.urihttp://hdl.handle.net/10919/115895en
dc.language.isoenen
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectship wakeen
dc.subjectnaval hydrodynamicsen
dc.subjectremote sensingen
dc.subjectneural networksen
dc.subjectdata fusionen
dc.titleMachine Learning and Data Fusion of Simulated Remote Sensing Dataen
dc.typeDissertationen
thesis.degree.disciplineAerospace Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.leveldoctoralen
thesis.degree.nameDoctor of Philosophyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Higgins_ET_D_2023.pdf
Size:
5.64 MB
Format:
Adobe Portable Document Format
Download

Collections

Doctoral Dissertations