dc.contributor.advisor |
Lakkis, Issam |
dc.contributor.author |
Hakla, Omar |
dc.contributor.author |
Lakkis, Issam |
dc.contributor.author |
Hoteit, Ibrahim |
dc.contributor.author |
Abou Jaoude, Dany |
dc.date.accessioned |
2022-09-05T03:38:03Z |
dc.date.available |
2022-09-05T03:38:03Z |
dc.date.issued |
2022-09-05 |
dc.date.submitted |
2022-09-04 |
dc.identifier.uri |
http://hdl.handle.net/10938/23535 |
dc.description.abstract |
Oceanic eddies are ubiquitous in oceans and play a major role in several parameters that include ocean energy transfer, nutrients distribution and air-sea interaction. Typically, eddy detection algorithms are based on single physical parameter, geometrics or other handcrafted features. To achieve better performances, we aim to develop a new approach to fuse multi-variable features for eddy detection. We will investigate lumping satellite datasets of Sea surface height, Sea surface temperature, Salinity in addition to full model solution velocity field through the inclusion of information (correlation) between the datasets. |
dc.language.iso |
en_US |
dc.subject |
Eddy |
dc.subject |
Deep learning |
dc.subject |
convolutional neural network |
dc.subject |
Segmentation |
dc.subject |
Labelme |
dc.subject |
Cyclonic |
dc.title |
Eddy Detection Using Reanalysis Datasets |
dc.type |
Research Project |
dc.contributor.department |
Department of Mechanical Engineering |
dc.contributor.faculty |
Maroun Semaan Faculty of Engineering and Architecture |
dc.contributor.commembers |
Lakkis, Issam |
dc.contributor.commembers |
Hoteit, Ibrahim |
dc.contributor.commembers |
Abou Jaoude, Dany |
dc.contributor.degree |
ME |
dc.contributor.AUBidnumber |
202020158 |