Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/74383
Title: Neural network training for the detection and classification of oceanic mesoscale eddies
Authors: Santana, Oliverio J. 
Hernández-Sosa, Daniel 
Martz, Jeffrey
Smith, Ryan N.
UNESCO Clasification: 120304 Inteligencia artificial
120326 Simulación
Keywords: Classification
Convolutional neural network
Data analysis
Deep learning
Detection, et al
Issue Date: 2020
Journal: Remote Sensing 
Abstract: Recent advances in deep learning have made it possible to use neural networks for the detection and classification of oceanic mesoscale eddies from satellite altimetry data. Various neural network models have been proposed in recent years to address this challenge, but they have been trained using different types of input data and evaluated using different performance metrics, making a comparison between them impossible. In this article, we examine the most common dataset and metric choices, by analyzing the reasons for the divergences between them and pointing out the most appropriate choice to obtain a fair evaluation in this scenario. Based on this comparative study, we have developed several neural network models to detect and classify oceanic eddies from satellite images, showing that our most advanced models perform better than the models previously proposed in the literature.
URI: http://hdl.handle.net/10553/74383
DOI: 10.3390/RS12162625
Source: Remote Sensing [EISSN 2072-4292], v. 12 (16), 2625, (Agosto 2020)
Appears in Collections:Artículos
Thumbnail
PDF
Adobe PDF (1,97 MB)
Show full item record

SCOPUSTM   
Citations

8
checked on Oct 2, 2022

Page view(s)

89
checked on Oct 1, 2022

Download(s)

65
checked on Oct 1, 2022

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.