Loading content, please wait..
loading..
Logo
Version 3.24
or
Authors Effrosynidis, D; Arampatzis, A; Sylaios, G
Author Full Name Effrosynidis, Dimitrios; Arampatzis, Avi; Sylaios, Georgios
Title Seagrass detection in the mediterranean: A supervised learning approach
Source ECOLOGICAL INFORMATICS
Language English
Document Type Article
Author Keywords Seagrass classification; Dataset integration and fusion; Machine learning; Data mining; Mediterranean Sea
Keywords Plus POSIDONIA-OCEANICA; REGRESSION; MODELS; GROWTH; BAY; PHOTOSYNTHESIS; DISTRIBUTIONS; PHOSPHORUS; POLLUTION; SALINITY
Abstract We deal with the problem of detecting seagrass presence/absence and distinguishing seagrass families in the Mediterranean via supervised learning methods. By merging datasets about seagrass presence and other external environmental variables, we develop suitable training data, enhanced by seagrass absence data algorithmically produced based on certain hypotheses. Experiments comparing several popular classification algorithms yield up to 93.4% accuracy in detecting seagrass presence. In a feature strength analysis, the most important variables determining presence-absence are found to be Chlorophyll-alpha levels and Distance-to-Coast. For determining family, variables cannot be easily singled out; several different variables seem to be of importance, with Chlorophyll-alpha surpassing all others. In both problems, tree-based classification algorithms perform better than others, with Random Forest being the most effective. Hidden preferences reveal that Cymodocea and Posidonia favor the low, limited-range chlorophyll-alpha levels (< 0.5 mg/m(3)), Halophila tolerates higher salinities ( > 39), while Ruppia prefers euryhaline conditions (37.5-39).
Author Address [Effrosynidis, Dimitrios; Arampatzis, Avi] Democritus Univ Thrace, Dept Elect & Comp Engn, Database & Informat Retrieval Res unit, GR-67100 Xanthi, Greece; [Sylaios, Georgios] Democritus Univ Thrace, Dept Environm Engn, Lab Ecol Engn & Technol, GR-67100 Xanthi, Greece
Reprint Address Effrosynidis, D (corresponding author), Democritus Univ Thrace, Dept Elect & Comp Engn, Database & Informat Retrieval Res unit, GR-67100 Xanthi, Greece.
E-mail Address deffrosy@ee.duth.gr; avi@ee.duth.gr; gsylaios@env.duth.gr
ResearcherID Number Sylaios, Georgios/AAM-6994-2020
ORCID Number SYLAIOS, GEORGIOS/0000-0003-2327-4015
Funding Agency and Grant Number European UnionEuropean Union (EU) [H2020-BG-12-2016-2, 727277]
Funding Text The research leading to these results received funding from the European Union's Horizon 2020 Research and Innovation Program (H2020-BG-12-2016-2) under grant agreement No. 727277 - ODYSSEA (Towards an integrated Mediterranean Sea Observing System). The article reflects only authors' view and that the Commission is not responsible for any use that may be made of the information it contains. The authors wish to thank Corine Martin (UNEP-WCMC) for providing the database.
Times Cited 4
Total Times Cited Count (WoS, BCI, and CSCD) 4
Publisher ELSEVIER
Publisher City AMSTERDAM
Publisher Address RADARWEG 29, 1043 NX AMSTERDAM, NETHERLANDS
ISSN 1574-9541
29-Character Source Abbreviation ECOL INFORM
ISO Source Abbreviation Ecol. Inform.
Publication Date NOV
Year Published 2018
Volume 48
Beginning Page 158
Ending Page 170
Digital Object Identifier (DOI) 10.1016/j.ecoinf.2018.09.004
Page Count 13
Web of Science Category Ecology
Subject Category Environmental Sciences & Ecology
Document Delivery Number HE7TC
Unique Article Identifier WOS:000453641900016
Plants associated with this reference

LEGAL NOTICES — This website is protected by Copyright © The University of Sussex, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022. The eHALOPH database is protected by Database Right and Copyright © The University of Sussex and other contributors, 2006, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022. This database is based on an earlier work by James Aronson.
THIS WEBSITE AND THIS DATABASE ARE PROVIDED ON AN "AS IS" BASIS, AND YOU USE THEM AND RELY ON THEM AT YOUR OWN RISK.

Contact email: halophytes@sussex.ac.uk
Credits – Tim Flowers, Joaquim Santos, Moritz Jahns, Brian Warburton, Peter Reed