No Cover Image

E-Thesis 85 views 15 downloads

Quantifying functional group abundances of intertidal canopy-forming brown macroalgae: combining unmanned aerial vehicle and satellite imagery with machine learning / JOSHUA MUTTER

Swansea University Author: JOSHUA MUTTER

Abstract

Canopy-forming brown macroalgae provide structural support for a diverse range of rocky shore organisms, altering rocky coastline into vibrant coastal macroalgal forests. Intertidal macroalgae provide a range of ecosystem services, and macroalgal forest cover is considered an essential ocean variabl...

Full description

Published: Swansea University, Wales, UK 2024
Institution: Swansea University
Degree level: Master of Research
Degree name: MRes
Supervisor: Griffin, J. and Fowler, M.
URI: https://cronfa.swan.ac.uk/Record/cronfa68371
first_indexed 2024-11-28T19:47:25Z
last_indexed 2025-01-16T20:49:39Z
id cronfa68371
recordtype RisThesis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-01-16T15:37:07.5543866</datestamp><bib-version>v2</bib-version><id>68371</id><entry>2024-11-28</entry><title>Quantifying functional group abundances of intertidal canopy-forming brown macroalgae: combining unmanned aerial vehicle and satellite imagery with machine learning</title><swanseaauthors><author><sid>8e3d7d04cfb62e5f72f05bed0cb232fe</sid><firstname>JOSHUA</firstname><surname>MUTTER</surname><name>JOSHUA MUTTER</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-11-28</date><abstract>Canopy-forming brown macroalgae provide structural support for a diverse range of rocky shore organisms, altering rocky coastline into vibrant coastal macroalgal forests. Intertidal macroalgae provide a range of ecosystem services, and macroalgal forest cover is considered an essential ocean variable for monitoring the anthropogenic degradation of coastal ecosystems. Advances in remote sensing techniques, including machine learning and brown algae index (BAI), could upscale efforts to remotely map intertidal macroalgal forests using multispectral satellite imagery. However, previous machine learning application is limited to higher resolution images from small aircraft, whereas BAI regression techniques lack validation on heterogeneous or diverse intertidal forests and are limited to broad taxonomic groups containing multiple spectrally variable species. Random Forests classifiers were trained using unmanned aerial vehicle (UAV) data from four shores around the UK. I used this to predict functional group cover based on multispectral images from the European Space Agency&#x2019;s Sentinel-2 satellite both i) within the original training shores, and ii) two new sites independent of model training. Total cover estimates were compared to those from previously employed BAI regression models, and re-parameterised BAI regression models using data from the four training shores containing greater heterogeneity and diversity. Random forest models accurately predicted functional group cover during within-set cross-validation but require the incorporation of intra-species variation in reflectivity to predict group cover on novel shores containing different environmental conditions and species traits. BAI regression models provided more robust estimates of total brown macroalgal cover when fitted to data that reflects the natural range heterogeneity and diversity present in intertidal macroalgae habitats. Caution is advised when applying a single BAI regression model as factors that impact near-infra-red or green reflectance can weaken predictability, such as variations in species reflectivity. Nevertheless, results revealed that multispectral satellite imagery can upscale the mapping of intertidal macroalgal coverage around heterogeneous UK shores, improving estimations of ecosystem services and monitoring of anthropogenic degradation.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea University, Wales, UK</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Coastal Ecology, Remote Sensing, Marine Biology, Macroalgae, Intertidal, Ecosystem Functions</keywords><publishedDay>11</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-11-11</publishedDate><doi/><url/><notes>A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information.</notes><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Griffin, J. and Fowler, M.</supervisor><degreelevel>Master of Research</degreelevel><degreename>MRes</degreename><apcterm/><funders/><projectreference/><lastEdited>2025-01-16T15:37:07.5543866</lastEdited><Created>2024-11-28T13:03:24.4600691</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Biosciences, Geography and Physics - Biosciences</level></path><authors><author><firstname>JOSHUA</firstname><surname>MUTTER</surname><order>1</order></author></authors><documents><document><filename>68371__33360__e606b7d1923f4b939f203c75e543f44a.pdf</filename><originalFilename>2024_Mutter_J.final.68371.pdf</originalFilename><uploaded>2025-01-16T15:20:35.7478525</uploaded><type>Output</type><contentLength>1688859</contentLength><contentType>application/pdf</contentType><version>E-Thesis &#x2013; open access</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: The Author, Joshua Mutter, 2024</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2025-01-16T15:37:07.5543866 v2 68371 2024-11-28 Quantifying functional group abundances of intertidal canopy-forming brown macroalgae: combining unmanned aerial vehicle and satellite imagery with machine learning 8e3d7d04cfb62e5f72f05bed0cb232fe JOSHUA MUTTER JOSHUA MUTTER true false 2024-11-28 Canopy-forming brown macroalgae provide structural support for a diverse range of rocky shore organisms, altering rocky coastline into vibrant coastal macroalgal forests. Intertidal macroalgae provide a range of ecosystem services, and macroalgal forest cover is considered an essential ocean variable for monitoring the anthropogenic degradation of coastal ecosystems. Advances in remote sensing techniques, including machine learning and brown algae index (BAI), could upscale efforts to remotely map intertidal macroalgal forests using multispectral satellite imagery. However, previous machine learning application is limited to higher resolution images from small aircraft, whereas BAI regression techniques lack validation on heterogeneous or diverse intertidal forests and are limited to broad taxonomic groups containing multiple spectrally variable species. Random Forests classifiers were trained using unmanned aerial vehicle (UAV) data from four shores around the UK. I used this to predict functional group cover based on multispectral images from the European Space Agency’s Sentinel-2 satellite both i) within the original training shores, and ii) two new sites independent of model training. Total cover estimates were compared to those from previously employed BAI regression models, and re-parameterised BAI regression models using data from the four training shores containing greater heterogeneity and diversity. Random forest models accurately predicted functional group cover during within-set cross-validation but require the incorporation of intra-species variation in reflectivity to predict group cover on novel shores containing different environmental conditions and species traits. BAI regression models provided more robust estimates of total brown macroalgal cover when fitted to data that reflects the natural range heterogeneity and diversity present in intertidal macroalgae habitats. Caution is advised when applying a single BAI regression model as factors that impact near-infra-red or green reflectance can weaken predictability, such as variations in species reflectivity. Nevertheless, results revealed that multispectral satellite imagery can upscale the mapping of intertidal macroalgal coverage around heterogeneous UK shores, improving estimations of ecosystem services and monitoring of anthropogenic degradation. E-Thesis Swansea University, Wales, UK Coastal Ecology, Remote Sensing, Marine Biology, Macroalgae, Intertidal, Ecosystem Functions 11 11 2024 2024-11-11 A selection of content is redacted or is partially redacted from this thesis to protect sensitive and personal information. COLLEGE NANME COLLEGE CODE Swansea University Griffin, J. and Fowler, M. Master of Research MRes 2025-01-16T15:37:07.5543866 2024-11-28T13:03:24.4600691 Faculty of Science and Engineering School of Biosciences, Geography and Physics - Biosciences JOSHUA MUTTER 1 68371__33360__e606b7d1923f4b939f203c75e543f44a.pdf 2024_Mutter_J.final.68371.pdf 2025-01-16T15:20:35.7478525 Output 1688859 application/pdf E-Thesis – open access true Copyright: The Author, Joshua Mutter, 2024 true eng
title Quantifying functional group abundances of intertidal canopy-forming brown macroalgae: combining unmanned aerial vehicle and satellite imagery with machine learning
spellingShingle Quantifying functional group abundances of intertidal canopy-forming brown macroalgae: combining unmanned aerial vehicle and satellite imagery with machine learning
JOSHUA MUTTER
title_short Quantifying functional group abundances of intertidal canopy-forming brown macroalgae: combining unmanned aerial vehicle and satellite imagery with machine learning
title_full Quantifying functional group abundances of intertidal canopy-forming brown macroalgae: combining unmanned aerial vehicle and satellite imagery with machine learning
title_fullStr Quantifying functional group abundances of intertidal canopy-forming brown macroalgae: combining unmanned aerial vehicle and satellite imagery with machine learning
title_full_unstemmed Quantifying functional group abundances of intertidal canopy-forming brown macroalgae: combining unmanned aerial vehicle and satellite imagery with machine learning
title_sort Quantifying functional group abundances of intertidal canopy-forming brown macroalgae: combining unmanned aerial vehicle and satellite imagery with machine learning
author_id_str_mv 8e3d7d04cfb62e5f72f05bed0cb232fe
author_id_fullname_str_mv 8e3d7d04cfb62e5f72f05bed0cb232fe_***_JOSHUA MUTTER
author JOSHUA MUTTER
author2 JOSHUA MUTTER
format E-Thesis
publishDate 2024
institution Swansea University
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Biosciences, Geography and Physics - Biosciences{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Biosciences, Geography and Physics - Biosciences
document_store_str 1
active_str 0
description Canopy-forming brown macroalgae provide structural support for a diverse range of rocky shore organisms, altering rocky coastline into vibrant coastal macroalgal forests. Intertidal macroalgae provide a range of ecosystem services, and macroalgal forest cover is considered an essential ocean variable for monitoring the anthropogenic degradation of coastal ecosystems. Advances in remote sensing techniques, including machine learning and brown algae index (BAI), could upscale efforts to remotely map intertidal macroalgal forests using multispectral satellite imagery. However, previous machine learning application is limited to higher resolution images from small aircraft, whereas BAI regression techniques lack validation on heterogeneous or diverse intertidal forests and are limited to broad taxonomic groups containing multiple spectrally variable species. Random Forests classifiers were trained using unmanned aerial vehicle (UAV) data from four shores around the UK. I used this to predict functional group cover based on multispectral images from the European Space Agency’s Sentinel-2 satellite both i) within the original training shores, and ii) two new sites independent of model training. Total cover estimates were compared to those from previously employed BAI regression models, and re-parameterised BAI regression models using data from the four training shores containing greater heterogeneity and diversity. Random forest models accurately predicted functional group cover during within-set cross-validation but require the incorporation of intra-species variation in reflectivity to predict group cover on novel shores containing different environmental conditions and species traits. BAI regression models provided more robust estimates of total brown macroalgal cover when fitted to data that reflects the natural range heterogeneity and diversity present in intertidal macroalgae habitats. Caution is advised when applying a single BAI regression model as factors that impact near-infra-red or green reflectance can weaken predictability, such as variations in species reflectivity. Nevertheless, results revealed that multispectral satellite imagery can upscale the mapping of intertidal macroalgal coverage around heterogeneous UK shores, improving estimations of ecosystem services and monitoring of anthropogenic degradation.
published_date 2024-11-11T05:52:52Z
_version_ 1822017791983616000
score 11.371473

Similar Items