Cloud Processing for Simultaneous Mapping of Seagrass Meadows in Optically Complex and Varied Water
Improved development of remote sensing approaches to deliver timely and accurate measurements for environmental monitoring, particularly with respect to marine and estuarine environments is a priority. We describe a machine learning, cloud processing protocol for simultaneous mapping seagrass meadow...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/3/609 |
| _version_ | 1827659034474315776 |
|---|---|
| author | Eva M. Kovacs Chris Roelfsema James Udy Simon Baltais Mitchell Lyons Stuart Phinn |
| author_facet | Eva M. Kovacs Chris Roelfsema James Udy Simon Baltais Mitchell Lyons Stuart Phinn |
| author_sort | Eva M. Kovacs |
| collection | DOAJ |
| description | Improved development of remote sensing approaches to deliver timely and accurate measurements for environmental monitoring, particularly with respect to marine and estuarine environments is a priority. We describe a machine learning, cloud processing protocol for simultaneous mapping seagrass meadows in waters of variable quality across Moreton Bay, Australia. This method was adapted from a protocol developed for mapping coral reef areas. Georeferenced spot check field-survey data were obtained across Moreton Bay, covering areas of differing water quality, and categorized into either substrate or ≥25% seagrass cover. These point data with coincident Landsat 8 OLI satellite imagery (30 m resolution; pulled directly from Google Earth Engine’s public archive) and a bathymetric layer (30 m resolution) were incorporated to train a random forest classifier. The semiautomated machine learning algorithm was applied to map seagrass in shallow areas of variable water quality simultaneously, and a bay-wide map was created for Moreton Bay. The output benthic habitat map representing seagrass presence/absence was accurate (63%) as determined by validation with an independent data set. |
| first_indexed | 2024-03-09T23:13:54Z |
| format | Article |
| id | doaj.art-a223fdbf2eca4b13bbb2884c520883de |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T23:13:54Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a223fdbf2eca4b13bbb2884c520883de2023-11-23T17:40:35ZengMDPI AGRemote Sensing2072-42922022-01-0114360910.3390/rs14030609Cloud Processing for Simultaneous Mapping of Seagrass Meadows in Optically Complex and Varied WaterEva M. Kovacs0Chris Roelfsema1James Udy2Simon Baltais3Mitchell Lyons4Stuart Phinn5Remote Sensing Research Centre, School of Earth and Environmental Science, The University of Brisbane, Brisbane, QLD 4072, AustraliaRemote Sensing Research Centre, School of Earth and Environmental Science, The University of Brisbane, Brisbane, QLD 4072, AustraliaScience Under Sail, Wellington Point, City of Redland, QLD 4160, AustraliaThe Wildlife Preservation Society of Queensland Bayside Branch (QLD) Inc., Brisbane, QLD 4101, AustraliaRemote Sensing Research Centre, School of Earth and Environmental Science, The University of Brisbane, Brisbane, QLD 4072, AustraliaRemote Sensing Research Centre, School of Earth and Environmental Science, The University of Brisbane, Brisbane, QLD 4072, AustraliaImproved development of remote sensing approaches to deliver timely and accurate measurements for environmental monitoring, particularly with respect to marine and estuarine environments is a priority. We describe a machine learning, cloud processing protocol for simultaneous mapping seagrass meadows in waters of variable quality across Moreton Bay, Australia. This method was adapted from a protocol developed for mapping coral reef areas. Georeferenced spot check field-survey data were obtained across Moreton Bay, covering areas of differing water quality, and categorized into either substrate or ≥25% seagrass cover. These point data with coincident Landsat 8 OLI satellite imagery (30 m resolution; pulled directly from Google Earth Engine’s public archive) and a bathymetric layer (30 m resolution) were incorporated to train a random forest classifier. The semiautomated machine learning algorithm was applied to map seagrass in shallow areas of variable water quality simultaneously, and a bay-wide map was created for Moreton Bay. The output benthic habitat map representing seagrass presence/absence was accurate (63%) as determined by validation with an independent data set.https://www.mdpi.com/2072-4292/14/3/609seagrasswater qualitycloud processingMoreton Baymachine learningfield data |
| spellingShingle | Eva M. Kovacs Chris Roelfsema James Udy Simon Baltais Mitchell Lyons Stuart Phinn Cloud Processing for Simultaneous Mapping of Seagrass Meadows in Optically Complex and Varied Water Remote Sensing seagrass water quality cloud processing Moreton Bay machine learning field data |
| title | Cloud Processing for Simultaneous Mapping of Seagrass Meadows in Optically Complex and Varied Water |
| title_full | Cloud Processing for Simultaneous Mapping of Seagrass Meadows in Optically Complex and Varied Water |
| title_fullStr | Cloud Processing for Simultaneous Mapping of Seagrass Meadows in Optically Complex and Varied Water |
| title_full_unstemmed | Cloud Processing for Simultaneous Mapping of Seagrass Meadows in Optically Complex and Varied Water |
| title_short | Cloud Processing for Simultaneous Mapping of Seagrass Meadows in Optically Complex and Varied Water |
| title_sort | cloud processing for simultaneous mapping of seagrass meadows in optically complex and varied water |
| topic | seagrass water quality cloud processing Moreton Bay machine learning field data |
| url | https://www.mdpi.com/2072-4292/14/3/609 |
| work_keys_str_mv | AT evamkovacs cloudprocessingforsimultaneousmappingofseagrassmeadowsinopticallycomplexandvariedwater AT chrisroelfsema cloudprocessingforsimultaneousmappingofseagrassmeadowsinopticallycomplexandvariedwater AT jamesudy cloudprocessingforsimultaneousmappingofseagrassmeadowsinopticallycomplexandvariedwater AT simonbaltais cloudprocessingforsimultaneousmappingofseagrassmeadowsinopticallycomplexandvariedwater AT mitchelllyons cloudprocessingforsimultaneousmappingofseagrassmeadowsinopticallycomplexandvariedwater AT stuartphinn cloudprocessingforsimultaneousmappingofseagrassmeadowsinopticallycomplexandvariedwater |