Assessment of Antarctic moss health from multi-sensor UAS imagery with random forest modelling
Moss beds are one of very few terrestrial vegetation types that can be found on the Antarctic continent and as such mapping their extent and monitoring their health is important to environmental managers. Across Antarctica, moss beds are experiencing changes in health as their environment changes. A...
Published in: | International Journal of Applied Earth Observation and Geoinformation |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Elsevier Science Bv
2018
|
Subjects: | |
Online Access: | https://eprints.utas.edu.au/45031/ https://doi.org/10.1016/j.jag.2018.01.004 |
id |
ftunivtasmania:oai:eprints.utas.edu.au:45031 |
---|---|
record_format |
openpolar |
spelling |
ftunivtasmania:oai:eprints.utas.edu.au:45031 2023-05-15T13:41:50+02:00 Assessment of Antarctic moss health from multi-sensor UAS imagery with random forest modelling Turner, D Lucieer, A Malenovsky, Z King, D Robinson, SA 2018 https://eprints.utas.edu.au/45031/ https://doi.org/10.1016/j.jag.2018.01.004 unknown Elsevier Science Bv Turner, D orcid:0000-0002-3029-6717 , Lucieer, A orcid:0000-0002-9468-4516 , Malenovsky, Z orcid:0000-0002-1271-8103 , King, D and Robinson, SA 2018 , 'Assessment of Antarctic moss health from multi-sensor UAS imagery with random forest modelling' , International Journal of Applied Earth Observation and Geoinformation, vol. 68 , pp. 168-179 , doi:10.1016/j.jag.2018.01.004 <http://dx.doi.org/10.1016/j.jag.2018.01.004>. UAV UAS random forest models Antarctica moss multispectral visible thermal digital surface model Article PeerReviewed 2018 ftunivtasmania https://doi.org/10.1016/j.jag.2018.01.004 2022-03-07T23:16:57Z Moss beds are one of very few terrestrial vegetation types that can be found on the Antarctic continent and as such mapping their extent and monitoring their health is important to environmental managers. Across Antarctica, moss beds are experiencing changes in health as their environment changes. As Antarctic moss beds are spatially fragmented with relatively small extent they require very high resolution remotely sensed imagery to monitor their distribution and dynamics. This study demonstrates that multi-sensor imagery collected by an Unmanned Aircraft System (UAS) provides a novel data source for assessment of moss health. In this study, we train a Random Forest Regression Model (RFM) with long-term field quadrats at a study site in the Windmill Islands, East Antarctica and apply it to UAS RGB and 6-band multispectral imagery, derived vegetation indices, 3D topographic data, and thermal imagery to predict moss health. Our results suggest that moss health, expressed as a percentage between 0 and 100% healthy, can be estimated with a root mean squared error (RMSE) between 7 and 12%. The RFM also quantifies the importance of input variables for moss health estimation showing the multispectral sensor data was important for accurate health prediction, such information being essential for planning future field investigations. The RFM was applied to the entire moss bed, providing an extrapolation of the health assessment across a larger spatial area. With further validation the resulting maps could be used for change detection of moss health across multiple sites and seasons. Article in Journal/Newspaper Antarc* Antarctic Antarctica East Antarctica Windmill Islands University of Tasmania: UTas ePrints Antarctic The Antarctic East Antarctica Windmill Islands ENVELOPE(110.417,110.417,-66.350,-66.350) International Journal of Applied Earth Observation and Geoinformation 68 168 179 |
institution |
Open Polar |
collection |
University of Tasmania: UTas ePrints |
op_collection_id |
ftunivtasmania |
language |
unknown |
topic |
UAV UAS random forest models Antarctica moss multispectral visible thermal digital surface model |
spellingShingle |
UAV UAS random forest models Antarctica moss multispectral visible thermal digital surface model Turner, D Lucieer, A Malenovsky, Z King, D Robinson, SA Assessment of Antarctic moss health from multi-sensor UAS imagery with random forest modelling |
topic_facet |
UAV UAS random forest models Antarctica moss multispectral visible thermal digital surface model |
description |
Moss beds are one of very few terrestrial vegetation types that can be found on the Antarctic continent and as such mapping their extent and monitoring their health is important to environmental managers. Across Antarctica, moss beds are experiencing changes in health as their environment changes. As Antarctic moss beds are spatially fragmented with relatively small extent they require very high resolution remotely sensed imagery to monitor their distribution and dynamics. This study demonstrates that multi-sensor imagery collected by an Unmanned Aircraft System (UAS) provides a novel data source for assessment of moss health. In this study, we train a Random Forest Regression Model (RFM) with long-term field quadrats at a study site in the Windmill Islands, East Antarctica and apply it to UAS RGB and 6-band multispectral imagery, derived vegetation indices, 3D topographic data, and thermal imagery to predict moss health. Our results suggest that moss health, expressed as a percentage between 0 and 100% healthy, can be estimated with a root mean squared error (RMSE) between 7 and 12%. The RFM also quantifies the importance of input variables for moss health estimation showing the multispectral sensor data was important for accurate health prediction, such information being essential for planning future field investigations. The RFM was applied to the entire moss bed, providing an extrapolation of the health assessment across a larger spatial area. With further validation the resulting maps could be used for change detection of moss health across multiple sites and seasons. |
format |
Article in Journal/Newspaper |
author |
Turner, D Lucieer, A Malenovsky, Z King, D Robinson, SA |
author_facet |
Turner, D Lucieer, A Malenovsky, Z King, D Robinson, SA |
author_sort |
Turner, D |
title |
Assessment of Antarctic moss health from multi-sensor UAS imagery with random forest modelling |
title_short |
Assessment of Antarctic moss health from multi-sensor UAS imagery with random forest modelling |
title_full |
Assessment of Antarctic moss health from multi-sensor UAS imagery with random forest modelling |
title_fullStr |
Assessment of Antarctic moss health from multi-sensor UAS imagery with random forest modelling |
title_full_unstemmed |
Assessment of Antarctic moss health from multi-sensor UAS imagery with random forest modelling |
title_sort |
assessment of antarctic moss health from multi-sensor uas imagery with random forest modelling |
publisher |
Elsevier Science Bv |
publishDate |
2018 |
url |
https://eprints.utas.edu.au/45031/ https://doi.org/10.1016/j.jag.2018.01.004 |
long_lat |
ENVELOPE(110.417,110.417,-66.350,-66.350) |
geographic |
Antarctic The Antarctic East Antarctica Windmill Islands |
geographic_facet |
Antarctic The Antarctic East Antarctica Windmill Islands |
genre |
Antarc* Antarctic Antarctica East Antarctica Windmill Islands |
genre_facet |
Antarc* Antarctic Antarctica East Antarctica Windmill Islands |
op_relation |
Turner, D orcid:0000-0002-3029-6717 , Lucieer, A orcid:0000-0002-9468-4516 , Malenovsky, Z orcid:0000-0002-1271-8103 , King, D and Robinson, SA 2018 , 'Assessment of Antarctic moss health from multi-sensor UAS imagery with random forest modelling' , International Journal of Applied Earth Observation and Geoinformation, vol. 68 , pp. 168-179 , doi:10.1016/j.jag.2018.01.004 <http://dx.doi.org/10.1016/j.jag.2018.01.004>. |
op_doi |
https://doi.org/10.1016/j.jag.2018.01.004 |
container_title |
International Journal of Applied Earth Observation and Geoinformation |
container_volume |
68 |
container_start_page |
168 |
op_container_end_page |
179 |
_version_ |
1766158971681374208 |