Disturbance Mapping in Arctic Tundra Improved by a Planning Workflow for Drone Studies: Advancing Tools for Future Ecosystem Monitoring
The Arctic is under great pressure due to climate change. Drones are increasingly used as a tool in ecology and may be especially valuable in rapidly changing and remote landscapes, as can be found in the Arctic. For effective applications of drones, decisions of both ecological and technical charac...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/21/4466 |
| _version_ | 1797511829343174656 |
|---|---|
| author | Isabell Eischeid Eeva M. Soininen Jakob J. Assmann Rolf A. Ims Jesper Madsen Åshild Ø. Pedersen Francesco Pirotti Nigel G. Yoccoz Virve T. Ravolainen |
| author_facet | Isabell Eischeid Eeva M. Soininen Jakob J. Assmann Rolf A. Ims Jesper Madsen Åshild Ø. Pedersen Francesco Pirotti Nigel G. Yoccoz Virve T. Ravolainen |
| author_sort | Isabell Eischeid |
| collection | DOAJ |
| description | The Arctic is under great pressure due to climate change. Drones are increasingly used as a tool in ecology and may be especially valuable in rapidly changing and remote landscapes, as can be found in the Arctic. For effective applications of drones, decisions of both ecological and technical character are needed. Here, we provide our method planning workflow for generating ground-cover maps with drones for ecological monitoring purposes. The workflow includes the selection of variables, layer resolutions, ground-cover classes and the development and validation of models. We implemented this workflow in a case study of the Arctic tundra to develop vegetation maps, including disturbed vegetation, at three study sites in Svalbard. For each site, we generated a high-resolution map of tundra vegetation using supervised random forest (RF) classifiers based on four spectral bands, the normalized difference vegetation index (NDVI) and three types of terrain variables—all derived from drone imagery. Our classifiers distinguished up to 15 different ground-cover classes, including two classes that identify vegetation state changes due to disturbance caused by herbivory (i.e., goose grubbing) and winter damage (i.e., ‘rain-on-snow’ and thaw-freeze). Areas classified as goose grubbing or winter damage had lower NDVI values than their undisturbed counterparts. The predictive ability of site-specific RF models was good (macro-F1 scores between 83% and 85%), but the area of the grubbing class was overestimated in parts of the moss tundra. A direct transfer of the models between study sites was not possible (macro-F1 scores under 50%). We show that drone image analysis can be an asset for studying future vegetation state changes on local scales in Arctic tundra ecosystems and encourage ecologists to use our tailored workflow to integrate drone mapping into long-term monitoring programs. |
| first_indexed | 2024-03-10T05:52:33Z |
| format | Article |
| id | doaj.art-0a4bff786604402896281db7f08f5ca9 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T05:52:33Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0a4bff786604402896281db7f08f5ca92023-11-22T21:33:54ZengMDPI AGRemote Sensing2072-42922021-11-011321446610.3390/rs13214466Disturbance Mapping in Arctic Tundra Improved by a Planning Workflow for Drone Studies: Advancing Tools for Future Ecosystem MonitoringIsabell Eischeid0Eeva M. Soininen1Jakob J. Assmann2Rolf A. Ims3Jesper Madsen4Åshild Ø. Pedersen5Francesco Pirotti6Nigel G. Yoccoz7Virve T. Ravolainen8Department of Arctic and Marine Biology, UiT The Arctic University of Norway, 9037 Tromsø, NorwayDepartment of Arctic and Marine Biology, UiT The Arctic University of Norway, 9037 Tromsø, NorwayDepartment of Biology—Ecoinformatics and Biodiversity, Aarhus University, 8000 Aarhus C, DenmarkDepartment of Arctic and Marine Biology, UiT The Arctic University of Norway, 9037 Tromsø, NorwayDepartment of Ecoscience, Aarhus University, 8410 Rønde, DenmarkFram Centre, Norwegian Polar Institute, 9296 Tromsø, NorwayCIRGEO Interdepartmental Research Center of Geomatics, TESAF Department, University of Padova, Viale dell’Università 16, 35020 Legnaro, ItalyDepartment of Arctic and Marine Biology, UiT The Arctic University of Norway, 9037 Tromsø, NorwayFram Centre, Norwegian Polar Institute, 9296 Tromsø, NorwayThe Arctic is under great pressure due to climate change. Drones are increasingly used as a tool in ecology and may be especially valuable in rapidly changing and remote landscapes, as can be found in the Arctic. For effective applications of drones, decisions of both ecological and technical character are needed. Here, we provide our method planning workflow for generating ground-cover maps with drones for ecological monitoring purposes. The workflow includes the selection of variables, layer resolutions, ground-cover classes and the development and validation of models. We implemented this workflow in a case study of the Arctic tundra to develop vegetation maps, including disturbed vegetation, at three study sites in Svalbard. For each site, we generated a high-resolution map of tundra vegetation using supervised random forest (RF) classifiers based on four spectral bands, the normalized difference vegetation index (NDVI) and three types of terrain variables—all derived from drone imagery. Our classifiers distinguished up to 15 different ground-cover classes, including two classes that identify vegetation state changes due to disturbance caused by herbivory (i.e., goose grubbing) and winter damage (i.e., ‘rain-on-snow’ and thaw-freeze). Areas classified as goose grubbing or winter damage had lower NDVI values than their undisturbed counterparts. The predictive ability of site-specific RF models was good (macro-F1 scores between 83% and 85%), but the area of the grubbing class was overestimated in parts of the moss tundra. A direct transfer of the models between study sites was not possible (macro-F1 scores under 50%). We show that drone image analysis can be an asset for studying future vegetation state changes on local scales in Arctic tundra ecosystems and encourage ecologists to use our tailored workflow to integrate drone mapping into long-term monitoring programs.https://www.mdpi.com/2072-4292/13/21/4466classifierdisturbancedroneecological monitoringGLCMherbivore |
| spellingShingle | Isabell Eischeid Eeva M. Soininen Jakob J. Assmann Rolf A. Ims Jesper Madsen Åshild Ø. Pedersen Francesco Pirotti Nigel G. Yoccoz Virve T. Ravolainen Disturbance Mapping in Arctic Tundra Improved by a Planning Workflow for Drone Studies: Advancing Tools for Future Ecosystem Monitoring Remote Sensing classifier disturbance drone ecological monitoring GLCM herbivore |
| title | Disturbance Mapping in Arctic Tundra Improved by a Planning Workflow for Drone Studies: Advancing Tools for Future Ecosystem Monitoring |
| title_full | Disturbance Mapping in Arctic Tundra Improved by a Planning Workflow for Drone Studies: Advancing Tools for Future Ecosystem Monitoring |
| title_fullStr | Disturbance Mapping in Arctic Tundra Improved by a Planning Workflow for Drone Studies: Advancing Tools for Future Ecosystem Monitoring |
| title_full_unstemmed | Disturbance Mapping in Arctic Tundra Improved by a Planning Workflow for Drone Studies: Advancing Tools for Future Ecosystem Monitoring |
| title_short | Disturbance Mapping in Arctic Tundra Improved by a Planning Workflow for Drone Studies: Advancing Tools for Future Ecosystem Monitoring |
| title_sort | disturbance mapping in arctic tundra improved by a planning workflow for drone studies advancing tools for future ecosystem monitoring |
| topic | classifier disturbance drone ecological monitoring GLCM herbivore |
| url | https://www.mdpi.com/2072-4292/13/21/4466 |
| work_keys_str_mv | AT isabelleischeid disturbancemappinginarctictundraimprovedbyaplanningworkflowfordronestudiesadvancingtoolsforfutureecosystemmonitoring AT eevamsoininen disturbancemappinginarctictundraimprovedbyaplanningworkflowfordronestudiesadvancingtoolsforfutureecosystemmonitoring AT jakobjassmann disturbancemappinginarctictundraimprovedbyaplanningworkflowfordronestudiesadvancingtoolsforfutureecosystemmonitoring AT rolfaims disturbancemappinginarctictundraimprovedbyaplanningworkflowfordronestudiesadvancingtoolsforfutureecosystemmonitoring AT jespermadsen disturbancemappinginarctictundraimprovedbyaplanningworkflowfordronestudiesadvancingtoolsforfutureecosystemmonitoring AT ashildøpedersen disturbancemappinginarctictundraimprovedbyaplanningworkflowfordronestudiesadvancingtoolsforfutureecosystemmonitoring AT francescopirotti disturbancemappinginarctictundraimprovedbyaplanningworkflowfordronestudiesadvancingtoolsforfutureecosystemmonitoring AT nigelgyoccoz disturbancemappinginarctictundraimprovedbyaplanningworkflowfordronestudiesadvancingtoolsforfutureecosystemmonitoring AT virvetravolainen disturbancemappinginarctictundraimprovedbyaplanningworkflowfordronestudiesadvancingtoolsforfutureecosystemmonitoring |