Spatial Analysis of Intra-Annual Reed Ecosystem Dynamics at Lake Neusiedl Using RGB Drone Imagery and Deep Learning
The reed belt of Lake Neusiedl, covering half the size of the lake, is subject to massive changes due to the strong decline of the water level over the last several years, especially in 2021. In this study, we investigated the spatial and temporal variations within a long-term ecosystem research (LT...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/16/3961 |
| _version_ | 1827728775047020544 |
|---|---|
| author | Claudia Buchsteiner Pamela Alessandra Baur Stephan Glatzel |
| author_facet | Claudia Buchsteiner Pamela Alessandra Baur Stephan Glatzel |
| author_sort | Claudia Buchsteiner |
| collection | DOAJ |
| description | The reed belt of Lake Neusiedl, covering half the size of the lake, is subject to massive changes due to the strong decline of the water level over the last several years, especially in 2021. In this study, we investigated the spatial and temporal variations within a long-term ecosystem research (LTER) site in a reed ecosystem at Lake Neusiedl in Austria under intense drought conditions. Spatio-temporal data sets from May to November 2021 were produced to analyze and detect changes in the wetland ecosystem over a single vegetation period. High-resolution orthomosaics processed from RGB imagery taken with an unmanned aerial vehicle (UAV) served as the basis for land cover classification and phenological analysis. An image annotation workflow was developed, and deep learning techniques using semantic image segmentation were applied to map land cover changes. The trained models delivered highly favorable results in terms of the assessed performance metrics. When considering the region between their minima and maxima, the water surface area decreased by 26.9%, the sediment area increased by 23.1%, and the vegetation area increased successively by 10.1% over the investigation period. Phenocam data for lateral phenological monitoring of the vegetation development of <i>Phragmites australis</i> was directly compared with phenological analysis from aerial imagery. This study reveals the enormous dynamics of the reed ecosystem of Lake Neusiedl, and additionally confirms the importance of remote sensing via drone and the strengths of deep learning for wetland classification. |
| first_indexed | 2024-03-10T23:36:40Z |
| format | Article |
| id | doaj.art-734e25dde77b40c09aee32139ed39bec |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:36:40Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-734e25dde77b40c09aee32139ed39bec2023-11-19T02:52:34ZengMDPI AGRemote Sensing2072-42922023-08-011516396110.3390/rs15163961Spatial Analysis of Intra-Annual Reed Ecosystem Dynamics at Lake Neusiedl Using RGB Drone Imagery and Deep LearningClaudia Buchsteiner0Pamela Alessandra Baur1Stephan Glatzel2Working Group Geoecology, Department of Geography and Regional Research, Faculty of Earth Sciences, Geography and Astronomy, University of Vienna, Josef-Holaubek-Platz 2, 1090 Vienna, AustriaWorking Group Geoecology, Department of Geography and Regional Research, Faculty of Earth Sciences, Geography and Astronomy, University of Vienna, Josef-Holaubek-Platz 2, 1090 Vienna, AustriaWorking Group Geoecology, Department of Geography and Regional Research, Faculty of Earth Sciences, Geography and Astronomy, University of Vienna, Josef-Holaubek-Platz 2, 1090 Vienna, AustriaThe reed belt of Lake Neusiedl, covering half the size of the lake, is subject to massive changes due to the strong decline of the water level over the last several years, especially in 2021. In this study, we investigated the spatial and temporal variations within a long-term ecosystem research (LTER) site in a reed ecosystem at Lake Neusiedl in Austria under intense drought conditions. Spatio-temporal data sets from May to November 2021 were produced to analyze and detect changes in the wetland ecosystem over a single vegetation period. High-resolution orthomosaics processed from RGB imagery taken with an unmanned aerial vehicle (UAV) served as the basis for land cover classification and phenological analysis. An image annotation workflow was developed, and deep learning techniques using semantic image segmentation were applied to map land cover changes. The trained models delivered highly favorable results in terms of the assessed performance metrics. When considering the region between their minima and maxima, the water surface area decreased by 26.9%, the sediment area increased by 23.1%, and the vegetation area increased successively by 10.1% over the investigation period. Phenocam data for lateral phenological monitoring of the vegetation development of <i>Phragmites australis</i> was directly compared with phenological analysis from aerial imagery. This study reveals the enormous dynamics of the reed ecosystem of Lake Neusiedl, and additionally confirms the importance of remote sensing via drone and the strengths of deep learning for wetland classification.https://www.mdpi.com/2072-4292/15/16/3961Lake NeusiedlreedLTERland cover classificationdeep learningDeepLabv3+ |
| spellingShingle | Claudia Buchsteiner Pamela Alessandra Baur Stephan Glatzel Spatial Analysis of Intra-Annual Reed Ecosystem Dynamics at Lake Neusiedl Using RGB Drone Imagery and Deep Learning Remote Sensing Lake Neusiedl reed LTER land cover classification deep learning DeepLabv3+ |
| title | Spatial Analysis of Intra-Annual Reed Ecosystem Dynamics at Lake Neusiedl Using RGB Drone Imagery and Deep Learning |
| title_full | Spatial Analysis of Intra-Annual Reed Ecosystem Dynamics at Lake Neusiedl Using RGB Drone Imagery and Deep Learning |
| title_fullStr | Spatial Analysis of Intra-Annual Reed Ecosystem Dynamics at Lake Neusiedl Using RGB Drone Imagery and Deep Learning |
| title_full_unstemmed | Spatial Analysis of Intra-Annual Reed Ecosystem Dynamics at Lake Neusiedl Using RGB Drone Imagery and Deep Learning |
| title_short | Spatial Analysis of Intra-Annual Reed Ecosystem Dynamics at Lake Neusiedl Using RGB Drone Imagery and Deep Learning |
| title_sort | spatial analysis of intra annual reed ecosystem dynamics at lake neusiedl using rgb drone imagery and deep learning |
| topic | Lake Neusiedl reed LTER land cover classification deep learning DeepLabv3+ |
| url | https://www.mdpi.com/2072-4292/15/16/3961 |
| work_keys_str_mv | AT claudiabuchsteiner spatialanalysisofintraannualreedecosystemdynamicsatlakeneusiedlusingrgbdroneimageryanddeeplearning AT pamelaalessandrabaur spatialanalysisofintraannualreedecosystemdynamicsatlakeneusiedlusingrgbdroneimageryanddeeplearning AT stephanglatzel spatialanalysisofintraannualreedecosystemdynamicsatlakeneusiedlusingrgbdroneimageryanddeeplearning |