SeagrassFinder: Deep learning for eelgrass detection and coverage estimation in the wild
Seagrass meadows play a crucial role in marine ecosystems, providing benefits such as carbon sequestration, water quality improvement, and habitat provision. Monitoring the distribution and abundance of seagrass is essential for environmental impact assessments and conservation efforts. However, the...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954125002092 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849233594692665344 |
|---|---|
| author | Jannik Elsäßer Laura Weihl Veronika Cheplygina Lisbeth Tangaa Nielsen |
| author_facet | Jannik Elsäßer Laura Weihl Veronika Cheplygina Lisbeth Tangaa Nielsen |
| author_sort | Jannik Elsäßer |
| collection | DOAJ |
| description | Seagrass meadows play a crucial role in marine ecosystems, providing benefits such as carbon sequestration, water quality improvement, and habitat provision. Monitoring the distribution and abundance of seagrass is essential for environmental impact assessments and conservation efforts. However, the current manual methods of analyzing underwater video data to assess seagrass coverage are time-consuming and subjective. This work explores the use of deep learning models to automate the process of seagrass detection and coverage estimation from underwater video data. We create a new dataset of over 8,300 annotated underwater images, and subsequently evaluate several deep learning architectures, including ResNet, InceptionNetV3, DenseNet, and Vision Transformer for the task of binary classification on the presence and absence of seagrass by transfer learning. The results demonstrate that deep learning models, particularly Vision Transformers, can achieve high performance in predicting eelgrass presence, with AUROC scores exceeding 0.95 on the final test dataset. The application of underwater image enhancement further improved the models’ prediction capabilities. Furthermore, we introduce a novel approach for estimating seagrass coverage from video data, showing promising preliminary results that align with expert manual labels, and indicating potential for consistent and scalable monitoring. The proposed methodology allows for the efficient processing of large volumes of video data, enabling the acquisition of much more detailed information on seagrass distributions in comparison to current manual methods. This information is crucial for environmental impact assessments and monitoring programs, as seagrasses are important indicators of coastal ecosystem health. This project demonstrates the value that deep learning can bring to the field of marine ecology and environmental monitoring. |
| format | Article |
| id | doaj-art-2e36a18ea7bc4ae4936dae3f6e742309 |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-2e36a18ea7bc4ae4936dae3f6e7423092025-08-20T05:05:02ZengElsevierEcological Informatics1574-95412025-12-019010320010.1016/j.ecoinf.2025.103200SeagrassFinder: Deep learning for eelgrass detection and coverage estimation in the wildJannik Elsäßer0Laura Weihl1Veronika Cheplygina2Lisbeth Tangaa Nielsen3DHI A/S, Agern Allé 5, Hørsholm, 2970, DenmarkComputer Science Department, IT University of Copenhagen, Rued Langaards Vej 7, Copenhagen, 2300, Denmark; Corresponding author.Computer Science Department, IT University of Copenhagen, Rued Langaards Vej 7, Copenhagen, 2300, DenmarkDHI A/S, Agern Allé 5, Hørsholm, 2970, DenmarkSeagrass meadows play a crucial role in marine ecosystems, providing benefits such as carbon sequestration, water quality improvement, and habitat provision. Monitoring the distribution and abundance of seagrass is essential for environmental impact assessments and conservation efforts. However, the current manual methods of analyzing underwater video data to assess seagrass coverage are time-consuming and subjective. This work explores the use of deep learning models to automate the process of seagrass detection and coverage estimation from underwater video data. We create a new dataset of over 8,300 annotated underwater images, and subsequently evaluate several deep learning architectures, including ResNet, InceptionNetV3, DenseNet, and Vision Transformer for the task of binary classification on the presence and absence of seagrass by transfer learning. The results demonstrate that deep learning models, particularly Vision Transformers, can achieve high performance in predicting eelgrass presence, with AUROC scores exceeding 0.95 on the final test dataset. The application of underwater image enhancement further improved the models’ prediction capabilities. Furthermore, we introduce a novel approach for estimating seagrass coverage from video data, showing promising preliminary results that align with expert manual labels, and indicating potential for consistent and scalable monitoring. The proposed methodology allows for the efficient processing of large volumes of video data, enabling the acquisition of much more detailed information on seagrass distributions in comparison to current manual methods. This information is crucial for environmental impact assessments and monitoring programs, as seagrasses are important indicators of coastal ecosystem health. This project demonstrates the value that deep learning can bring to the field of marine ecology and environmental monitoring.http://www.sciencedirect.com/science/article/pii/S1574954125002092Ecological monitoringMarine biologyMarine ecologyMarine imagingDeep learningComputer vision |
| spellingShingle | Jannik Elsäßer Laura Weihl Veronika Cheplygina Lisbeth Tangaa Nielsen SeagrassFinder: Deep learning for eelgrass detection and coverage estimation in the wild Ecological Informatics Ecological monitoring Marine biology Marine ecology Marine imaging Deep learning Computer vision |
| title | SeagrassFinder: Deep learning for eelgrass detection and coverage estimation in the wild |
| title_full | SeagrassFinder: Deep learning for eelgrass detection and coverage estimation in the wild |
| title_fullStr | SeagrassFinder: Deep learning for eelgrass detection and coverage estimation in the wild |
| title_full_unstemmed | SeagrassFinder: Deep learning for eelgrass detection and coverage estimation in the wild |
| title_short | SeagrassFinder: Deep learning for eelgrass detection and coverage estimation in the wild |
| title_sort | seagrassfinder deep learning for eelgrass detection and coverage estimation in the wild |
| topic | Ecological monitoring Marine biology Marine ecology Marine imaging Deep learning Computer vision |
| url | http://www.sciencedirect.com/science/article/pii/S1574954125002092 |
| work_keys_str_mv | AT jannikelsaßer seagrassfinderdeeplearningforeelgrassdetectionandcoverageestimationinthewild AT lauraweihl seagrassfinderdeeplearningforeelgrassdetectionandcoverageestimationinthewild AT veronikacheplygina seagrassfinderdeeplearningforeelgrassdetectionandcoverageestimationinthewild AT lisbethtangaanielsen seagrassfinderdeeplearningforeelgrassdetectionandcoverageestimationinthewild |