Leveraging citizen science to classify and track benthic habitat states: An unsupervised UMAP-HDBSCAN pipeline applied to the global reef life survey dataset
Benthic biogenic habitats are crucial for coastal marine ecosystems, supporting food and shelter for a large range of marine species, but they are increasingly threatened by increasing anthropogenic impacts. While large-scale monitoring data are increasingly available, tools to describe benthic habi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-05-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954125000676 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850079237172625408 |
|---|---|
| author | Clément Violet Aurélien Boyé Stanislas Dubois Graham J. Edgar Elizabeth S. Oh Rick D. Stuart-Smith Martin P. Marzloff |
| author_facet | Clément Violet Aurélien Boyé Stanislas Dubois Graham J. Edgar Elizabeth S. Oh Rick D. Stuart-Smith Martin P. Marzloff |
| author_sort | Clément Violet |
| collection | DOAJ |
| description | Benthic biogenic habitats are crucial for coastal marine ecosystems, supporting food and shelter for a large range of marine species, but they are increasingly threatened by increasing anthropogenic impacts. While large-scale monitoring data are increasingly available, tools to describe benthic habitat changes in standardised and yet finely resolved manner are still needed. The aim of this study was to define reef benthic habitat states and explore their spatial and temporal variability on a global scale using an innovative clustering pipeline. For this purpose, we used substrate cover data collected along 6554 transects worldwide by citizen scientists contributing to the Reef Life Survey program. We applied an innovative clustering pipeline that combines three algorithms — Uniform Manifold Approximation and Projection (UMAP) for dimension reduction; Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) — to identify benthic habitat states and Shapley values to interpret the clusters identified. This unsupervised pipeline identified 17 distinct clusters worldwide, representing typical temperate and tropical benthic habitats such as large canopy forming algae and branching corals, respectively, as well as transitional states between different habitat states. Temporal site-specific analyses further demonstrated the pipeline's effectiveness in capturing fine-scale habitat dynamics. By providing a standardised, scalable approach, this work enables consistent tracking of benthic habitat changes across spatial and temporal scales worldwide. This study also showcases the potential of integrating the UMAP-HDBSCAN pipeline with Shapley values for clustering noisy ecological data from citizen science initiatives. |
| format | Article |
| id | doaj-art-1488cf9d303d4e09843a2a8b4ffbd82e |
| institution | DOAJ |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-1488cf9d303d4e09843a2a8b4ffbd82e2025-08-20T02:45:18ZengElsevierEcological Informatics1574-95412025-05-018610305810.1016/j.ecoinf.2025.103058Leveraging citizen science to classify and track benthic habitat states: An unsupervised UMAP-HDBSCAN pipeline applied to the global reef life survey datasetClément Violet0Aurélien Boyé1Stanislas Dubois2Graham J. Edgar3Elizabeth S. Oh4Rick D. Stuart-Smith5Martin P. Marzloff6Ifremer, Centre de Bretagne, DYNECO LEBCO, Plouzané, France; Corresponding author.Ifremer, Centre de Bretagne, DYNECO LEBCO, Plouzané, FranceIfremer, Centre de Bretagne, DYNECO LEBCO, Plouzané, FranceInstitute for Marine and Antarctic Studies (IMAS), University of Tasmania, Hobart, Tasmania, AustraliaInstitute for Marine and Antarctic Studies (IMAS), University of Tasmania, Hobart, Tasmania, AustraliaInstitute for Marine and Antarctic Studies (IMAS), University of Tasmania, Hobart, Tasmania, AustraliaIfremer, Centre de Bretagne, DYNECO LEBCO, Plouzané, FranceBenthic biogenic habitats are crucial for coastal marine ecosystems, supporting food and shelter for a large range of marine species, but they are increasingly threatened by increasing anthropogenic impacts. While large-scale monitoring data are increasingly available, tools to describe benthic habitat changes in standardised and yet finely resolved manner are still needed. The aim of this study was to define reef benthic habitat states and explore their spatial and temporal variability on a global scale using an innovative clustering pipeline. For this purpose, we used substrate cover data collected along 6554 transects worldwide by citizen scientists contributing to the Reef Life Survey program. We applied an innovative clustering pipeline that combines three algorithms — Uniform Manifold Approximation and Projection (UMAP) for dimension reduction; Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) — to identify benthic habitat states and Shapley values to interpret the clusters identified. This unsupervised pipeline identified 17 distinct clusters worldwide, representing typical temperate and tropical benthic habitats such as large canopy forming algae and branching corals, respectively, as well as transitional states between different habitat states. Temporal site-specific analyses further demonstrated the pipeline's effectiveness in capturing fine-scale habitat dynamics. By providing a standardised, scalable approach, this work enables consistent tracking of benthic habitat changes across spatial and temporal scales worldwide. This study also showcases the potential of integrating the UMAP-HDBSCAN pipeline with Shapley values for clustering noisy ecological data from citizen science initiatives.http://www.sciencedirect.com/science/article/pii/S1574954125000676Benthic habitatCitizen scienceClusteringHabitat statesHDBSCANUMAP |
| spellingShingle | Clément Violet Aurélien Boyé Stanislas Dubois Graham J. Edgar Elizabeth S. Oh Rick D. Stuart-Smith Martin P. Marzloff Leveraging citizen science to classify and track benthic habitat states: An unsupervised UMAP-HDBSCAN pipeline applied to the global reef life survey dataset Ecological Informatics Benthic habitat Citizen science Clustering Habitat states HDBSCAN UMAP |
| title | Leveraging citizen science to classify and track benthic habitat states: An unsupervised UMAP-HDBSCAN pipeline applied to the global reef life survey dataset |
| title_full | Leveraging citizen science to classify and track benthic habitat states: An unsupervised UMAP-HDBSCAN pipeline applied to the global reef life survey dataset |
| title_fullStr | Leveraging citizen science to classify and track benthic habitat states: An unsupervised UMAP-HDBSCAN pipeline applied to the global reef life survey dataset |
| title_full_unstemmed | Leveraging citizen science to classify and track benthic habitat states: An unsupervised UMAP-HDBSCAN pipeline applied to the global reef life survey dataset |
| title_short | Leveraging citizen science to classify and track benthic habitat states: An unsupervised UMAP-HDBSCAN pipeline applied to the global reef life survey dataset |
| title_sort | leveraging citizen science to classify and track benthic habitat states an unsupervised umap hdbscan pipeline applied to the global reef life survey dataset |
| topic | Benthic habitat Citizen science Clustering Habitat states HDBSCAN UMAP |
| url | http://www.sciencedirect.com/science/article/pii/S1574954125000676 |
| work_keys_str_mv | AT clementviolet leveragingcitizensciencetoclassifyandtrackbenthichabitatstatesanunsupervisedumaphdbscanpipelineappliedtotheglobalreeflifesurveydataset AT aurelienboye leveragingcitizensciencetoclassifyandtrackbenthichabitatstatesanunsupervisedumaphdbscanpipelineappliedtotheglobalreeflifesurveydataset AT stanislasdubois leveragingcitizensciencetoclassifyandtrackbenthichabitatstatesanunsupervisedumaphdbscanpipelineappliedtotheglobalreeflifesurveydataset AT grahamjedgar leveragingcitizensciencetoclassifyandtrackbenthichabitatstatesanunsupervisedumaphdbscanpipelineappliedtotheglobalreeflifesurveydataset AT elizabethsoh leveragingcitizensciencetoclassifyandtrackbenthichabitatstatesanunsupervisedumaphdbscanpipelineappliedtotheglobalreeflifesurveydataset AT rickdstuartsmith leveragingcitizensciencetoclassifyandtrackbenthichabitatstatesanunsupervisedumaphdbscanpipelineappliedtotheglobalreeflifesurveydataset AT martinpmarzloff leveragingcitizensciencetoclassifyandtrackbenthichabitatstatesanunsupervisedumaphdbscanpipelineappliedtotheglobalreeflifesurveydataset |