GEOAI FOR MARINE ECOSYSTEM MONITORING: A COMPLETE WORKFLOW TO GENERATE MAPS FROM AI MODEL PREDICTIONS
Mapping and monitoring marine ecosystems imply several challenges for data collection and processing: water depth, restricted access to locations, instrumentation costs or weather constraints for sampling, among others. Nowadays, Artificial Intelligence (AI) and Geographic Information System (GIS) o...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-06-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-archives.copernicus.org/articles/XLVIII-4-W7-2023/223/2023/isprs-archives-XLVIII-4-W7-2023-223-2023.pdf |
| _version_ | 1797797558090727424 |
|---|---|
| author | J. Talpaert Daudon M. Contini I. Urbina-Barreto B. Elliott F. Guilhaumon A. Joly S. Bonhommeau J. Barde |
| author_facet | J. Talpaert Daudon M. Contini I. Urbina-Barreto B. Elliott F. Guilhaumon A. Joly S. Bonhommeau J. Barde |
| author_sort | J. Talpaert Daudon |
| collection | DOAJ |
| description | Mapping and monitoring marine ecosystems imply several challenges for data collection and processing: water depth, restricted access to locations, instrumentation costs or weather constraints for sampling, among others. Nowadays, Artificial Intelligence (AI) and Geographic Information System (GIS) open source software can be combined in new kinds of workflows, to annotate and predict objects directly on georeferenced raster data (e.g. orthomosaics). Here, we describe and share the code of a generic method to train a deep learning model with spatial annotations and use it to directly generate model predictions as spatial features. This workflow has been tested and validated in three use cases related to marine ecosystem monitoring at different geographic scales: (i) segmentation of corals on orthomosaics made of underwater images to automate coral reef habitats mapping, (ii) detection and classification of fishing vessels on remote sensing satellite imagery to estimate a proxy of fishing effort (iii) segmentation of marine species and habitats on underwater images with a simple geolocation. Models have been successfully trained and the models predictions are displayed with maps in the three use cases. |
| first_indexed | 2024-03-13T03:50:09Z |
| format | Article |
| id | doaj.art-c0a424c0202d428dbe34ebd4ee50fb23 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-03-13T03:50:09Z |
| publishDate | 2023-06-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-c0a424c0202d428dbe34ebd4ee50fb232023-06-22T16:55:14ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342023-06-01XLVIII-4-W7-202322323010.5194/isprs-archives-XLVIII-4-W7-2023-223-2023GEOAI FOR MARINE ECOSYSTEM MONITORING: A COMPLETE WORKFLOW TO GENERATE MAPS FROM AI MODEL PREDICTIONSJ. Talpaert Daudon0M. Contini1I. Urbina-Barreto2B. Elliott3F. Guilhaumon4A. Joly5S. Bonhommeau6J. Barde7UMR Marbec, IRD, La Réunion, FranceIfremer DOI, La Réunion, FranceUMR Entropie (Future Maore Reefs), IRD, La Réunion, FranceDuke University, Duke Marine Lab, Beaufort, NC, USAUMR Entropie (Future Maore Reefs), IRD, La Réunion, FranceINRIA Zenith, Montpellier, FranceIfremer DOI, La Réunion, FranceUMR Marbec, IRD, FranceMapping and monitoring marine ecosystems imply several challenges for data collection and processing: water depth, restricted access to locations, instrumentation costs or weather constraints for sampling, among others. Nowadays, Artificial Intelligence (AI) and Geographic Information System (GIS) open source software can be combined in new kinds of workflows, to annotate and predict objects directly on georeferenced raster data (e.g. orthomosaics). Here, we describe and share the code of a generic method to train a deep learning model with spatial annotations and use it to directly generate model predictions as spatial features. This workflow has been tested and validated in three use cases related to marine ecosystem monitoring at different geographic scales: (i) segmentation of corals on orthomosaics made of underwater images to automate coral reef habitats mapping, (ii) detection and classification of fishing vessels on remote sensing satellite imagery to estimate a proxy of fishing effort (iii) segmentation of marine species and habitats on underwater images with a simple geolocation. Models have been successfully trained and the models predictions are displayed with maps in the three use cases.https://isprs-archives.copernicus.org/articles/XLVIII-4-W7-2023/223/2023/isprs-archives-XLVIII-4-W7-2023-223-2023.pdf |
| spellingShingle | J. Talpaert Daudon M. Contini I. Urbina-Barreto B. Elliott F. Guilhaumon A. Joly S. Bonhommeau J. Barde GEOAI FOR MARINE ECOSYSTEM MONITORING: A COMPLETE WORKFLOW TO GENERATE MAPS FROM AI MODEL PREDICTIONS The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | GEOAI FOR MARINE ECOSYSTEM MONITORING: A COMPLETE WORKFLOW TO GENERATE MAPS FROM AI MODEL PREDICTIONS |
| title_full | GEOAI FOR MARINE ECOSYSTEM MONITORING: A COMPLETE WORKFLOW TO GENERATE MAPS FROM AI MODEL PREDICTIONS |
| title_fullStr | GEOAI FOR MARINE ECOSYSTEM MONITORING: A COMPLETE WORKFLOW TO GENERATE MAPS FROM AI MODEL PREDICTIONS |
| title_full_unstemmed | GEOAI FOR MARINE ECOSYSTEM MONITORING: A COMPLETE WORKFLOW TO GENERATE MAPS FROM AI MODEL PREDICTIONS |
| title_short | GEOAI FOR MARINE ECOSYSTEM MONITORING: A COMPLETE WORKFLOW TO GENERATE MAPS FROM AI MODEL PREDICTIONS |
| title_sort | geoai for marine ecosystem monitoring a complete workflow to generate maps from ai model predictions |
| url | https://isprs-archives.copernicus.org/articles/XLVIII-4-W7-2023/223/2023/isprs-archives-XLVIII-4-W7-2023-223-2023.pdf |
| work_keys_str_mv | AT jtalpaertdaudon geoaiformarineecosystemmonitoringacompleteworkflowtogeneratemapsfromaimodelpredictions AT mcontini geoaiformarineecosystemmonitoringacompleteworkflowtogeneratemapsfromaimodelpredictions AT iurbinabarreto geoaiformarineecosystemmonitoringacompleteworkflowtogeneratemapsfromaimodelpredictions AT belliott geoaiformarineecosystemmonitoringacompleteworkflowtogeneratemapsfromaimodelpredictions AT fguilhaumon geoaiformarineecosystemmonitoringacompleteworkflowtogeneratemapsfromaimodelpredictions AT ajoly geoaiformarineecosystemmonitoringacompleteworkflowtogeneratemapsfromaimodelpredictions AT sbonhommeau geoaiformarineecosystemmonitoringacompleteworkflowtogeneratemapsfromaimodelpredictions AT jbarde geoaiformarineecosystemmonitoringacompleteworkflowtogeneratemapsfromaimodelpredictions |