http://lod.bco-dmo.org/id/dataset/943698
eng; USA
utf8
dataset
Highest level of data collection, from a common set of sensors or instrumentation, usually within the same research project
Biological and Chemical Oceanography Data Management Office (BCO-DMO)
Unavailable
508-289-2009
WHOI MS#36
Woods Hole
MA
02543
USA
info@bco-dmo.org
http://www.bco-dmo.org
Monday - Friday 8:00am - 5:00pm
For questions regarding this resource, please contact BCO-DMO via the email address provided.
pointOfContact
2024-11-15
ISO 19115-2 Geographic Information - Metadata - Part 2: Extensions for Imagery and Gridded Data
ISO 19115-2:2009(E)
Mask R-CNN and U-Net model and output of coral reef halo measurements based on global multispectral satellite imagery
2024-12-18
publication
2024-12-18
revision
Marine Biological Laboratory/Woods Hole Oceanographic Institution Library (MBLWHOI DLA)
2024-12-18
publication
https://doi.org/10.26008/1912/bco-dmo.943698.1
Elizabeth Madin
University of Hawaiʻi at Mānoa
principalInvestigator
Simone Franceschini
University of Hawaiʻi at Mānoa
principalInvestigator
Biological and Chemical Oceanography Data Management Office (BCO-DMO)
Unavailable
508-289-2009
WHOI MS#36
Woods Hole
MA
02543
USA
info@bco-dmo.org
http://www.bco-dmo.org
Monday - Friday 8:00am - 5:00pm
For questions regarding this resource, please contact BCO-DMO via the email address provided.
publisher
Cite this dataset as: Madin, E., Franceschini, S. (2024) Mask R-CNN and U-Net model and output of coral reef halo measurements based on global multispectral satellite imagery. Biological and Chemical Oceanography Data Management Office (BCO-DMO). (Version 1) Version Date 2024-12-18 [if applicable, indicate subset used]. doi:10.26008/1912/bco-dmo.943698.1 [access date]
Mask R-CNN and U-Net model and output calculations Dataset Description: Methods and Sampling: <p>The Mask R-CNN model was trained using the training data set, thereby automatizing the identification of reef halos from the test set of satellite images and extracting the shape of the reef halos from the imagery background (i.e., extracting both the patch reef and its surrounding halo). The Mask RCNN was trained with 3322 reef halos from 13 AOIs, while the remaining 805 halos from seven AOIs were kept to evaluate the model’s performance.</p>
<p>After object extraction, we automated halo measurement using a U-Net pixel classification model which discriminated the halo (sand ring) from the interior reef patch. A total of 6428 annotations from the training set were used for model training. Annotations consisted of pixel areas manually classified by users, divided into “patch reef” and “halo” classes, respectively.</p>
<p>The total of 6428 annotations used for the classification model was derived from splitting some of the 4127 original annotations (see related dataset). This process was implemented as part of the model training to improve pixel classification by creating diverse and multiple samples.These shapefiles were created as part of the training process and can be recreated from the original annotations already provided by processing them within the ArcGIS using&nbsp;the .dlpk model (as explained also in the <a href="https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Ftensorflow&amp;data=05%7C02%7Cksoenen%40whoi.edu%7Ce6f7998e68b5479b7d3508dd0a7e3060%7Cd44c5cc6d18c46cc8abd4fdf5b6e5944%7C0%7C0%7C638678259355172035%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&amp;sdata=YbO%2FMt1%2FrrdmfBVPeW5HAMxGUzvpADBEZmzpFfhYV1o%3D&amp;reserved=0">github tensorflow</a>).</p>
Funding provided by NSF Division of Ocean Sciences (NSF OCE) Award Number: OCE-1941737 Award URL: https://www.nsf.gov/awardsearch/show-award?AWD_ID=1941737
completed
Elizabeth Madin
University of Hawaiʻi at Mānoa
8084399506
2440 Campus Road, Box 368
HONOLULU
HI
968222234
US
emadin@hawaii.edu
pointOfContact
Simone Franceschini
University of Hawaiʻi at Mānoa
Hawai'i Institute of Marine Biology
Kane'ohe
HI
96744
USA
simonefr@hawaii.edu
pointOfContact
asNeeded
Dataset Version: 1
Unknown
AOI
object_id
hArea_m2
rArea_m2
log_hArea_m2
log_rArea_m2
theme
None, User defined
region
object ID
area_measured
featureType
BCO-DMO Standard Parameters
otherRestrictions
otherRestrictions
Access Constraints: none. Use Constraints: Please follow guidelines at: http://www.bco-dmo.org/terms-use Distribution liability: Under no circumstances shall BCO-DMO be liable for any direct, incidental, special, consequential, indirect, or punitive damages that result from the use of, or the inability to use, the materials in this data submission. If you are dissatisfied with any materials in this data submission your sole and exclusive remedy is to discontinue use.
CAREER: Decoding seascape-scale vegetation patterns on coral reefs to understand ecosystem health: Integrating research and education from organismal to planetary scales
http://oceansphere.org
CAREER: Decoding seascape-scale vegetation patterns on coral reefs to understand ecosystem health: Integrating research and education from organismal to planetary scales
<p><em>NSF Award Abstract:</em><br />
Coral reefs worldwide are under increasing threat from a range of human-induced stressors. Climate change is understood to be a key global stressor threatening reefs, but the only proven levers for ecosystem managers to increase reef resilience is to mitigate local and regional stressors such as fishing pressure. A vexing question persists, however, which is how to measure the effects of fishing on ecosystems, particularly over the large spatial (e.g., >10s of meters) and temporal (multi-year) scales over which fishing occurs. One promising approach to doing so is using the large-scale vegetation patterns found on coral reefs globally, called “halos”, to remotely observe when, where, and to what extent fishing pressure is affecting community structure and function. This program combines lab- and field-based experiments with cutting-edge satellite imaging technology and computer science approaches to provide a leap forward in our understanding of how species-level interactions can scale up in space and time to shape coral reef seascapes around the world. By drawing on these approaches, the synergistic education program: 1) integrates science and art (i.e., murals and satellite imagery) to educate and inspire Hawai‘i’s students and general public about coral reef ecology; 2) builds technological capacity in Hawai‘i’s underrepresented minority high school to graduate students, and 3) empowers these students with science communication skills to communicate with diverse audiences. By leveraging this research program and the cutting-edge technologies it will involve, the investigator establishes a strong foundation for long-term teaching and mentoring activities focused on increasing capacity within STEM-underrepresented minorities with Hawaiian and other Pacific Islander backgrounds. Decoding what coral reef halos can tell us about the effects of fishing on reef ecosystem health provides valuable knowledge to reef ecosystem managers and conservation practitioners as reefs continue to rapidly change due to human stressors.</p>
<p>This project combines lab- and field-based experiments with cutting-edge satellite imaging technology and computer science approaches to address the goals of: 1) determining the mechanisms that create the “halos” that form around coral patch reefs, and 2) testing the predictions arising from these mechanisms in a global arena. This project uses a transdisciplinary approach – spanning ecology, oceanography, geospatial science, and computer science – to address these goals. This program has three scientific objectives: to determine 1) which species interaction mechanisms and environmental factors cause reef halos and what their relative importance is; 2) whether these mechanisms are globally consistent or vary geographically; and 3) whether halos can therefore be used as an indicator of aspects of coral reef ecosystem health. In the process, this research advances our understanding of how remote observation tools (satellite and drone imagery; camera traps) can be integrated with computer science (machine learning) and ecological approaches (mechanistic experiments) to generate emergent insights that would not otherwise be possible.</p>
<p>This project is jointly funded by the Biological Oceanography Program, the Established Program to Stimulate Competitive Research (EPSCoR), and Ocean Education Programs.</p>
<p>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.</p>
Coral Reef Halos
largerWorkCitation
project
eng; USA
oceans
2024-12-18
Hawai’i (field components) and global (synthetic components)
0
BCO-DMO catalogue of parameters from Mask R-CNN and U-Net model and output of coral reef halo measurements based on global multispectral satellite imagery
Biological and Chemical Oceanography Data Management Office (BCO-DMO)
Unavailable
508-289-2009
WHOI MS#36
Woods Hole
MA
02543
USA
info@bco-dmo.org
http://www.bco-dmo.org
Monday - Friday 8:00am - 5:00pm
For questions regarding this resource, please contact BCO-DMO via the email address provided.
pointOfContact
http://lod.bco-dmo.org/id/dataset-parameter/943773.rdf
Name: AOI
Units: unitless
Description: <p>Area of interest. Twenty areas in total. Country codes: AUS = Australia, BHS = Bahamas, BLZ = Belize, EGY = Egypt, SAU = Saudi Arabia, USA = United States of America (Florida)</p>
http://lod.bco-dmo.org/id/dataset-parameter/943774.rdf
Name: object_id
Units: unitless
Description: <p>The object ID was used to relate the halo area of each object to its reef patch to get a ratio, not to relate them to the test data set,</p>
http://lod.bco-dmo.org/id/dataset-parameter/943775.rdf
Name: hArea_m2
Units: square meter (m2)
Description: <p>Halo area</p>
http://lod.bco-dmo.org/id/dataset-parameter/943776.rdf
Name: rArea_m2
Units: square meter (m2)
Description: <p>Reef area</p>
http://lod.bco-dmo.org/id/dataset-parameter/943777.rdf
Name: log_hArea_m2
Units: square meter (m2)
Description: <p>Log-transformed halo area</p>
http://lod.bco-dmo.org/id/dataset-parameter/943778.rdf
Name: log_rArea_m2
Units: square meter (m2)
Description: <p>Log-transformed reefarea</p>
GB/NERC/BODC > British Oceanographic Data Centre, Natural Environment Research Council, United Kingdom
Biological and Chemical Oceanography Data Management Office (BCO-DMO)
Unavailable
508-289-2009
WHOI MS#36
Woods Hole
MA
02543
USA
info@bco-dmo.org
http://www.bco-dmo.org
Monday - Friday 8:00am - 5:00pm
For questions regarding this resource, please contact BCO-DMO via the email address provided.
pointOfContact
51950
https://darchive.mblwhoilibrary.org/server/api/core/bitstreams/1f073a05-90b6-489b-a431-c8edf9c84b94/content
download
https://doi.org/10.26008/1912/bco-dmo.943698.1
download
onLine
dataset
<p>The Mask R-CNN model was trained using the training data set, thereby automatizing the identification of reef halos from the test set of satellite images and extracting the shape of the reef halos from the imagery background (i.e., extracting both the patch reef and its surrounding halo). The Mask RCNN was trained with 3322 reef halos from 13 AOIs, while the remaining 805 halos from seven AOIs were kept to evaluate the model’s performance.</p>
<p>After object extraction, we automated halo measurement using a U-Net pixel classification model which discriminated the halo (sand ring) from the interior reef patch. A total of 6428 annotations from the training set were used for model training. Annotations consisted of pixel areas manually classified by users, divided into “patch reef” and “halo” classes, respectively.</p>
<p>The total of 6428 annotations used for the classification model was derived from splitting some of the 4127 original annotations (see related dataset). This process was implemented as part of the model training to improve pixel classification by creating diverse and multiple samples.These shapefiles were created as part of the training process and can be recreated from the original annotations already provided by processing them within the ArcGIS using&nbsp;the .dlpk model (as explained also in the <a href="https://nam02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Ftensorflow&amp;data=05%7C02%7Cksoenen%40whoi.edu%7Ce6f7998e68b5479b7d3508dd0a7e3060%7Cd44c5cc6d18c46cc8abd4fdf5b6e5944%7C0%7C0%7C638678259355172035%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&amp;sdata=YbO%2FMt1%2FrrdmfBVPeW5HAMxGUzvpADBEZmzpFfhYV1o%3D&amp;reserved=0">github tensorflow</a>).</p>
Specified by the Principal Investigator(s)
<p>Both the Mask R-CNN and U-Net models were developed using Tensorflow (ver. 2.5.1), Keras (ver. 2.4.3), and PyTorch (ver. 1.8.2) libraries in Python (ver. 3.9) and ArcGIS (ver. 2.9.1.) The machine running the deep learning model had an Intel® Core™ i9-9900K CPU @3.60 GHz processor with 128 GB of installed RAM and a PNY NVIDIA Quadro A6000 GPU.</p>
<p>The areas of both reefs and halos were calculated by counting the number of pixels assigned to the respective "reef" and "halo" classes. The total area for each spatial object was estimated with the known size of a pixel.</p>
<p>&nbsp;</p>
Specified by the Principal Investigator(s)
asNeeded
7.x-1.1
Biological and Chemical Oceanography Data Management Office (BCO-DMO)
Unavailable
508-289-2009
WHOI MS#36
Woods Hole
MA
02543
USA
info@bco-dmo.org
http://www.bco-dmo.org
Monday - Friday 8:00am - 5:00pm
For questions regarding this resource, please contact BCO-DMO via the email address provided.
pointOfContact