Leveraging Automated Image Analysis Tools to Transform Our Capacity to Assess Status and Trends of Coral Reefs
Digital photography is widely used by coral reef monitoring programs to assess benthic status and trends. In addition to creating a permanent archive, photographic surveys can be rapidly conducted, which is important in environments where bottom-time is frequently limiting. However, substantial effo...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-04-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fmars.2019.00222/full |
| _version_ | 1818406787004497920 |
|---|---|
| author | Ivor D. Williams Courtney S. Couch Courtney S. Couch Oscar Beijbom Oscar Beijbom Thomas A. Oliver Bernardo Vargas-Angel Bernardo Vargas-Angel Brett D. Schumacher Russell E. Brainard |
| author_facet | Ivor D. Williams Courtney S. Couch Courtney S. Couch Oscar Beijbom Oscar Beijbom Thomas A. Oliver Bernardo Vargas-Angel Bernardo Vargas-Angel Brett D. Schumacher Russell E. Brainard |
| author_sort | Ivor D. Williams |
| collection | DOAJ |
| description | Digital photography is widely used by coral reef monitoring programs to assess benthic status and trends. In addition to creating a permanent archive, photographic surveys can be rapidly conducted, which is important in environments where bottom-time is frequently limiting. However, substantial effort is required to manually analyze benthic images; which is expensive and leads to lags before data are available. Using previously analyzed imagery from NOAA’s Pacific Reef Assessment and Monitoring Program, we assessed the capacity of a trained and widely used machine-learning image analysis tool – CoralNet coralnet.ucsd.edu – to generate fully-automated benthic cover estimates for the main Hawaiian Islands (MHI) and American Samoa. CoralNet was able to generate estimates of site-level coral cover for both regions that were highly comparable to those generated by human analysts (Pearson’s r > 0.97, and with bias of 1% or less). CoralNet was generally effective at estimating cover of common coral genera (Pearson’s r > 0.92 and with bias of 2% or less in 6 of 7 cases), but performance was mixed for other groups including algal categories, although generally better for American Samoa than MHI. CoralNet performance was improved by simplifying the classification scheme from genus to functional group and by training within habitat types, i.e., separately for coral-rich, pavement, boulder, or “other” habitats. The close match between human-generated and CoralNet-generated estimates of coral cover pooled to the scale of island and year demonstrates that CoralNet is capable of generating data suitable for assessing spatial and temporal patterns. The imagery we used was gathered from sites randomly located in <30 m hard-bottom at multiple islands and habitat-types per region, suggesting our results are likely to be widely applicable. As image acquisition is relatively straightforward, the capacity of fully-automated image analysis tools to minimize the need for resource intensive human analysts opens possibilities for enormous increases in the quantity and consistency of coral reef benthic data that could become available to researchers and managers. |
| first_indexed | 2024-12-14T09:17:29Z |
| format | Article |
| id | doaj.art-ff463d74dc2a4195a03c12ccc5208b0c |
| institution | Directory Open Access Journal |
| issn | 2296-7745 |
| language | English |
| last_indexed | 2024-12-14T09:17:29Z |
| publishDate | 2019-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj.art-ff463d74dc2a4195a03c12ccc5208b0c2022-12-21T23:08:25ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452019-04-01610.3389/fmars.2019.00222420984Leveraging Automated Image Analysis Tools to Transform Our Capacity to Assess Status and Trends of Coral ReefsIvor D. Williams0Courtney S. Couch1Courtney S. Couch2Oscar Beijbom3Oscar Beijbom4Thomas A. Oliver5Bernardo Vargas-Angel6Bernardo Vargas-Angel7Brett D. Schumacher8Russell E. Brainard9Ecosystem Sciences Division, Pacific Islands Fisheries Science Center, National Oceanic and Atmospheric Administration (NOAA), Honolulu, HI, United StatesEcosystem Sciences Division, Pacific Islands Fisheries Science Center, National Oceanic and Atmospheric Administration (NOAA), Honolulu, HI, United StatesJoint Institute for Marine and Atmospheric Research, University of Hawai’i at Mānoa, Honolulu, HI, United StatesGlobal Change Institute, The University of Queensland, St Lucia, QLD, AustraliaBerkeley Artificial Intelligence Research, University of California, Berkeley, Berkeley, CA, United StatesEcosystem Sciences Division, Pacific Islands Fisheries Science Center, National Oceanic and Atmospheric Administration (NOAA), Honolulu, HI, United StatesEcosystem Sciences Division, Pacific Islands Fisheries Science Center, National Oceanic and Atmospheric Administration (NOAA), Honolulu, HI, United StatesJoint Institute for Marine and Atmospheric Research, University of Hawai’i at Mānoa, Honolulu, HI, United StatesSustainable Fisheries Division, Pacific Islands Regional Office, National Oceanic and Atmospheric Administration, Honolulu, HI, United StatesEcosystem Sciences Division, Pacific Islands Fisheries Science Center, National Oceanic and Atmospheric Administration (NOAA), Honolulu, HI, United StatesDigital photography is widely used by coral reef monitoring programs to assess benthic status and trends. In addition to creating a permanent archive, photographic surveys can be rapidly conducted, which is important in environments where bottom-time is frequently limiting. However, substantial effort is required to manually analyze benthic images; which is expensive and leads to lags before data are available. Using previously analyzed imagery from NOAA’s Pacific Reef Assessment and Monitoring Program, we assessed the capacity of a trained and widely used machine-learning image analysis tool – CoralNet coralnet.ucsd.edu – to generate fully-automated benthic cover estimates for the main Hawaiian Islands (MHI) and American Samoa. CoralNet was able to generate estimates of site-level coral cover for both regions that were highly comparable to those generated by human analysts (Pearson’s r > 0.97, and with bias of 1% or less). CoralNet was generally effective at estimating cover of common coral genera (Pearson’s r > 0.92 and with bias of 2% or less in 6 of 7 cases), but performance was mixed for other groups including algal categories, although generally better for American Samoa than MHI. CoralNet performance was improved by simplifying the classification scheme from genus to functional group and by training within habitat types, i.e., separately for coral-rich, pavement, boulder, or “other” habitats. The close match between human-generated and CoralNet-generated estimates of coral cover pooled to the scale of island and year demonstrates that CoralNet is capable of generating data suitable for assessing spatial and temporal patterns. The imagery we used was gathered from sites randomly located in <30 m hard-bottom at multiple islands and habitat-types per region, suggesting our results are likely to be widely applicable. As image acquisition is relatively straightforward, the capacity of fully-automated image analysis tools to minimize the need for resource intensive human analysts opens possibilities for enormous increases in the quantity and consistency of coral reef benthic data that could become available to researchers and managers.https://www.frontiersin.org/article/10.3389/fmars.2019.00222/fullcoral reefimage analysismachine learningCoralNetHawaiiAmerican Samoa |
| spellingShingle | Ivor D. Williams Courtney S. Couch Courtney S. Couch Oscar Beijbom Oscar Beijbom Thomas A. Oliver Bernardo Vargas-Angel Bernardo Vargas-Angel Brett D. Schumacher Russell E. Brainard Leveraging Automated Image Analysis Tools to Transform Our Capacity to Assess Status and Trends of Coral Reefs Frontiers in Marine Science coral reef image analysis machine learning CoralNet Hawaii American Samoa |
| title | Leveraging Automated Image Analysis Tools to Transform Our Capacity to Assess Status and Trends of Coral Reefs |
| title_full | Leveraging Automated Image Analysis Tools to Transform Our Capacity to Assess Status and Trends of Coral Reefs |
| title_fullStr | Leveraging Automated Image Analysis Tools to Transform Our Capacity to Assess Status and Trends of Coral Reefs |
| title_full_unstemmed | Leveraging Automated Image Analysis Tools to Transform Our Capacity to Assess Status and Trends of Coral Reefs |
| title_short | Leveraging Automated Image Analysis Tools to Transform Our Capacity to Assess Status and Trends of Coral Reefs |
| title_sort | leveraging automated image analysis tools to transform our capacity to assess status and trends of coral reefs |
| topic | coral reef image analysis machine learning CoralNet Hawaii American Samoa |
| url | https://www.frontiersin.org/article/10.3389/fmars.2019.00222/full |
| work_keys_str_mv | AT ivordwilliams leveragingautomatedimageanalysistoolstotransformourcapacitytoassessstatusandtrendsofcoralreefs AT courtneyscouch leveragingautomatedimageanalysistoolstotransformourcapacitytoassessstatusandtrendsofcoralreefs AT courtneyscouch leveragingautomatedimageanalysistoolstotransformourcapacitytoassessstatusandtrendsofcoralreefs AT oscarbeijbom leveragingautomatedimageanalysistoolstotransformourcapacitytoassessstatusandtrendsofcoralreefs AT oscarbeijbom leveragingautomatedimageanalysistoolstotransformourcapacitytoassessstatusandtrendsofcoralreefs AT thomasaoliver leveragingautomatedimageanalysistoolstotransformourcapacitytoassessstatusandtrendsofcoralreefs AT bernardovargasangel leveragingautomatedimageanalysistoolstotransformourcapacitytoassessstatusandtrendsofcoralreefs AT bernardovargasangel leveragingautomatedimageanalysistoolstotransformourcapacitytoassessstatusandtrendsofcoralreefs AT brettdschumacher leveragingautomatedimageanalysistoolstotransformourcapacitytoassessstatusandtrendsofcoralreefs AT russellebrainard leveragingautomatedimageanalysistoolstotransformourcapacitytoassessstatusandtrendsofcoralreefs |