TY - JOUR
T1 - 3D photogrammetry and deep-learning deliver accurate estimates of epibenthic biomass
AU - Marlow, Joseph
AU - Halpin, John Edward
AU - Wilding, Thomas Andrew
N1 - Publisher Copyright:
© 2024 The Authors. Methods in Ecology and Evolution published by John Wiley & Sons Ltd on behalf of British Ecological Society.
PY - 2024/3/26
Y1 - 2024/3/26
N2 - Accurate biomass estimates are key to understanding a wide variety of ecological functions. In marine systems, epibenthic biomass estimates have traditionally relied on either destructive/extractive methods that are limited to horizontal soft-sediment environments, or simplistic geometry-based biomass conversions that are unsuitable for more complex morphologies. Consequently, there is a requirement for non-destructive, higher-accuracy methods that can be used in an array of environments, targeting more morphologically diverse taxa, and at ecological relevant scales. We used a combination of 3D photogrammetry, convolutional neural network (CNN) automated taxonomic identification, and taxa-specific biovolume:biomass calibrations to test the viability of estimating biomass of three species of morphologically complex epibenthic taxa from in situ stereo 2D source imagery. Our trained CNN produced accurate and reliable annotations of our target taxa across a wide range of conditions. When incorporated into photogrammetric 3D models of underwater surveys, we were able to automatically isolate our three target taxa from their environment, producing biovolume measurements that had respective mean similarities of 99%, 102% and 120% of those obtained from human annotators. When combined with taxa-specific biovolume:biomass calibration values, we produced biomass estimates of 88%, 125% and 133% mean similarity to that of the ‘true’ biomass of the respective taxa. Our methodology provides a highly reliable and efficient method for estimating epibenthic biomass of morphologically complex taxa using non-destructive 2D imagery. This approach can be applied to a variety of environments and photo/video survey approaches (e.g. SCUBA, ROV, AUV) and is especially valuable in spatially extensive surveys where manual approaches are prohibitively time-consuming.
AB - Accurate biomass estimates are key to understanding a wide variety of ecological functions. In marine systems, epibenthic biomass estimates have traditionally relied on either destructive/extractive methods that are limited to horizontal soft-sediment environments, or simplistic geometry-based biomass conversions that are unsuitable for more complex morphologies. Consequently, there is a requirement for non-destructive, higher-accuracy methods that can be used in an array of environments, targeting more morphologically diverse taxa, and at ecological relevant scales. We used a combination of 3D photogrammetry, convolutional neural network (CNN) automated taxonomic identification, and taxa-specific biovolume:biomass calibrations to test the viability of estimating biomass of three species of morphologically complex epibenthic taxa from in situ stereo 2D source imagery. Our trained CNN produced accurate and reliable annotations of our target taxa across a wide range of conditions. When incorporated into photogrammetric 3D models of underwater surveys, we were able to automatically isolate our three target taxa from their environment, producing biovolume measurements that had respective mean similarities of 99%, 102% and 120% of those obtained from human annotators. When combined with taxa-specific biovolume:biomass calibration values, we produced biomass estimates of 88%, 125% and 133% mean similarity to that of the ‘true’ biomass of the respective taxa. Our methodology provides a highly reliable and efficient method for estimating epibenthic biomass of morphologically complex taxa using non-destructive 2D imagery. This approach can be applied to a variety of environments and photo/video survey approaches (e.g. SCUBA, ROV, AUV) and is especially valuable in spatially extensive surveys where manual approaches are prohibitively time-consuming.
KW - 3D
KW - artificial intelligence
KW - benthos
KW - CNN
KW - deep-learning
KW - machine-learning
UR - http://www.scopus.com/inward/record.url?scp=85188561767&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85188561767&partnerID=8YFLogxK
U2 - 10.1111/2041-210X.14313
DO - 10.1111/2041-210X.14313
M3 - Article
AN - SCOPUS:85188561767
SN - 2041-210X
JO - Methods in Ecology and Evolution
JF - Methods in Ecology and Evolution
ER -