Considering the rates of growth in two taxa of coral across Pacific islands

Sandin, Stuart A.; Edwards, Clinton B.; Pedersen, Nicole E.; Petrovic, Vid; Pavoni, Gaia; Alcantar, Esmeralda; Chancellor, Kendall S.; Fox, Michael D.; Stallings, Brenna; Sullivan, Christopher J.; Rotjan, Randi D.; Ponchio, Federico; Zgliczynski, Brian J.

doi:10.1016/bs.amb.2020.08.006

Cited by 14 publications

(24 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TagLab also performs data analysis; some of its functions, such as the Multitemporal Comparison tool, proved extremely useful for extracting spatial information from orthoimages (Sandin et al, 2020). However, the current version of TagLab has limitations on the size of the orthoimages handled, which cannot exceed

32000 \times 32000

pixels.…”

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

“…As each orthoimage may contain thousands of colonies, this tool greatly simplifies the temporal evolution analysis of benthos. Although the user study in this paper does not include this analysis tool, the functionality has already been adopted in a recent publication (Sandin et al, 2020).…”

Section: Resources For Automatic Analysismentioning

confidence: 99%

See 2 more Smart Citations

TagLab: AI‐assisted annotation for the fast and accurate semantic segmentation of coral reef orthoimages

Pavoni

Corsini

Ponchio

et al. 2021

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

Semantic segmentation is a widespread image analysis task; in some applications, it requires such high accuracy that it still has to be done manually, taking a long time. Deep learning‐based approaches can significantly reduce such times, but current automated solutions may produce results below expert standards. We propose agLab, an interactive tool for the rapid labelling and analysis of orthoimages that speeds up semantic segmentation. TagLab follows a human‐centered artificial intelligence approach that, by integrating multiple degrees of automation, empowers human capabilities. We evaluated TagLab's efficiency in annotation time and accuracy through a user study based on a highly challenging task: the semantic segmentation of coral communities in marine ecology. In the assisted labelling of corals, TagLab increased the annotation speed by approximately 90% for nonexpert annotators while preserving the labelling accuracy. Furthermore, human–machine interaction has improved the accuracy of fully automatic predictions by about 7% on average and by 14% when the model generalizes poorly. Considering the experience done through the user study, TagLab has been improved, and preliminary investigations suggest a further significant reduction in annotation times.

show abstract

32000 \times 32000

pixels.…”

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

TagLab: AI‐assisted annotation for the fast and accurate semantic segmentation of coral reef orthoimages

Pavoni

Corsini

Ponchio

et al. 2021

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The details of our field sampling design have been discussed in detail elsewhere ( Edwards et al, 2017 ; Fox et al, 2019 ; Kodera et al, 2020 ; Sandin et al, 2020 ). Briefly, the photographic surveys were conducted by a pair of divers within 100 m 2 plots positioned along the 10m isobath in oceanic fore reef habitats.…”

Section: Methodsmentioning

confidence: 99%

“…Using structure from motion (SfM) algorithms, 3D models of reef tracts can be derived from survey imagery ( Pizarro et al, 2009 ; Smith et al, 2016 ; Edwards et al, 2017 ; Ferrari et al, 2017 ; Kodera et al, 2020 ; Sandin et al, 2020 ), enabling analysis in a data medium that much more closely resembles real-world coral environments, particularly in steep or geometrically-complex areas that are common in reefs but poorly captured with top-down imagery. A variety of metrics, including percent cover, growth, species composition, or disease or bleaching incidence can be extracted from 3D models, or 2D orthographic projections (orthoprojections) thereof, using random point sampling or full semantic segmentation (i.e., labeling per-point, per-taxa; hereafter referred to simply as segmentation).…”

Section: Introductionmentioning

confidence: 99%

Automated 2D, 2.5D, and 3D Segmentation of Coral Reef Pointclouds and Orthoprojections

et al. 2022

Self Cite

View full text Add to dashboard Cite

Enabled by advancing technology, coral reef researchers increasingly prefer use of image-based surveys over approaches depending solely upon in situ observations, interpretations, and recordings of divers. The images collected, and derivative products such as orthographic projections and 3D models, allow researchers to study a comprehensive digital twin of their field sites. Spatio-temporally located twins can be compared and annotated, enabling researchers to virtually return to sites long after they have left them. While these new data expand the variety and specificity of biological investigation that can be pursued, they have introduced the much-discussed Big Data Problem: research labs lack the human and computational resources required to process and analyze imagery at the rate it can be collected. The rapid development of unmanned underwater vehicles suggests researchers will soon have access to an even greater volume of imagery and other sensor measurements than can be collected by diver-piloted platforms, further exacerbating data handling limitations. Thoroughly segmenting (tracing the extent of and taxonomically identifying) organisms enables researchers to extract the information image products contain, but is very time-consuming. Analytic techniques driven by neural networks offer the possibility that the segmentation process can be greatly accelerated through automation. In this study, we examine the efficacy of automated segmentation on three different image-derived data products: 3D models, and 2D and 2.5D orthographic projections thereof; we also contrast their relative accessibility and utility to different avenues of biological inquiry. The variety of network architectures and parameters tested performed similarly, ∼80% IoU for the genus Porites, suggesting that the primary limitations to an automated workflow are 1) the current capabilities of neural network technology, and 2) consistency and quality control in image product collection and human training/testing dataset generation.

show abstract

Variability in composition of parrotfish bite scars across space and over time on a central Pacific atoll

Charendoff,

Edwards,

Pedersen

et al. 2023

Coral Reefs

View full text Add to dashboard Cite

Parrotfishes are conspicuous herbivores, microvores, and detritivores in coral reef ecosystems, and the impacts of their feeding, particularly their capacity to expose reef carbonate, have received much attention. In many cases, parrotfish assemblages have been shown to control algal proliferation and promote the settlement of corals and crustose coralline algae (CCA). In extreme cases, high densities of parrotfishes may negatively affect net reef accretion through bioerosion and targeted coral predation. Most evidence describing the impacts of parrotfish foraging on benthic community structure is based upon correlations between benthic composition and parrotfish behavior or abundance, with much less known about process-based change of individual parrotfish bite scars through time. Here, we estimated parrotfish bite selectivity and determined the change in benthic composition within parrotfish bite scars relative to change in the overall reefscape using data collected over a 12-month duration from the fore reef habitat at Palmyra Atoll. We identified 2150 parrotfish bite scars which appeared most frequently on turf algae covered substrata but also on coral, CCA, and encrusting macroalgae. Of those bites taken on live coral, 96% of scars returned to live coral within 12 months. Notably, adult coral survivorship in bite scars was higher than at randomly sampled coral-covered locations not affected by parrotfish bites. The exposed substrate within bite scars was most commonly colonized by the dominant benthic functional group in the area immediately surrounding the scar. We found little evidence of coral recruitment to bite scars (1/2150); however, CCA growth on bites initially on turf algae increased from 18.4 to 32.9% across the two time intervals. Our results suggest that benthic areas affected by parrotfish bites were more likely to undergo a successional shift to a more calcified state relative to unaffected benthic areas, indicating that parrotfish grazing helps maintain highly calcified coral reef ecosystems.

show abstract

Considering the rates of growth in two taxa of coral across Pacific islands

Cited by 14 publications

References 77 publications

TagLab: AI‐assisted annotation for the fast and accurate semantic segmentation of coral reef orthoimages

TagLab: AI‐assisted annotation for the fast and accurate semantic segmentation of coral reef orthoimages

Automated 2D, 2.5D, and 3D Segmentation of Coral Reef Pointclouds and Orthoprojections

Variability in composition of parrotfish bite scars across space and over time on a central Pacific atoll

Contact Info

Product

Resources

About