Dominica Harrison

Habitat complexity plays a critical role in coral reef ecosystems by enhancing habitat availability, increasing ecological resilience, and offering coastal protection. Structure-from-motion (SfM) photogrammetry has become a standard approach for quantifying habitat complexity in reef monitoring programs. However, a major bottleneck remains in the two-dimensional (2D) classification of benthic cover in three-dimensional (3D) models, where experts are required to manually annotate individual colonies and identify coral species or taxonomic groups. With recent advances in deep learning and computer vision, automated classification of benthic habitats is possible. While some semi-automated tools exist, they are often limited in scope or do not provide semantic segmentation. In this investigation, we trained a convolutional neural network with the ResNet101 architecture on three years (2015, 2017, and 2019) of human-annotated 2D orthomosaics from Kiritimati, Kiribati. Our model accuracy ranged from 71% to 95%, with an overall accuracy of 84% and a mean intersection of union of 0.82, despite highly imbalanced training data, and it demonstrated successful generalizability when applied to new, untrained 2023 plots. Successful automation depends on training data that captures local ecological variation. As coral monitoring efforts move toward standardized workflows, locally developed models will be key to achieving fully automated, high-resolution classification of benthic communities across diverse reef environments.

Sponges are remarkably active animals with a range of behaviors that are broadly termed sneezes. Little is known about what triggers sneezes or how sneezes propagate in an animal that lacks either muscular or nervous systems. We explored the triggers of sponge behavior in situ in the demosponge Suberites concinnus. The placement of this tennis ball-sized sponge at the focal point of a camera array on an instrument platform in Barkley Sound, BC, Canada, provided a unique opportunity for our investigation. The observatory has a suite of environmental sensors measuring parameters such as photosynthetically active radiation (PAR), oxygen, turbidity, salinity, pressure, current speed, and temperature. An array of 8 cameras designed for 3D imaging was used to capture hourly images. Our findings revealed both long-term (annual) and short-term (daily) behaviors in S. concinnus. The sponge contracted for 2 mo each winter. In February, it gradually expanded and became very active with short-term full-body contractions each lasting 11 h through the summer. A meta-analysis of contraction behaviors in other species of sponge showed that contraction duration is a factor of sponge size and that all sponges contract faster than they expand. Invertebrates and fish were frequently in contact with the sponge, but no single interaction was found to correlate with patterns of sponge behavior. However, significant correlations between sponge behaviors and chlorophyll and turbidity were found using generalized additive mixed models. Our study underscores the dynamic nature of these sessile filter feeders and their responses to their environment.

Biological data sets are increasingly becoming information-dense, making it effective to use a computer science-based analysis. We used convolution neural networks (CNN) and the specific CNN architecture Unet to study sponge behavior over time. We analyzed a large time series of hourly high-resolution still images of a marine sponge, Suberites concinnus (Demospongiae, Suberitidae) captured between 2012 and 2015 using the NEPTUNE seafloor cabled observatory, off the west coast of Vancouver Island, Canada. We applied semantic segmentation with the Unet architecture with some modifications, including adapting parts of the architecture to be more applicable to three-channel images (RGB). Some alterations that made this model successful were the use of a dice-loss coefficient, Adam optimizer and a dropout function after each convolutional layer which provided losses, accuracies and dice scores of up to 0.03, 0.98 and 0.97, respectively. The model was tested with five-fold cross-validation. This study is a first step towards analyzing trends in the behavior of a demosponge in an environment that experiences severe seasonal and inter-annual changes in climate. The end objective is to correlate changes in sponge size (activity) over seasons and years with environmental variables collected from the same observatory platform. Our work provides a roadmap for others who seek to cross the interdisciplinary boundaries between biology and computer science.