Search for: All records

Anthropogenic global change is occurring at alarming rates, leading to increased urgency in the ability to monitor wildlife health in real time. Monitoring sentinel marine species, such as bottlenose dolphins, is particularly important due to extensive anthropogenic modifications to their habitats. The most common non-invasive method of monitoring cetacean health is documentation of skin lesions, often associated with poor health or disease, but the current methodology is inefficient and imprecise. Recent advancements in technology, such as machine learning, can provide researchers with more efficient ecological monitoring methods to address health questions at both the population and the individual levels. Our work develops a machine learning model to classify skin lesions on the understudied Tamanend's bottlenose dolphins (Tursiops erebennus) of the Chesapeake Bay, using manual estimates of lesion presence in photographs. We assess the model's performance and find that our best model performs with a high mean average precision (65.6 %–86.8 %), and generally increased accuracy with improved photo quality. We also demonstrate the model's ability to address ecological questions across scales by generating model-based estimates of lesion prevalence and testing the effect of gregariousness on health status. At the population level, our model accurately estimates a prevalence of 72.1 % spot and 27.3 % fringe ring lesions, with a slight underprediction compared to manual estimates (82.2 % and 32.1 %). On the other hand, we find that individual-level analyses from the model predictions may be more sensitive to data quality, and thus, some individual scale questions may not be feasible to address if data quality is inconsistent. Manually, we do find that lesion presence in individuals suggests a positive relationship between lesion presence and gregariousness. This work demonstrates that object detection models on photographic data are reasonably successful, highly efficient, and provide initial estimates on the health status of understudied populations of bottlenose dolphins. 

As demands for wildlife tourism increase, provisioning has become a popular means of providing up-close viewing to the public. At Monkey Mia, Shark Bay, Australia, up to five adult female Indo-Pacific bottlenose dolphins ( Tursiops aduncus ) visit a 100 m stretch of beach daily to receive fish handouts. In 2011, a severe marine heatwave (MHW) devastated seagrass and fish populations in Shark Bay. Offspring survival declined precipitously among seagrass specialists (dolphins that forage disproportionately in seagrass habitat). As all provisioned dolphins at the site are seagrass specialists, we examined how provisioned and non-provisioned seagrass specialists responded to the MHW. Using 27 years of data we compare habitat use, home range size, calf mortality, and predation risk between provisioned and non-provisioned females and their offspring before and after the MHW. Our results show that provisioned females have extremely small home ranges compared to non-provisioned females, a pattern attributable to their efforts to remain near the site of fish handouts. However, weaned offspring (juveniles) born to provisioned females who are not provisioned themselves also had much smaller home ranges, suggesting a persistent maternal effect on their behavior. After the MHW, adult females increased their use of seagrass habitats, but not their home range size. Provisioned females had significantly lower calf mortality than non-provisioned females, a pattern most evident pre-MHW, and, in the first 5 years after the MHW (peri-MHW, 2011–2015), calf mortality did not significantly increase for either group. However, the ecosystem did not recover, and post-MHW (2016–2020), calf mortality was substantially higher, regardless of provisioning status. With few survivors, the impact of the MHW on juvenile mortality post-weaning is not known. However, over three decades, juvenile mortality among offspring of provisioned vs. non-provisioned females did not statistically differ. Thus, the survival benefits accrued to calves in the provisioned group likely cease after weaning. Finally, although shark attack rates on seagrass specialists did not change over time, elevated predation on calves cannot be ruled out as a cause of death post-MHW. We discuss our results as they relate to anthropogenic influences on dolphin behavioral plasticity and responses to extreme climate events.