Species distribution modelling of Bryde's whales, humpback whales, southern right whales, and sperm whales in the southern African region to inform their conservation in expanding economies

Comparative Analysis of MaxEnt and Deep Learning Approaches for Modeling Humpback Whale Distribution in North Iceland

In this study, we compared the established MaxEnt and a more novel deep learning approach for modeling the distribution of humpback whales (Megaptera novaeangliae) in north Iceland. We examined the mechanisms, structures, and optimization techniques of both approaches, highlighting their differences and similarities. Monthly distribution models for Skjálfandi Bay were created, from 2018 until 2021, using presence-only sighting data and satellite remote sensing data. Search efforts and boat tracklines were utilized to create pseudo-absence points for both models. Additionally, the trained models were used to create distribution projections for the year 2022, solely based on the available environmental data. We compared the results using the established area under the curve value. The findings indicate that both approaches have their limitations and advantages. MaxEnt does not allow continuous updating within a time series, yet it mitigates the risk of overfitting by employing the maximum entropy principle. The deep learning model is more likely to overfit, but the larger weight network increases the model's capability to capture complex relationships and patterns. Ultimately, the results show that the deep learning model had a higher predictive performance in modeling both current and future humpback whale distributions. Both modeling approaches have inherent limitations, such as the low resolution of the input data, spatial biases, and the inability to fully capture the entire complexity of natural processes. Despite this, deep learning showed promising results in modeling the distribution of humpback whales and prompts further research in different study areas and applications for other mobile animal species.

Assessing changing baleen whale distributions and reported incidents relative to vessel activity in the Northwest Atlantic

Baleen whales are among the largest marine megafauna, and while mostly well-protected from direct exploitation, they are increasingly affected by vessel traffic, interactions with fisheries, and climate change. Adverse interactions, notably vessel strikes and fishing gear entanglement, often result in distress, injury, or death for these animals. In Atlantic Canadian waters, such negative interactions or 'incidents' are consistently reported to marine animal response organizations but have not yet been analyzed relative to the spatial distribution of whales and vessels. Using a database of 483,003 whale sightings, 1,110 incident reports, and 82 million hours of maritime vessel activity, we conducted a spatiotemporal vulnerability analysis for all six baleen whale species occurring in the Northwest Atlantic Ocean by developing an ensemble of habitat-suitability models. The relative spatial risk of vessel-induced incidents was assessed for present (1985-2015) and projected near-future (2035-2055) distributions of baleen whales. Areas of high habitat suitability for multiple baleen whale species were intrinsically linked to sea surface temperature and salinity, with multispecies hotspots identified in the Bay of Fundy, Scotian Shelf, Laurentian Channel, Flemish Cap, and Gulf of St. Lawrence. Present-day model projections were independently evaluated using a separate database of acoustic detections and found to align well. Regions of high relative incident risk were projected close to densely inhabited regions, principal maritime routes, and major fishing grounds, in general coinciding with reported incident hotspots. While some high-risk regions already benefit from mitigation strategies aimed at protecting North Atlantic Right Whales, our analysis highlights the importance of considering risks to multiple species, both in the present day and under continued environmental change.

Mapping the Future: Revealing Habitat Preferences and Patterns of the Endangered Chilean Dolphin in Seno Skyring, Patagonia

Species distribution modeling helps understand how environmental factors influence species distribution, creating profiles to predict presence in unexplored areas and assess ecological impacts. This study examined the habitat use and population ecology of the Chilean dolphin in Seno Skyring, Chilean Patagonia. We used three models-random forest (RF), generalized linear model (GLM), and artificial neural network (ANN)-to predict dolphin distribution based on environmental and biotic data like water temperature, salinity, and fish farm density. Our research has determined that the RF model is the most precise tool for predicting the habitat preferences of Chilean dolphins. The results indicate that these dolphins are primarily located within six kilometers of the coast, strongly correlating with areas featuring numerous fish farms, sheltered waters close to the shore with river inputs, and shallow productive zones. This suggests a potential association between dolphin presence and fish-farming activities. These findings can guide targeted conservation measures, such as regulating fish-farming practices and protecting vital coastal areas to improve the survival prospects of the Chilean dolphin. Given the extensive fish-farming industry in Chile, this research highlights the need for greater knowledge and comprehensive conservation efforts to ensure the species' long-term survival. By understanding and mitigating the impacts of fish farming and other human activities, we can better protect the habitat and well-being of Chilean dolphins.

Distribution models of baleen whale species in the Irish Exclusive Economic Zone to inform management and conservation

Irish waters are under increasing pressure from anthropogenic sources including the development of offshore renewable energy, vessel traffic and fishing activity. Spatial planning requires robust datasets on species distribution and the identification of important habitats to inform the planning process. Despite limited survey effort, long-term citizen science data on whale presence are available and provide an opportunity to fill information gaps. Using presence-only data as well as a variety of environmental variables, we constructed seasonal ensemble species distribution models based on five different algorithms for minke whales, fin whales, humpback whales, sei whales, and blue whales. The models predicted that the coastal waters off the south and west of Ireland are particularly suitable for minke, fin and humpback whales. Offshore waters in the Porcupine Seabight area were identified as a relevant habitat for fin whales, sei whales and blue whales. We combined model outputs with data on maritime traffic, fishing activity and offshore wind farms to measure the exposure of all the species to these pressures, identifying areas of concern. This study serves as a baseline for the species presence in Irish waters over the last two decades to help develop appropriate marine spatial plans in the future.

Testing spatial transferability of species distribution models reveals differing habitat preferences for an endangered delphinid (Cephalorhynchus hectori) in Aotearoa, New Zealand

Species distribution models (SDMs) can be used to predict distributions in novel times or space (termed transferability) and fill knowledge gaps for areas that are data poor. In conservation, this can be used to determine the extent of spatial protection required. To understand how well a model transfers spatially, it needs to be independently tested, using data from novel habitats. Here, we test the transferability of SDMs for Hector's dolphin (Cephalorhynchus hectori), a culturally important (taonga) and endangered, coastal delphinid, endemic to Aotearoa New Zealand. We collected summer distribution data from three populations from 2021 to 2023. Using Generalised Additive Models, we built presence/absence SDMs for each population and validated the predictive ability of the top models (with TSS and AUC). Then, we tested the transferability of each top model by predicting the distribution of the remaining two populations. SDMs for two populations showed useful performance within their respective areas (Banks Peninsula and Otago), but when used to predict the two areas outside the models' source data, performance declined markedly. SDMs from the third area (Timaru) performed poorly, both for prediction within the source area and when transferred spatially. When data for model building were combined from two areas, results were mixed. Model interpolation was better when presence/absence data from Otago, an area of low density, were combined with data from areas of higher density, but was otherwise poor. The overall poor transferability of SDMs suggests that habitat preferences of Hector's dolphins vary between areas. For these dolphins, population-specific distribution data should be used for conservation planning. More generally, we demonstrate that a one model fits all approach is not always suitable. When SDMs are used to predict distribution in data-poor areas an assessment of performance in the new habitat is required, and results should be interpreted with caution.

Clicking throughout the year: sperm whale clicks in relation to environmental conditions off the west coast of South Africa

Knowledge of cetacean occurrence and behaviour in southern African waters is limited, and passive acoustic monitoring has the potential to address this gap efficiently. Seasonal acoustic occurrence and diel-vocalizing patterns of sperm whales in relation to environmental conditions are described here using passive acoustic monitoring data collected off the west coast of South Africa. Four autonomous acoustic recorders (AARs) were deployed on 3 oceanographic moorings from July 2014 to January 2017. Sperm whale clicks were detected year round in most recording sites, with peaks in acoustic occurrence in summer and late winter through spring. Diel-vocalizing patterns were detected in winter, spring and summer. Higher percentages of sperm whale clicks were recorded by AARs deployed at 1100 m water depth compared to those concurrently deployed at 850 and 4500 m, likely inferring that the whales exhibited some preference to water depths around 1100 m. Acoustic propagation modelling suggested a maximum detection range of 83 km in winter for sperm whale clicks produced at 1100 m. Random forest models classified daylight regime, sea surface height anomaly and month of the year as the most important predictors of sperm whale acoustic occurrence. The continuous acoustic occurrence of sperm whales suggests that the study area supports large biomasses of prey to sustain this species’ food requirements year round. This is the first study to describe the seasonal acoustic occurrence and diel-vocalizing patterns of sperm whales off the west coast of South Africa, extending knowledge of the species previously available only through whaling records.