A species distribution modeling approach based on aerial survey observations from 2017 to 2022 to predict North Atlantic Right Whale habitats in the Estuary and Gulf of St. Lawrence
Bibliographic record
Abstract
The North Atlantic Right Whale (NARW) was historically abundant along the North Atlantic coasts, ranging from the Gulf of Mexico to Greenland and from northwestern Africa to Norway. Nowadays, the species is primarily found along the coastal regions of the eastern United States and Atlantic Canada, with an estimated population of only 356 individuals. Over the last decade, their distribution shifted significantly, with approximately 40% of the population moving from traditional summer feeding grounds to the Gulf of St. Lawrence (GSL). The high number of mortalities observed in 2017 and 2019 have led Fisheries and Oceans Canada to implement a monitoring program aimed at detecting whales, triggering protective management measures, and gathering information on their spatial and temporal distribution. Data from the surveys conducted between August 2017 and November 2022 were combined with environmental variables in Generalized Additive Mixed Models to identify factors influencing NARW distribution in the GSL and predict their likelihood of occurrence. Models were developed using data collected between 2017 and 2020, considering two-month periods, half-seasons and the entire season of NARW occurrence. Period-specific models were found to outperform the global model when tested over the training dataset (2017-2020 observations). However, the global model trained with data from the entire season of occurrence proved to be more accurate when tested against the independent observation dataset acquired in 2021-2022. The best model included depth, sea surface temperature, salinity and chlorophyll a as important factors influencing the probability of NARW occurrence. Additionally, it included mean sea level anomalies, thermal fronts, current speed, and bottom topography, likely due to their role in prey aggregation processes. The predicted probability maps generated by this study highlight the importance of several areas in the GSL, such as Shediac Valley, Bradelle Valleys, and West Anticosti, and provide insights into seasonal variations in distribution. These maps will inform the designation of conservation areas and guide management strategies to mitigate risks posed by shipping and fishing activities to this endangered population.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".