Guiana Dolphin long term survey by deep learning
Bibliographic record
Abstract
The Guiana dolphin (Sotalia guianensis), commonly known as estuarine dolphin is one of the ten dolphins in great danger of extinction, currently classified as “near threatened” in the IUCN Red List of Threatened Species (IUCN, 2019). Indeed this species has restricted global distribution [1] as it is only found across the South-Western Atlantic OceanCentral and South America coast and is notably resident of the Guiana coastline. Due to its sedentary nature, Guiana dolphins are vulnerable to its habitat degradation and fall easily victim to bycatch in gillnets [2]. Monitoring the population activity and assessing the anthropic impact is therefore fundamental for conservation. Since 2021 a long term survey has been deploying multiple hydrophones using deep learning for the automatic detection of Guiana dolphin vocalization. With the beginning of shoreline pile driving in 2023, we could simultaneously conduct the anthropophony survey in one of the 3 stations, assessing the human influences on this endangered species.[1] Borobia, Monica & Siciliano, Salvatore & Lodi, Liliane & Hoek, Wyb. (2011). Distribution of the South American dolphin Sotalia fluviatilis. Canadian Journal of Zoology. 69. 1025-1039. 10.1139/z91-148.[2] Almeida, Inaê & Percequillo, Alexandre & Rollo, Mario. (2024). Surviving the Tide: Assessing Guiana dolphin persistence amidst growing threats in a protected estuary in South-eastern Brazil. Journal for Nature Conservation. 82. 1-9. 10.1016/j.jnc.2024.126713.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".