Contrasting the efficiency of imaging systems for mesozooplankton indicators across Pacific and Atlantic coastal ecosystems
Bibliographic record
Abstract
Mesozooplankton have a pivotal role in marine food webs, linking primary producers to higher trophic levels. Their abundance and traits serve as key indicators of ecosystem structure and function, making them essential components of long-term ocean monitoring. However, the need to monitor biodiversity and functional traits, combined with their pronounced spatial and temporal variability, requires extensive sampling and presents significant laboratory bottlenecks and cost-related challenges. Imaging instruments, combined with automated image classifiers such as Ecotaxa, offer a promising solution by enabling high-throughput, cost-effective processing of large numbers of samples, while also providing highly precise trait measurements previously unattainable with traditional methods. In this study, we compare the performance of human-sorted microscopy, human-sorted images and computer-sorted images across three contrasting coastal ecosystems on Canada's Pacific and Atlantic coasts. First, we demonstrated that upfront investment in identifying a larger number of images contributed to the development of robust regional image libraries, which significantly enhanced the performance of automated classifiers (e.g., mean F1 score = 0.54 with up to 200 images per taxon and 0.68 with up to 5000 images per taxon). Results showed that automated image classification performance varies with specimen characteristics such as symmetry, geodesic thickness, and taxa richness. We then assessed how each method captures local mesozooplankton diversity and altered key ecological indicators. Based on observed ecosystem-specific differences, we provide recommendations for optimizing classification workflows in relation to local diversity patterns. This study provides large-scale empirical evidence that investing in the development of regional image libraries enhances the scalability and accuracy of coastal ecological assessments. These emerging digital assets have the potential to significantly advance ecosystem monitoring and management. • Differences in automated zooplankton classification performance between regions. • Larger regional image libraries led to better model performance. • Differences between microscopy and imaging between regions. • Taxonomic resolution impacted classification accuracy.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".