Automatic estimation of lipid content from <i>in situ</i> images of Arctic copepods using machine learning
Bibliographic record
Abstract
Abstract In Arctic marine ecosystems, large planktonic copepods form a crucial hub of matter and energy. Their energy-rich lipid stores play a central role in marine trophic networks and the biological carbon pump. Since the past ~15 years, in situ imaging devices provide images whose resolution allows us to estimate an individual copepod’s lipid sac volume, and this reveals many ecological information inaccessible otherwise. One such device is the Lightframe On-sight Keyspecies Investigation. However, when done manually, weeks of work are needed by trained personnel to obtain such information for only a handful of sampled images. We removed this hurdle by training a machine learning algorithm (a convolutional neural network) to estimate the lipid content of individual Arctic copepods from the in situ images. This algorithm obtains such information at a speed (a few minutes) and a resolution (individuals, over half a meter on the vertical), allowing us to revisit historical datasets of in situ images to better understand the dynamics of lipid production and distribution and to develop efficient monitoring protocols at a moment when marine ecosystems are facing rapid upheavals and increasing threats.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".