A stomata imaging and segmentation pipeline incorporating generative AI to reduce dependency on manual groundtruthing
Bibliographic record
Abstract
Stomata regulate gas and water exchange in plants and are crucial for plant productivity and survival, making their trait analysis essential for advancing plant biology research. While current machine learning methods enable automated stomatal trait extraction, existing approaches face significant limitations that require extensive manual labeling for training and additional human annotation when applied to new species. This study presents an automated system for extracting stomatal traits from Pisum sativum (pea) leaves that addresses these challenges through generative artificial intelligence. Our pipeline integrates imaging, detection, segmentation, and synthetic data generation processes. A nail polish impression technique was employed to prepare leaf microscopic images, followed by the application of deep learning networks to identify and segment stomata in these images. By including generative AI-produced synthetic data, our system achieves high segmentation accuracy across species, reducing manual relabeling requirements. This approach enables seamless cross-species model adaptation for many cases, alleviating the annotation bottleneck that often limits machine learning applications in plant biology. Our results demonstrate the pipeline's effectiveness for automated stomatal trait extraction and highlight generative AI's transformative potential in advancing stomatal detection methodologies, offering a scalable solution for broad-scale comparative stomatal analysis.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".