Utilising affordable smartphones and open-source time-lapse photography for pollinator image collection and annotation
Bibliographic record
Abstract
Monitoring plant-pollinator interactions is crucial for understanding the factors influencing these relationships across space and time. Traditional methods in pollination ecology are resource-intensive, while time-lapse photography offers potential for non-destructive and automated complementary techniques. However, accurate identification of pollinators at finer taxonomic levels (i.e., genus or species) requires high enough image quality. This study assessed the feasibility of using a smartphone setup to capture time-lapse images of arthropods visiting flowers and evaluated whether these images offered sufficient resolution for arthropod identification by taxonomists. Smartphones were positioned above target flowers from various plant species in urban green areas around Leipzig and Halle, Germany. We present proportions of arthropod identifications (instances) at different taxonomic levels (order, family, genus, species) based on visible features in the images as interpreted by taxonomists. We document whether limitations stem from the automated setup (e.g., fixed positioning preventing capture of distinguishing features despite high image resolution) or from low image quality. Recommendations are provided to address these challenges. Our results indicate that 89.81% of all Hymenoptera instances were identified to family level, 84.56% of pollinator family instances to genus level, and only 25.35% to species level. We were less able to identify Dipterans to finer taxonomic levels, with nearly 50% of instances not identifiable to family level, and only 26.18% and 15.19% identified to genus and species levels. This was due to their small size and the more challenging features needed for identification (e.g., in the wing veins). Advancing smartphone technology, along with their accessibility, affordability, and user-friendliness, offers a promising option for coarse-level pollinator monitoring.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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) | 0.000 | 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 teacher head, 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".