Reviewer #1 (Public Review): Boosting biodiversity monitoring using smartphone-driven, rapidly accumulating community-sourced data
Bibliographic record
Abstract
Ecosystem services, which derive in part from biological diversity, are a fundamental support for human society. However, human activities are causing harm to biodiversity, ultimately endangering these critical ecosystem services. Halting nature loss and mitigating these impacts necessitates comprehensive biodiversity distribution data, a requirement for implementing the Kunming-Montreal Global Biodiversity Framework. To efficiently collect species observations from the public, we launched the ‘Biome’ mobile application in Japan. By employing species identification algorithms and gamification elements, the app has gathered >6M observations since its launch in 2019. However, community-sourced data often exhibit spatial and taxonomic biases. Species distribution models (SDMs) enable infer species distribution while accommodating such bias. We investigated Biome data’s quality and how incorporating the data influences the performance of SDMs. Species identification accuracy exceeds 95% for birds, reptiles, mammals, and amphibians, but seed plants, molluscs, and fishes scored below 90%. The distributions of 132 terrestrial plants and animals across Japan were modeled, and their accuracy was improved by incorporating our data into traditional survey data. For endangered species, traditional survey data required >2,000 records to build accurate models (Boyce index ≥ 0.9), though only ca.300 records were required when the two data sources were blended. The unique data distributions may explain this improvement: Biome data covers urban-natural gradients uniformly, while traditional data is biased towards natural areas. Combining multiple data sources offers insights into species distributions across Japan, aiding protected area designation and ecosystem service assessment. Providing a platform to accumulate community-sourced distribution data and improving data processing protocol will contribute to not only conserving natural ecosystems but also detecting species distribution changes and testing ecological theories.
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 | 0.044 | 0.308 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.004 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.007 | 0.006 |
| Open science | 0.006 | 0.004 |
| Research integrity | 0.018 | 0.008 |
| Insufficient payload (model declined to judge) | 0.052 | 0.022 |
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".