Machine Learning for Biodiversity Monitoring from Remote Sensing and Citizen Science Data
Bibliographic record
Abstract
Biodiversity loss is occurring at an unprecedented rate, threatening ecosystem services critical to food, water, and human health and well-being.Understanding species distributions is crucial for conservation policy.However, traditional species distribution modeling (SDM) methods focus on limited species or regions, leaving major knowledge gaps.A key barrier is the extensive effort needed for traditional monitoring.Remote sensing and citizen science offer opportunities to transform biodiversity monitoring and enable modeling complex ecosystems.This thesis introduces the task of mapping bird species to habitats by predicting encounter rates from satellite images and crowd-sourced citizen science data.We create a dataset with satellite images from the US and Kenya with labels derived from presenceabsence observation data from citizen science database eBird.We train baseline models and show that we can learn specific distribution patterns from these data.We also show that we can utilize the trained models to improve predictions in areas where data may be limited, specifically, where eBird checklists are limited.The released dataset -SatBird and pre-trained models enable scalable ecosystem modeling worldwide.i vii 6.4.2Multiple Hotspots scenario . . . . . . . . . .
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.003 |
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".