Life & medical sciences · OECD FoS 1.6 · China MoE 0713 生态学
Ecology & biodiversity
生态学与生物多样性
L2Local breakthroughs ↑ Rising Score 2.10 · Last reviewed 2026-10-21 · Next review 2027-01-19
BIGGEST BREAKTHROUGH 2021-03 AI · majorField · major
BirdNET deep-learning bird sound ID (Ecological Informatics) ↗
Standard acoustic ID tool for ~1,000 species
Why this level
Acoustic (BirdNET) and camera-trap classifiers are routine; Europe's Biodiversa+ pilot deployed ~200 AI sensors at 70 sites, moving from pilots to networks.
S = 0.30·method + 0.35·discovery + 0.25·adoption + 0.10·education (education scores 0 when there is no evidence; if empty, the other weights are renormalised)
Sources
Composite 1.5–2.49: at least one peer-reviewed/officially verified AI-key result, or one dimension at 3; routine workflow largely unchanged. All levels →
Research directions
Acoustic species IDCamera-trap classificationHabitat mapping
Papers
- Bridging the deployment gap in automated moth monitoring through biodiversity foundation models
Foundation models close the lab-to-field gap
2026-10-20 · Scientific Reports
- A global assessment of BirdNET performance: Differences among continents, biomes, and species
First global independent evaluation; shows regional bias
2026-01 · Ecological Indicators
- Perspectives in machine learning for wildlife conservation
Field perspective
2022-02-09 · Nature Communications
- BirdNET: A deep learning solution for avian diversity monitoring
Standard acoustic ID tool for ~1,000 species
2021-03 · Ecological Informatics
- Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning
Volunteer-level accuracy on 3.2M images, saving ~8 years of labour
2018-06-05 · Proceedings of the National Academy of Sciences
- WildMAE: Structure-Aware Masked Autoencoding for Wildlife Image Reconstruction
A structure-aware MAE improves camera-trap image reconstruction on Snapshot Serengeti.
2026-10-20 · arXiv · Yicheng Zhang, Yujie Jin, Ke Zhang, Jiaxin Wu
- Phylogenetic estimation of diversity-dependent biogeographic rates using deep learning
Introduces DDGeoSSE and uses deep learning to estimate diversity-dependent speciation, extinction and dispersal rates from phylogenies.
2026-10-15 · bioRxiv · Soewongsono, A. C., Landis, M. J.
- Recording context and data splitting can inflate acoustic re-identification accuracy across species and studies
Recording context and data splitting can inflate ML acoustic re-identification accuracy, often reported above 90%.
2026-10-09 · bioRxiv · Wallington, G., Lighten, J.
- Fully integrative species delimitation with machine learning and diverse data types in delimSOM 2.0
delimSOM 2.0 uses multilayer self-organising maps to integrate genomic, phenotypic, ecological and spatial data for species delimitation.
2026-10-07 · bioRxiv · Schoenberger, D., Pyron, R. A., Dupuis, J. R.
- DAPHNE: A global database of pest herbivores and their natural enemies
Uses an open-weight LLM to mine abstracts and build a global database of pest–natural-enemy interactions.
2026-10-01 · bioRxiv · Scheepens, D. R., Freeman, R., Newbold, T.
- Acoustic Monitoring of Tropical Bats: Saccopteryx bilineata's response to habitat and time across a restoration gradient using a 2D-CNN
A lightweight 2D CNN detects Saccopteryx bilineata echolocation calls to study activity across a restoration gradient.
2026-09-29 · bioRxiv · Secord, I. L., Zhang, X., Preston-Allen, R., Banks-Leite, C.
- PlanktonLake-CEREEP- A Freshwater Plankton Image Dataset with Semi-Automated Label Cleaning
A labelled freshwater plankton image dataset with semi-automated label cleaning for ML classifiers.
2026-09-29 · bioRxiv · Dechaumet, L., Puppo, C., Carmignac, D., Blusseau, S.
- From arXiv, bioRxiv, medRxiv and OpenAlex (last ~30 days); summaries written by AIMap from the abstract.
Milestones 7
Big glowing nodes are leaps: AI leap cool · Field leap warm · double ring = both
-
Paper
Biodiversity foundation model transfers to field moth monitoring of 2,727 species (Sci. Rep.)Foundation models close the lab-to-field gap
Scientific Reports -
Paper
AI cuts wildlife tracking time from months to daysFaster tracking analysis
Phys.orgTo be verified -
Paper
Global BirdNET evaluation across 67 sites and 1,020 species (Ecological Indicators)First global independent evaluation; shows regional bias
Ecological IndicatorsTo be verified -
Deployment
Biodiversa+ automated monitoring stations pilot (~200 sensors)~200 AI sensors piloted in Europe
ZenodoTo be verified -
Paper
Perspectives in machine learning for wildlife conservation (Nat. Commun.)Field perspective
Nature Communications -
System
BirdNET deep-learning bird sound ID (Ecological Informatics)Standard acoustic ID tool for ~1,000 species
Ecological InformaticsTo be verified -
Paper
Deep learning automatically identifies, counts and describes wild animals in camera-trap images (PNAS)Volunteer-level accuracy on 3.2M images, saving ~8 years of labour
PNAS
No milestones match this filter.
More papers & repos 7
| Type | Title | Date |
|---|---|---|
| Paper | Bridging the deployment gap in automated moth monitoring through biodiversity foundation models | 2026-10-20 |
| Paper | A global assessment of BirdNET performance: Differences among continents, biomes, and species To be verified | 2026-01 |
| Paper | Perspectives in machine learning for wildlife conservation | 2022-02-09 |
| Paper | BirdNET: A deep learning solution for avian diversity monitoring To be verified | 2021-03 |
| Paper | Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning | 2018-06-05 |
| Repo | kahst/BirdNET-Analyzer To be verified | — |
| Repo | google/cameratrapai (SpeciesNet) To be verified | — |
Latest news 6
- Explainable artificial intelligence reveals spatially divergent effects of global change on mammalsNature CommunicationsenPaper
- Drones, AI and the future of wildlife conservationPhysics World（IOP）en
- AI cuts wildlife tracking time from months to daysPhys.orgenTo be verified