AI Science Tracker
EN

Global Estimation and Mapping of the Conservation Status of Tree Species Using Artificial Intelligence

Department of Biology, University of Fribourg, Fribourg, Switzerland; Interfaculty Bioinformatics Unit, University of Bern, Bern, Switzerland; Global Gothenburg Biodiversity Centre, Department of Biological and Environmental Sciences, Sweden, University of Gothenburg, Gothenburg, Sweden; Department of Biology, Philipps-University Marburg, Marburg, Germany; Swiss Institute of Bioinformatics, Fribourg, Switzerland · 29 Apr 2022 · biology

Discovery

Global Estimation and Mapping of the Conservation Status of Tree Species Using Artificial Intelligence

Source check: Source checked. Not independent scientific confirmation.

Finding: For 21,691 unassessed tree species, the authors estimated 22,889 of 58,429 species overall (39.1%) as possibly threatened, raising coverage to 52,191 species; results highlighted differences across taxa and regions. Fivefold cross-validation on assessed species: binary classifier accuracy 83.7% (87.1% for not threatened and 78.1% for possibly threatened); 100 Monte Carlo dropout predictions characterized uncertainty. This is predictive assessment, not expert-confirmed IUCN status; higher-confidence filtering yielded 90% accuracy for fewer cases.

Technology: A supervised fully connected neural network using species occurrence, range, biome, climate and human-footprint features predicted extinction-risk categories for species without IUCN assessments.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
A supervised fully connected neural network using species occurrence, range, biome, climate and human-footprint features predicted extinction-risk categories for species without IUCN assessments.
Test and result
For 21,691 unassessed tree species, the authors estimated 22,889 of 58,429 species overall (39.1%) as possibly threatened, raising coverage to 52,191 species; results highlighted differences across taxa and regions.
Limitation / still unknown
Fivefold cross-validation on assessed species: binary classifier accuracy 83.7% (87.1% for not threatened and 78.1% for possibly threatened); 100 Monte Carlo dropout predictions characterized uncertainty. This is predictive assessment, not expert-confirmed IUCN status; higher-confidence filtering yielded 90% accuracy for fewer cases.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.839792/full · https://www.fr.ch/sites/default/files/2022-09/silva-et-al-2022-fpls-global-tree-assessment.pdf

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary source full text Methods and Results; version/date checked against bibliographic record..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse biology discoveries.