Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Spain

European Research Council grant · Running

NAIVE Neotropical AI-assisted VErtebrate identification through ZooMS

Coordinator
Universitat Autonoma De Barcelona, Spain
Runs
1 December 2026 to 31 May 2028
Status
Running
EU funding
€150k
Total cost
—
Partners
2 organisations in 1 countries
Type
European Research Council grant
Grant agreement
101334879

What the project is doing

In the project's own words, from its summary on CORDIS.

The biodiversity crisis in the Neotropics, driven by illegal wildlife trade and habitat loss, threatens global food security and social equity. Reversing this “defaunation” requires deep historical baselines found in archaeological remains. However, extreme bone fragmentation renders 90-95% of these specimens, and many confiscated wildlife products, taxonomically unidentifiable through traditional morphology. While DNA analysis can bridge this gap, it remains prohibitively expensive and slow for large-scale ecological or forensic applications.

Zooarchaeology by Mass Spectrometry (ZooMS) offers a cost-effective alternative, but faces two critical bottlenecks: the lack of a comprehensive Neotropical reference library and a heavy reliance on expert-led manual peak matching. This subjectivity and low scalability are particularly problematic for wildlife forensics, where rapid, standardized decision-making is essential. NAIVE will transform collagen peptide mass fingerprinting into the first AI-driven taxonomic intelligence platform for megadiverse vertebrate systems.

The project will systematically curate a collagen reference dataset for key Brazilian species by combining LC-MS/MS and MALDI-TOF MS, prioritizing CITES-listed and trafficked taxa. Furthermore, NAIVE will develop: i) a supervised hierarchical AI classifier and a degradation-aware spectral model capable of identifying taxa from incomplete or fragmented peptide fingerprints; ii) a probabilistic confidence scoring system to guide enforcement, determining when results are definitive or require escalation to DNA analysis; iii) a cloud-based spectral intelligence platform for automated data upload, classification, and reporting.

This digital transformation converts ZooMS from an expert-dependent laboratory method into a scalable forensic screening technology. By integrating proteomics, AI, and conservation policy, NAIVE will position itself at the forefront of next-generation biodiversity forensic technologies.

Topics

Who is involved

OrganisationCityCountryRole
Universitat Autonoma De BarcelonaCerdanyola Del VallesSpainCoordinator
Vertical Imaginae Solutions S.l.SabadellSpainParticipant

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI