Pulse Brain · Growing Health Evidence Index
Tier 3 — Observational / field trialPreprint

MorphOTU: A universal image-based framework for delineating biodiversity discovery

Zhan, Z.; Chen, W.; Liu, X.; Yue, L.; Zhang, F.

bioRxiv · 2026

Read source ↗ All evidence

Summary

The absence of a scalable system for organizing the vast majority of unidentified species becomes the central obstacle in biodiversity science. Existing molecular and computer-vision methods rely on DNA material or closed-set labels, which hamper biodiversity quantification under the open, incomplete conditions that characterize real ecosystems. Here, we introduce morphOTUs, a general image-based framework that constructs operational units of biodiversity directly from phenotype. Using morphOTU, we derive image-based OTUs across five plant and beetle datasets spanning heterogeneous imaging conditions. These units recover species-level boundaries, retain coherent structure when most species are "unseen" during training, and accurately approximate richness and Shannon diversity indices even under sparse labeling or limited sampling. Visual explanations reveal that morphOTU consistently focuses on biologically meaningful traits and captures continuous phenotypic variation. By providing a scalable and open-set framework for quantifying phenotypic diversity, morphOTUs enable biodiversity assessment that includes unnamed species and unlock the ecological value of rapidly expanding digital image repositories.

Outcomes reported

The absence of a scalable system for organizing the vast majority of unidentified species becomes the central obstacle in biodiversity science. Existing molecular and computer-vision methods rely on DNA material or closed-set labels, which hamper biodiversity quantification under the open, incomplete conditions that characterize real ecosystems. Here, we introduce morphOTUs, a general image-based framework that constructs operational units of biodiversity directly from phenotype. Using morphOTU, we derive image-based OTUs across five plant and beetle datasets spanning heterogeneous imaging conditions. These units recover species-level boundaries, retain coherent structure when most species are "unseen" during training, and accurately approximate richness and Shannon diversity indices even under sparse labeling or limited sampling. Visual explanations reveal that morphOTU consistently focuses on biologically meaningful traits and captures continuous phenotypic variation. By providing a scalable and open-set framework for quantifying phenotypic diversity, morphOTUs enable biodiversity assessment that includes unnamed species and unlock the ecological value of rapidly expanding digital image repositories.

Theme
Farming systems, soils & land use
Subject
Other / interdisciplinary
Study type
Research
Source type
Preprint
Status
Preprint
Geography
United Kingdom
System type
Other
DOI
10.64898/2026.04.28.721370
Catalogue ID
IRmoxajxbw-d60302
Pulse AI · ask about this record

Dig deeper with Pulse AI.

Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.