Abstract
PREMISE: Angiosperm leaves present a classic identification problem due to their morphological complexity. Computer-vision algorithms can identify diagnostic regions in images, and heat map outputs illustrate those regions for identification, providing novel insights through visual feedback. We investigate the potential of analyzing leaf heat maps to reveal novel, human-friendly botanical information with applications for extant- and fossil-leaf identification. METHODS: We developed a manual scoring system for hotspot locations on published computer-vision heat maps of cleared leaves that showed diagnostic regions for family identification. Heat maps of 3114 cleared leaves of 930 genera in 14 angiosperm families were analyzed. The top-5 and top-1 hotspot regions of highest diagnostic value were scored for 21 leaf locations. The resulting data were viewed using box plots and analyzed using cluster and principal component analyses. We manually identified similar features in fossil leaves to informally demonstrate potential fossil applications. RESULTS: The method successfully mapped machine strategy using standard botanical language, and distinctive patterns emerged for each family. Hotspots were concentrated on secondary veins (Salicaceae, Myrtaceae, Anacardiaceae), tooth apices (Betulaceae, Rosaceae), and on the little-studied margins of untoothed leaves (Rubiaceae, Annonaceae, Ericaceae). Similar features drove the results from multivariate analyses. The results echo many traditional observations, while also showing that most diagnostic leaf features remain undescribed. CONCLUSIONS: Machine-derived heat maps that initially appear to be dominated by noise can be translated into human-interpretable knowledge, highlighting paths forward for botanists and paleobotanists to discover new diagnostic botanical characters.
Abstract from the paper’s OpenAlex record; open copy licensed other-oa. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 6
Claim · model-written summary
Hotspots were concentrated on secondary veins in Salicaceae, Myrtaceae and Anacardiaceae.
- Taxon
- Salicaceae, Myrtaceae, AnacardiaceaeSalicaceaeMyrtaceaeAnacardiaceaee1
- Organ / stage
- secondary veinse1
- Outcome
- Hotspots were concentratede1
Verbatim
e1“Hotspots were concentrated on secondary veins (Salicaceae, Myrtaceae, Anacardiaceae)”
Claim · model-written summary
Hotspots were concentrated on tooth apices in Betulaceae and Rosaceae.
- Taxon
- Betulaceae, RosaceaeBetulaceaeRosaceaee2
- Organ / stage
- tooth apicese2
- Outcome
- Hotspots were concentratede2
Verbatim
e2“Hotspots were concentrated on secondary veins (Salicaceae, Myrtaceae, Anacardiaceae), tooth apices (Betulaceae, Rosaceae)”
Claim · model-written summary
Hotspots were concentrated on the margins of untoothed leaves in Rubiaceae, Annonaceae and Ericaceae.
Verbatim
e3“Hotspots were concentrated on secondary veins (Salicaceae, Myrtaceae, Anacardiaceae), tooth apices (Betulaceae, Rosaceae), and on the little-studied margins of untoothed leaves (Rubiaceae, Annonaceae, Ericaceae)”
Claim · model-written summary
Similar features drove the results of multivariate analyses.
Verbatim
e4“Similar features drove the results from multivariate analyses”
e5“Heat maps of 3114 cleared leaves of 930 genera in 14 angiosperm families were analyzed”
Claim · model-written summary
Most diagnostic leaf features of angiosperms remain undescribed.
Verbatim
e6“while also showing that most diagnostic leaf features remain undescribed”
e5“Heat maps of 3114 cleared leaves of 930 genera in 14 angiosperm families were analyzed”
Claim · model-written summary
Similar features were identified in fossil leaves.
Verbatim
e7“We manually identified similar features in fossil leaves to informally demonstrate potential fossil applications”
e5“Heat maps of 3114 cleared leaves of 930 genera in 14 angiosperm families were analyzed”