An image dataset of cleared, x-rayed, and fossil leaves vetted to plant family for human and machine learning

Abstract

Leaves are the most abundant and visible plant organ, both in the modern world and the fossil record. Identifying foliage to the correct plant family based on leaf architecture is a fundamental botanical skill that is also critical for isolated fossil leaves, which often, especially in the Cenozoic, represent extinct genera and species from extant families. Resources focused on leaf identification are remarkably scarce; however, the situation has improved due to the recent proliferation of digitized herbarium material, live-plant identification applications, and online collections of cleared and fossil leaf images. Nevertheless, the need remains for a specialized image dataset for comparative leaf architecture. We address this gap by assembling an open-access database of 30,252 images of vouchered leaf specimens vetted to family level, primarily of angiosperms, including 26,176 images of cleared and x-rayed leaves representing 354 families and 4,076 of fossil leaves from 48 families. The images maintain original resolution, have user-friendly filenames, and are vetted using APG and modern paleobotanical standards. The cleared and x-rayed leaves include the Jack A. Wolfe and Leo J. Hickey contributions to the National Cleared Leaf Collection and a collection of high-resolution scanned x-ray negatives, housed in the Division of Paleobotany, Department of Paleobiology, Smithsonian National Museum of Natural History, Washington D.C.; and the Daniel I. Axelrod Cleared Leaf Collection, housed at the University of California Museum of Paleontology, Berkeley. The fossil images include a sampling of Late Cretaceous to Eocene paleobotanical sites from the Western Hemisphere held at numerous institutions, especially from Florissant Fossil Beds National Monument (late Eocene, Colorado), as well as several other localities from the Late Cretaceous to Eocene of the Western USA and the early Paleogene of Colombia and southern Argentina. The dataset facilitates new research and education opportunities in paleobotany, comparative leaf architecture, systematics, and machine learning.

Decoding family‐level features for modern and fossil leaves from computer‐vision heat maps

“…Fossils at right were manually marked, based on visual inspection, with unfilled squares to represent potential regions of similarity to computer‐vision hotspot locations on cleared leaves from the same family shown at left. All fossil images are from the open‐access image collection of Wilf et al (2021). Anacardiaceae .…”

“…Images and voucher data from the collection can be viewed online at the Cleared Leaf Image Database website (www. clearedleavesdb.org; Das et al, 2014; higher-resolution images are available via Wilf et al, 2021). Dipteronia sinensis (1134).…”

“…All published heat maps used here, placed by Wilf et al (2016) on Figshare (https://doi.org/10.6084/m9.figshare.1521157.v1), were generated from prepared images of the Jack A. Wolfe contribution to the National Cleared Leaf Collection (NCLC‐W), as described by Wilf et al (2016); NCLC‐W is housed in the Division of Paleobotany, Smithsonian National Museum of Natural History, Washington, D.C. Images and voucher data from the collection can be viewed online at the Cleared Leaf Image Database website (http://www.clearedleavesdb.org; Das et al, 2014; higher‐resolution images are available via Wilf et al, 2021).…”

“…No published computer‐vision algorithms can identify fossil leaves yet, and no computer‐vision algorithms were used to find these examples. The examples were found by visually inspecting an open‐access image database of vetted fossil leaves identified at the family level (Wilf et al, 2021).…”

First fossil-leaf floras from Brunei Darussalam show dipterocarp dominance in Borneo by the Pliocene

“…For cleared leaves, we consulted slides and images from the National Cleared Leaf Collection (NCLC) held in the Division of Paleobotany of the National Museum of Natural History, Washington, D.C., including both the Jack A. Wolfe (NCLC-W) and Leo J. Hickey (NCLC-H) contributions. These collections are also online at (NCLC-W) and (NCLC-H) and were recently consolidated digitally as part of an open access leaf-image dataset ( Wilf et al, 2021 ).…”