254 Recent Advances in Fossil Imaging

This session will bring together an array of scientists who are tackling the application of imaging fossils with modern techniques.

Wednesday, 22 October 2025
8:00 AM - 12:00 PM
HBGCC, 304B

Deep Learning Reveals Complex Sediment Penetrative Burrows from the Terminal Ediacaran of Namibia

Paper number: 254-9
Program: Technical Sessions
Time: 10:15 AM – 10:30 AM

Authors

Abstract

Sediment penetrative burrowing is a critical process that exerts significant control on seafloor structure, chemistry, and ultimately, habitability. This behavioral innovation has historically been associated with the early Cambrian; however, in recent years late Ediacaran sites have yielded several notable examples of these behaviors, thus suggesting the evolutionary roots of the modern, animal dominated benthos extend further back than previously thought. However, assessment of these putative early trace fossils is often limited by their ephemerality, preservation, and relative lack of diagnostic form. As such, deep learning approaches to image analysis represent a promising avenue for exploration of these structures -- and behavioral innovations -- in 3D.

Here we provide evidence for late Ediacaran (c. 539.41 Ma) sediment penetrative burrow-like structures from the basal Spitskop Member of the Nama Group, Namibia, segmented from CT scans with a 2D U-Net model. These structures, found in association with serially probing worm traces, bear a variety of forms, including spirals, with many at least 4 cm deep. As such, these structures potentially represent among both the earliest and deepest examples of sediment penetrative burrowing, and as such bear significant import for our understanding of the timing of these critical ecosystem engineering behaviors prior to the Cambrian boundary.

Geological Society of America Abstracts with Programs. Vol. 57, No. 6

doi: 10.1130/abs/2025AM-414864

© Copyright 2025 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.