The Ediacara Biota represents a turning point in the evolution of life on Earth, signifying the transition from single celled organisms to complex, community-forming macrobiota. The exceptional fossil record of the soft-bodied Ediacara Biota provides critical insight into the nature of this transition and into ecosystem dynamics leading up to the so-called “Cambrian Explosion”. However, the preservation of non-biomineralizing organisms in a diversity of lithologies goes hand-in-hand with considerable taphonomic complexity that often shrouds true paleoecological and paleobiological signatures. We address the nature of this taphonomic complexity within the fossiliferous sandstones of the Ediacara Member in South Australia. Utilizing the most fossiliferous outcropping of the Ediacara Member, located at the Nilpena Station National Heritage Ediacara Fossil Site, we conduct a focused, taxon-level biostratinomic characterization of the tubular organism Funisia dorothea. Funisia is the most abundant body fossil in the Ediacara Member, making the characterization of its preservational variability essential to the accurate interpretation of regional paleobiology and paleoecology. We describe remarkable biostratinomic complexity in all Funisia populations at Nilpena, identifying four distinct preservational variants of internal and external molds and four additional successive biostratinomic grades corresponding to loss of external characters. Synthesis of these observations identify the most robust preservational forms of Funisia for use in paleobiological interpretation and highlight the important impact that Funisia's high abundance had on regional paleoecology and on population-scale preservation in the Ediacara Member.

The graphoglyptid trace fossil Paleodictyon, characterized by stratiform hexagonal meshes, typically occurs preserved at the base of deep-marine turbidites. There is, however, a growing number of occurrences of Paleodictyon in shallow-marine deposits as evidenced by new finds in the Eocene of Iran. The Paleodictyon-containing Asara Shale Member of the Karaj Formation accumulated in a shallow backarc basin. Parallel-crested wave-ripple marks and microbially induced sedimentary structures occur closely above and below the Paleodictyon-bearing strata. Shallow-marine Paleodictyon have so far been reported from morphologically structured, extensive, epicontinental seas, rift basins, and young, prograding passive continental margins, but mainly from foreland and backarc basins. In the two latter cases, the Paleodictyon producers appear to represent adaptive survivors. Initially they settled in abyssal to bathyal turbiditic settings that rapidly aggraded and/or became tectonically uplifted with slight changes to depositional conditions. Finally, the Paleodictyon producers lived in rather shallow water and became preserved by tempestites. This scenario argues against the continuous presence of Paleodictyon producers in shallow-marine settings, suggesting instead they appeared there recurrently.

Accurate taxonomic classification of microfossils in thin-sections is an important biostratigraphic procedure. As paleontological expertise is typically restricted to specific taxonomic groups and experts are not present in all institutions, geoscience researchers often suffer from lack of quick access to critical taxonomic knowledge for biostratigraphic analyses. Moreover, diminishing emphasis on education and training in systematics poses a major challenge for the future of biostratigraphy, and on associated endeavors reliant on systematics. Here we present a machine learning approach to classify and organize fusulinids—microscopic index fossils for the late Paleozoic. The technique we employ has the potential to use such important taxonomic knowledge in models that can be applied to recognize and categorize fossil specimens. Our results demonstrate that, given adequate images and training, convolutional neural network models can correctly identify fusulinids with high levels of accuracy. Continued efforts in digitization of biological and paleontological collections at numerous museums and adoption of machine learning by paleontologists can enable the development of highly accurate and easy-to-use classification tools and, thus, facilitate biostratigraphic analyses by non-experts as well as allow for cross-validation of disparate collections around the world. Automation of classification work would also enable expert paleontologists and others to focus efforts on exploration of more complex interpretations and concepts.