Search

The rapid and accurate taxonomic identification of fossils is of great significance in paleontology, biostratigraphy, and other fields. However, taxonomic identification is often labor-intensive and tedious, and the requisition of extensive prior knowledge about a taxonomic group also requires long-term training. Moreover, identification results are often inconsistent across researchers and communities. Accordingly, in this study, we used deep learning to support taxonomic identification. We used web crawlers to collect the Fossil Image Dataset (FID) via the Internet, obtaining 415,339 images belonging to 50 fossil clades. Then we trained three powerful convolutional neural networks on a high-performance workstation. The Inception-ResNet-v2 architecture achieved an average accuracy of 0.90 in the test dataset when transfer learning was applied. The clades of microfossils and vertebrate fossils exhibited the highest identification accuracies of 0.95 and 0.90, respectively. In contrast, clades of sponges, bryozoans, and trace fossils with various morphologies or with few samples in the dataset exhibited a performance below 0.80. Visual explanation methods further highlighted the discrepancies among different fossil clades and suggested similarities between the identifications made by machine classifiers and taxonomists. Collecting large paleontological datasets from various sources, such as the literature, digitization of dark data, citizen-science data, and public data from the Internet may further enhance deep learning methods and their adoption. Such developments will also possibly lead to image-based systematic taxonomy to be replaced by machine-aided classification in the future. Pioneering studies can include microfossils and some invertebrate fossils. To contribute to this development, we deployed our model on a server for public access at www.ai-fossil.com. [ABSTRACT FROM AUTHOR]

The Permian–Triassic mass extinction was the largest biotic extinction event in the Phanerozoic and affected both marine and continental life. Marine Permian–Triassic transitional sequences can be correlated in many regions, but this has proved difficult for continental successions. A growing number of studies show that spinicaudatans are some of the most common fossils in continental strata and can be used as index fossils for continental stratigraphic division and correlation. Here we document the morphology and biostratigraphic significance of Euestheria gutta based on well‐preserved fossils from southwestern China. It shows strong intraspecific morphological variation, while the most important feature is the strongly convex larval valve and significant finely pitted to weakly reticulated ornamentation on the growth bands. Evidence from palaeobotany, charcoal, and organic carbon isotopes indicated that the continental mass extinction in southwestern China was marked by the catastrophic loss of tropical rainforest vegetation, enhanced wildfire and a negative carbon isotope excursion (CIE) during the P–Tr transition. Meanwhile, abundant E. gutta first appeared at the onset of the negative CIE and just above the horizon of the loss of macroflora. Based on the global geographic distribution of E. gutta and temporal correlation, we conclude that this species existed from the latest Permian to the earliest Triassic, and the occurrence of E. gutta could be used as an index fossil of the continental mass extinction interval or P–Tr transitional beds. [ABSTRACT FROM AUTHOR]

The Triassic rocks are widespread in China, and both marine and terrestrial strata are well developed. The Triassic stratigraphic architecture of China is very complex in both spatial variation of the so-called "South Marine and North Continental", i.e. the southern areas of China occupied mostly by marine facies while the northern China by terrestrial facies during the Triassic Period, and temporal transition of the "Lower Marine and Upper Continental", i.e. the lower part of the Triassic System composed mainly of marine facies and the upper part of terrestrial strata especially in South China. Although the Global Stratotype Section and Point (GSSP) of the Permian-Triassic boundary is located in South China, the Triassic of China except for some marine Lower-Middle Triassic depositions shows significantly local characteristics and is hardly correlated with the global chronostratigraphic chart. Consequently, the Triassic of China contains not only the international research hotspots but also difficult points in stratigraphic study. This paper aims to present a brief review of the Triassic in China, including chronostratigraphy, biostratigraphy, magnetostratigraphy and chemostratigraphy, and summarize an integrated Triassic stratigraphic framework of China. Accordingly, a stratigraphic correlation is proposed for the lithostratigraphic sequences among the three tectono-paleogeographic stratigraphic regions. The comprehensive study indicates that ammonoids are the classic index fossils in Triassic biostratigraphy but conodonts are more advantageous in the study and definition of the Triassic chronostratigraphic boundaries. China still has the potential to optimize the GSSPs of the Induan-Olenekian boundary and Olenekian-Anisian boundary. The correlation of the Permian-Triassic boundary between marine and terrestrial facies might be achieved with the help of the Permian-Triassic "transitional bed" and its related biotic and environmental events in association with the biostratigraphic study of conchostracan, vertebrate and plant fossils. In addition, the carbon isotopes have been proved to be one of the powerful methods in marine Triassic stratigraphic study, whereas the oxygen and strontium isotopes may be additional important bridges to establish the correlation between the marine and terrestrial strata, but as yet lacking of relevant studies in terrestrial strata. Considering the most stratigraphic intervals of the Triassic and the terrestrial Triassic in China are difficult to be correlated to the global chart, the proposed Chinese (regional) Triassic chronostratigraphic chart of marine and terrestrial stages would be of importance to the study of Chinese Triassic stratigraphy and related aspects, but the stages must be conceptually in line with international standards and studied as soon as possible in order to finalize the definition. [ABSTRACT FROM AUTHOR]

The end-Permian mass extinction, the largest biological crisis in Earth history, is currently understood in the context of Siberian Traps volcanism introducing large quantities of green- house gases to the atmosphere, culminating in the Early Triassic hothouse. In our study, the late Permian and Early Triassic atmospheric CO2 history was reconstructed by applying the paleosol pCO2 barometer. Atmospheric pCO2 shows an approximate 4x increase from mean concentrations of 412-919 ppmv in the late Permian (Changhsingian) to maximum levels between 2181 and 2610 ppmv in the Early Triassic (late Griesbachian). Mean CO2 estimates for the later Early Triassic are between 1261-1936 ppmv (Dienerian) and 1063-1757 ppmv (Spathian). Significantly lower concentrations ranging from 343 to 634 ppmv are reconstructed for the latest Early to Middle Triassic (Anisian). The 5 m.y. episode of elevated pCO2 suggests that negative feedback mechanisms such as silicate weathering were not effective enough to reduce atmospheric pCO2 to precrisis levels and that marine authigenic clay formation (i.e., reverse weathering) may have been an important component of the global carbon cycle keeping atmospheric pCO2 at elevated levels. [ABSTRACT FROM AUTHOR]