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 .
The Permian–Triassic was a major transition in the evolution of life in the earth history, when happened the greatest mass extinction during the Phanerozoic and an unusually prolonged or delayed recovery. Most studies have been carried in the marine facies while very few in the continental facies. On land, plants play a great role in the interaction of climate and terrestrial ecosystems. Here we present a regional case of stepwise recovery of vegetation in North China. Prior to the Permian–Triassic mass extinction, the voltzialean conifer forest community dominated in the Changhsingian. Consequently, the extinction event wiped out of the voltzialean conifer forest community, probably conciding with the extension of the red beds. The first post-crisis flora was an Induan herbaceous lycopsid community, succeeded by the Pleuromeia–Neocalamites shrub marsh community. A pteridosperm shrub woodland community dominated for a short time in the late Early Triassic along with the reappearance of insect herbivory. In the early Middle Triassic, gymnosperm forest communities gradually rose to predominate in both uplands and lowlands along with other diverse plant communities, indicating the beginning of the establishment of the Mesophytic Flora. In the late Middle Triassic–Late Triassic, it was occupied by the Danaeopsis–Symopteris flora and the opportunism elements gradually were replaced by the advanced taxa, which represents the complete establishment of the Mesophytic Flora.