Automatic taxonomic identification based on the Fossil Image Dataset (>415,000 images) and deep convolutional neural networks

Abstract

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.

Automated graptolite identification at high taxonomic resolution using residual networks

“…Liu et al. 30 evaluated the results of three typical deep CNN (convolutional neural network) architectures on a large-scale fossil dataset of more than 50 clades including invertebrates, vertebrates, plants, microfossils, and fossil traces from five hyperclades. Hou et al.…”

Automatic identification of conodont species using fine-grained convolutional neural networks

“…These CNNs generally show a trend of deeper and deeper network layers and more complex network architectures, all of which play an important role in image recognition tasks, while the application of these CNNs in fields such as medicine, agriculture, and transportation has greatly contributed to the development of deep learning. Not coincidentally, increasingly sophisticated CNNs are widely used in various fields of geology, such as paleontological fossil identification (Keçeli et al, 2018;de Lima et al, 2019;Hsiang et al, 2019;Mitra et al, 2019;Bourel et al, 2020;Marchant et al, 2020;Pires de Lima et al, 2020;Romero et al, 2020;An et al, 2022;Liu et al, 2022;Wang et al, 2022), geological prospecting Li et al, 2021), carbonate microfacies analysis (Liu and Song, 2020), and mineral rock identification (Xu and Zhou, 2018;Zhang et al, 2018;Baraboshkin et al, 2020;Guo et al, 2020;Alférez et al, 2021).…”

Automatic identification and morphological comparison of bivalve and brachiopod fossils based on deep learning

“…To reduce the workload and work difficulty for researchers, automatic fossil identification methods relying on machine learning have been proposed extensively in recent years, among which models using convolutional neural networks (CNNs) ( e.g ., VGG-16 ( Simonyan & Zisserman, 2014 ), Inception-ResNet ( Szegedy et al, 2017 ), GoogLeNet ( Szegedy et al, 2015 ), etc .) have achieved good results ( Dionisio et al, 2020 ; Liu & Song, 2020 ; Liu et al, 2023 ; Niu & Xu, 2022 ; Wang et al, 2022 ; Ho et al, 2023 ). Other supervised ( e.g.…”