Abstract
The calcimicrobial crust–cement boundstone in the Xiannüdong Formation of the Cambrian Series 2 is a distinctive reef type that reflects the evolution of late Precambrian stromatolite structures. This study provides a high-resolution dataset by segmenting large slab images of Girvanella-based reefs into 114 × 114 pixel tiles and annotating microfacies components through a point-counting-based automated labeling.The dataset includes PNG images and corresponding CSV files and can be used as training data for deep learning-based classification of carbonate microfacies. It contributes to research on the evolution of ancient marine ecosystems and the structure of early carbonate platforms.
Similar content being viewed by others
Data availability
All data supporting this study are available in Figshare (https://doi.org/10.6084/m9.figshare.31033825)12.
Code availability
All Python scripts developed for this study are already publicly available without restrictions. The complete codebase, including scripts for automated thin-section tile generation, annotation handling and class assignment, and visualization tools for label integration and validation, is permanently hosted on GitHub (https://github.com/neobassist/girvanella-boundstone-code) under a CC-BY 4.0 license.
The released materials include:
• Python scripts for automated thin-section tile generation
• Python code for annotation handling and class assignment
• Visualization tools for label integration and validation
The full workflow, including a Jupyter Notebook (.ipynb), a Conda environment configuration file (.yml), class label mapping files (label_map.py, label_map.csv), and a detailed README.md with step-by-step instructions, is already openly accessible via GitHub and is intended to ensure long-term accessibility and reproducibility.
References
Ezaki, Y., Liu, J., Adachi, N. & Yan, Z. Microbialite development during the protracted inhibition of skeletal-dominated reefs in the Zhangxia Formation (Cambrian Series 3) in Shandong Province, North China. PALAIOS 32, 559–571 (2017).
Adachi, N., Ezaki, Y., Liu, J. & Yan, Z. Cambrian through Ordovician reef transitions in North and South China: Changes in reef construction and background geobiological environments. Palaeogeography, Palaeoclimatology, Palaeoecology 630, 111804 (2023).
Wood, R., Zhuravlev, A. Y., Debrenne, F. & Riding, R. Functional biology and evolution of archaeocyathan reefs. Palaeontology 35, 1–17 (1992).
Riding, R. Microbial carbonates: the geological record of calcified bacterial-algal mats and biofilms. Sedimentology 47, 179–214 (2000).
Liu, W. & Zhang, X. Girvanella-coated grains from Cambrian oolitic limestone. Facies 58, 779–787 (2012).
Kim, D., Choh, S. J., Liu, W., Zhang, X. & Hong, J. Cambrian Series 2 calcimicrobial crust–cement boundstone in the Yangtze Block, China: A distinctive bioconstruction as a legacy of Precambrian reef evolution. Sedimentary Geology 477, 106804 (2025).
Liu, X. & Song, H. Automatic identification of fossils and abiotic grains during carbonate microfacies analysis using deep convolutional neural networks. Sedimentary Geology 410, 105790, https://doi.org/10.1016/j.sedgeo.2020.105790 (2020).
Koeshidayatullah, A. S., Rahman, A., Reza, R. A., Putra, A. P. & Abdullah, N. Fully automated carbonate petrography using deep convolutional neural networks. Pure KFUPM Repository https://pure.kfupm.edu.sa/en/publications/fully-automated-carbonate-petrography-using-deep-convolutional-ne (2020).
Nande, A. & Patwardhan, S. Intelligent identification of carbonate components based on YOLOv5. Facies https://link.springer.com/article/10.1007/s10347-024-00694-x (2024).
Vieira de Mello, A., da Silva, M. R. & dos Santos, R. Deep mineralogical segmentation of thin section images using CNN + QEMSCAN maps. arXiv preprint arXiv:2505.17008 https://arxiv.org/abs/2505.17008 (2025).
Al-Fahdi, A. et al. Lithofacies and microfacies and depositional environment model of the Cenozoic carbonate platform: an example from the Upper Jafnayn Formation of Jafnayn area in north-east Oman. Arabian Journal of Geosciences 17(12), 320, https://doi.org/10.1007/s12517-024-12094-0 (2024).
Choi, S. Y. et al. High-resolution annotated dataset of Girvanella boundstone microfacies from the Xiannüdong Formation, China. Figshare, https://doi.org/10.6084/m9.figshare.31033825 (2026).
Flügel, E. Microfacies of Carbonate Rocks: Analysis, Interpretation and Application. Springer (2010).
Adachi, N., Ezaki, Y. & Liu, J. Cambrian microbial reefs thriving in an oxygen-stratified early marine environment. Geology 32, 881–884 (2004).
Li, K., Song, J., Yan, H., Liu, S. & Yang, D. Carbonate microfacies classification model based on dual neural network: a case study on the fourth member of the upper Ediacaran Dengying Formation in the Moxi gas field, Central Sichuan Basin. Arabian Journal of Geosciences 15, 1773 (2022).
Acknowledgements
We thank D.C. Kim and J.S. Hong for providing the original thin section image dataset and supporting the annotation process. We also acknowledge the support of B.G. Lee and J.D. Do for their initial development of the tile generation scripts. Optical microscopy imaging was conducted at the Department of Geology, Kangwon National University. We are grateful to all colleagues who provided critical feedback during the manuscript preparation. This work was supported by the Korea Institute of Ocean Science and Technology (KIOST), project number PKB0011.
Author information
Authors and Affiliations
Contributions
S.Y.C. led the manuscript writing and coordinated the overall revision and conversion of the original codebase into a Python-based pipeline. He was also responsible for dataset integration, label validation, and repository documentation. D.C.K. and J.S.H. provided the raw thin section data and contributed to the tile-level annotation process. B.G.L. and J.D.D. developed the original MATLAB scripts for tile generation and class assignment. C.H.K. and C.W.L. supervised the study design, provided critical revisions, and guided the research direction. All authors reviewed and approved the final manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Choi, S., Kim, D., Hong, J. et al. High-resolution Annotated Dataset of Girvanella Boundstone Microfacies from the Xiannüdong Formation, China. Sci Data (2026). https://doi.org/10.1038/s41597-026-06958-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41597-026-06958-1
