Articles | Volume 17, issue 2
https://doi.org/10.5194/essd-17-595-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/essd-17-595-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
cigFacies: a massive-scale benchmark dataset of seismic facies and its application
School of Earth and Space Sciences, University of Science and Technology of China, Hefei, China
School of Earth and Space Sciences, University of Science and Technology of China, Hefei, China
Xiaoming Sun
Institute of Advanced Technology, University of Science and Technology of China, Hefei, China
Mingcai Hou
Institute of Sedimentary Geology, Chengdu University of Technology, Chengdu, China
State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Chengdu University of Technology, Chengdu, China
Hang Gao
School of Earth and Space Sciences, University of Science and Technology of China, Hefei, China
Guangyu Wang
School of Earth and Space Sciences, University of Science and Technology of China, Hefei, China
Hanlin Sheng
School of Earth and Space Sciences, University of Science and Technology of China, Hefei, China
Related authors
Zhixiang Guo, Xinming Wu, Yimin Dou, Hui Gao, and Guillaume Caumon
EGUsphere, https://doi.org/10.5194/egusphere-2026-1087, https://doi.org/10.5194/egusphere-2026-1087, 2026
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
We present a fast way to generate subsurface structure models from seismic surveys while honoring known horizons and faults. Instead of compressing the data into a hidden representation, our method works directly with the original model values and applies geological constraints during generation. Tests on synthetic and real surveys show more realistic structures and efficient prediction, producing a 512 by 512 model in 1.56 seconds on an NVIDIA H20 graphics processing unit.
Hui Gao, Xinming Wu, Jinyu Zhang, Xiaoming Sun, and Zhengfa Bi
Geosci. Model Dev., 16, 2495–2513, https://doi.org/10.5194/gmd-16-2495-2023, https://doi.org/10.5194/gmd-16-2495-2023, 2023
Short summary
Short summary
We propose a workflow to automatically generate synthetic seismic data and corresponding stratigraphic labels (e.g., clinoform facies, relative geologic time, and synchronous horizons) by geological and geophysical forward modeling. Trained with only synthetic datasets, our network works well to accurately and efficiently predict clinoform facies in 2D and 3D field seismic data. Such a workflow can be easily extended for other geological and geophysical scenarios in the future.
Zhixiang Guo, Xinming Wu, Yimin Dou, Hui Gao, and Guillaume Caumon
EGUsphere, https://doi.org/10.5194/egusphere-2026-1087, https://doi.org/10.5194/egusphere-2026-1087, 2026
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
We present a fast way to generate subsurface structure models from seismic surveys while honoring known horizons and faults. Instead of compressing the data into a hidden representation, our method works directly with the original model values and applies geological constraints during generation. Tests on synthetic and real surveys show more realistic structures and efficient prediction, producing a 512 by 512 model in 1.56 seconds on an NVIDIA H20 graphics processing unit.
Guangyu Wang, Xinming Wu, and Wen Zhang
Earth Syst. Sci. Data, 17, 3447–3471, https://doi.org/10.5194/essd-17-3447-2025, https://doi.org/10.5194/essd-17-3447-2025, 2025
Short summary
Short summary
Seismic paleochannel interpretation is vital for georesource exploration and paleoclimate research yet remains time-consuming. While deep learning offers automation potential, it is limited by the lack of labeled data. We present a workflow to simulate geologically reasonable 3D seismic volumes with diverse paleochannels, generating a large-scale labeled dataset. Field applications demonstrate its effectiveness. The dataset and codes are publicly available to support future research.
Hui Gao, Xinming Wu, Jinyu Zhang, Xiaoming Sun, and Zhengfa Bi
Geosci. Model Dev., 16, 2495–2513, https://doi.org/10.5194/gmd-16-2495-2023, https://doi.org/10.5194/gmd-16-2495-2023, 2023
Short summary
Short summary
We propose a workflow to automatically generate synthetic seismic data and corresponding stratigraphic labels (e.g., clinoform facies, relative geologic time, and synchronous horizons) by geological and geophysical forward modeling. Trained with only synthetic datasets, our network works well to accurately and efficiently predict clinoform facies in 2D and 3D field seismic data. Such a workflow can be easily extended for other geological and geophysical scenarios in the future.
Zhengfa Bi, Xinming Wu, Zhaoliang Li, Dekuan Chang, and Xueshan Yong
Geosci. Model Dev., 15, 6841–6861, https://doi.org/10.5194/gmd-15-6841-2022, https://doi.org/10.5194/gmd-15-6841-2022, 2022
Short summary
Short summary
We present an implicit modeling method based on deep learning to produce a geologically valid and structurally compatible model from unevenly sampled structural data. Trained with automatically generated synthetic data with realistic features, our network can efficiently model geological structures without the need to solve large systems of mathematical equations, opening new opportunities for further leveraging deep learning to improve modeling capacity in many Earth science applications.
Cited articles
Chen, L., Lu, Y.-C., Guo, T.-L., and Deng, L.-S.: Growth characteristics of Changhsingian (Late Permian) carbonate platform margin reef complexes in Yuanba gas Field, northeastern Sichuan Basin, China, Geol. J., 47, 524–536, 2012. a
Duan, Y., Zheng, X., Hu, L., and Sun, L.: Seismic facies analysis based on deep convolutional embedded clustering, Geophysics, 84, IM87–IM97, 2019. a
Dunham, M., Malcolm, A., and Welford, J.: Toward a semisupervised machine learning application to seismic facies classification, in: EAGE 2020 Annual Conference & Exhibition Online, 2020, 1–5, European Association of Geoscientists & Engineers, 2020. a
Fensel, D., Simsek, U., Angele, K., Huaman, E., Kärle, E., Panasiuk, O., Toma, I., Umbrich, J., and Wahler, A.: Knowledge graphs, Springer, https://doi.org/10.1007/978-3-030-37439-6, 2020. a
Gao, H., Wu, X., Sun, X., and Hou, M.: cigFacies datasets: the massive-scale benchmark dataset of seismic facies, Zenodo [data set], https://doi.org/10.5281/zenodo.10777460, 2024a. a, b, c
Gao, H., Wu, X., Sun, X., and Hou, M.: cigFacies codes: cigFaciesNet for data generation and model training, Zenodo [code], https://doi.org/10.5281/zenodo.13150879, 2024b. a, b
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A. C.: Improved training of wasserstein gans, ArXiv [preprint], 30, https://doi.org/10.48550/arXiv.1803.01541, 2017. a
He, K., Zhang, X., Ren, S., and Sun, J.: Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 26 June–1 July 2016, Las Vegas, USA, 770–778, https://doi.org/10.48550/arXiv.1512.03385, 2016. a
Hogan, A., Blomqvist, E., Cochez, M., d’Amato, C., Melo, G. D., 75 Gutierrez, C., Kirrane, S., Gayo, J. E. L., Neumaier, S., Polleres, A., Navigli, R., Ngomo, A.-C. N., Rashid, S. M., Rula, A., Schmelzeisen, L., Sequeda, J., Staab, S., and Zimmermann, A.: Knowledge graphs, ACM Computing Surveys (Csur), 54, 1–37, https://doi.org/10.1145/3447772, 2021. a
Hu, X., Xu, Y., Ma, X., Zhu, Y., Ma, C., Li, C., Lü, H., Wang, X., Zhou, C., and Wang, C.: Knowledge System, Ontology, and Knowledge Graph of the Deep-Time Digital Earth (DDE): Progress and Perspective, J. Earth Sci., 34, 1323–1327, 2023. a
Jia, C. Z., Zhao, W. Z., Zou, C. N., Feng, Z. Q., Yuan, X. J., Chi, Y. L., Tao, S. Z., and Xue, S. H.: Geological Theory and Exploration Technology for Lithostratigraphic Hydrocarbon Reservoirs, Pet. Explor. Develop., 34, 257–272, 2007. a
Karras, T., Aila, T., Laine, S., and Lehtinen, J.: Progressive Growing of GANs for Improved Quality, Stability, and Variation, ArXiv [preprint], abs/1710.10196, https://doi.org/10.48550/arXiv.1710.10196, 2017. a
Li, J., Wu, X., Ye, Y., Yang, C., Hu, Z., Sun, X., and Zhao, T.: Unsupervised contrastive learning for seismic facies characterization, Geophysics, 88, WA81–WA89, 2023. a
Liu, J., Dai, X., Gan, L., Liu, L., and Lu, W.: Supervised seismic facies analysis based on image segmentation, Geophysics, 83, O25–O30, 2018. a
Liu, M., Jervis, M., Li, W., and Nivlet, P.: Seismic facies classification using supervised convolutional neural networks and semisupervised generative adversarial networks, Geophysics, 85, O47–O58, 2020. a
Ma, C., Kale, A. S., Zhang, J., and Ma, X.: A knowledge graph and service for regional geologic time standards, Geosci. Front., 14, 101453, https://doi.org/10.1016/j.gsf.2022.101453, 2023. a
Mitchum Jr., R. M., Vail, P. R., and Sangree, J. B.: Seismic stratigraphy and global changes of sea level: Part 6. Stratigraphic interpretation of seismic reflection patterns in depositional sequences: Section 2. Application of seismic reflection configuration to stratigraphic interpretation, AAPG Bulletin, 26, 117–133, https://doi.org/10.1306/M26490C8, 1977a. a, b
Mitchum Jr., R. M., Vail, P. R., and Thompson III, S.: Seismic stratigraphy and global changes of sea level: Part 2. The depositional sequence as a basic unit for stratigraphic analysis: Section 2. Application of seismic reflection configuration to stratigraphic interpretation, AAPG Bulletin, 26, 53–62, https://doi.org/10.1306/M26490C4, 1977b. a, b
Paulheim, H.: Knowledge graph refinement: A survey of approaches and evaluation methods, Semantic web, 8, 489–508, 2017. a
Puzyrev, V. and Elders, C.: Unsupervised seismic facies classification using deep convolutional autoencoder, Geophysics, 87, IM125–IM132, 2022. a
Qi, J., Lin, T., Zhao, T., Li, F., and Marfurt, K.: Semisupervised multiattribute seismic facies analysis, Interpretation, 4, SB91–SB106, 2016. a
Qian, F., Yin, M., Liu, X.-Y., Wang, Y.-J., Lu, C., and Hu, G.-M.: Unsupervised seismic facies analysis via deep convolutional autoencoders, Geophysics, 83, A39–A43, 2018. a
Sangree, J. and Widmier, J.: Seismic stratigraphy and global changes of sea level: Part 9. Seismic interpretation of clastic depositional facies: Section 2. Application of seismic reflection configuration to stratigraphic interpretation, AAPG Bulletin, 62, 752–771, https://doi.org/10.1306/C1EA4E46-16C9-11D7-8645000102C1865D, 1977. a
Sheriff, R.: Inferring stratigraphy from seismic data, AAPG Bulletin, 60, 528–542, 1976. a
Tan, L., Liu, H., Tang, Y., Luo, B., Zhang, Y., Yang, Y., Liao, Y., Du, W., and Yang, X.: Characteristics and mechanism of Upper Permian reef reservoirs in the eastern Longgang Area, northeastern Sichuan Basin, China, Petroleum, 6, 130–137, 2020. a
Wrona, T., Pan, I., Gawthorpe, R. L., and Fossen, H.: Seismic facies analysis using machine learning, Geophysics, 83, O83–O95, 2018. a
Wu, X. and Fomel, S.: Least-squares horizons with local slopes and multigrid correlations, Geophysics, 83, IM29–IM40, 2018. a
Xu, G. and Haq, B. U.: Seismic facies analysis: Past, present and future, Earth-Sci. Rev., 224, 103876, https://doi.org/10.1016/j.earscirev.2021.103876, 2022. a, b, c
Xu, G., Xie, G., Long, K., and Song, X.: Sedimentary features and exploration targets of Middle Permian reservoirs in the SW Sichuan Basin, Natural Gas Industry B, 2, 415–420, 2015. a
Zhang, H., Chen, T., Liu, Y., Zhang, Y., and Liu, J.: Automatic seismic facies interpretation using supervised deep learning, Geophysics, 86, IM15–IM33, 2021. a
Zhang, L., Hou, M., Chen, A., Zhong, H., Ogg, J. G., and Zheng, D.: Construction of a fluvial facies knowledge graph and its application in sedimentary facies identification, Geosci. Front., 14, 101521, https://doi.org/10.1016/j.gsf.2022.101521, 2023. a
Zhao, T.: Seismic facies classification using different deep convolutional neural networks, in: SEG International Exposition and Annual Meeting, 14–19 October 2018, Anaheim, California, USA, SEG–2018, SEG, https://doi.org/10.1190/segam2018-2997085.1, 2018. a
Zhao, T., Li, F., and Marfurt, K. J.: Seismic attribute selection for unsupervised seismic facies analysis using user-guided data-adaptive weights, Geophysics, 83, O31–O44, 2018. a
Zhou, C., Wang, H., Wang, C., Hou, Z., Zheng, Z., Shen, S., Cheng, Q., Feng, Z., Wang, X., Lv, H., Fan, J., Hu, X., Hou, M., and Zhu, Y.: Geoscience knowledge graph in the big data era, Sci. China Earth Sci., 64, 1105–1114, 2021. a
Short summary
We propose three strategies for field seismic data curation, knowledge-guided synthesization, and generative adversarial network (GAN)-based generation to construct a massive-scale, feature-rich, and high-realism benchmark dataset of seismic facies and evaluate its effectiveness in training a deep-learning model for automatic seismic facies classification.
We propose three strategies for field seismic data curation, knowledge-guided synthesization,...
Altmetrics
Final-revised paper
Preprint