Articles | Volume 16, issue 9
https://doi.org/10.5194/gmd-16-2495-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-16-2495-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Development and technical paper
| 
09 May 2023
Development and technical paper |
| 09 May 2023
| 09 May 2023
ClinoformNet-1.0: stratigraphic forward modeling and deep learning for seismic clinoform delineation
School of Earth and Space Sciences, University of Science and Technology of China, Hefei 230026, China
School of Earth and Space Sciences, University of Science and Technology of China, Hefei 230026, China
Jinyu Zhang
Bureau of Economic Geology, Jackson School of Geosciences, The University of Texas at Austin, Austin, Texas 78758, USA
Xiaoming Sun
School of Earth and Space Sciences, University of Science and Technology of China, Hefei 230026, China
Zhengfa Bi
School of Earth and Space Sciences, University of Science and Technology of China, Hefei 230026, 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, Xiaoming Sun, Mingcai Hou, Hang Gao, Guangyu Wang, and Hanlin Sheng
Earth Syst. Sci. Data, 17, 595–609, https://doi.org/10.5194/essd-17-595-2025, https://doi.org/10.5194/essd-17-595-2025, 2025
Short summary
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.
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, Xiaoming Sun, Mingcai Hou, Hang Gao, Guangyu Wang, and Hanlin Sheng
Earth Syst. Sci. Data, 17, 595–609, https://doi.org/10.5194/essd-17-595-2025, https://doi.org/10.5194/essd-17-595-2025, 2025
Short summary
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.
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
Adams, E. W. and Schlager, W.: Basic types of submarine slope curvature, J. Sediment. Res., 70, 814–828, https://doi.org/10.1306/2DC4093A-0E47-11D7-8643000102C1865D, 2000. a
Araya-Polo, M., Jennings, J., Adler, A., and Dahlke, T.: Deep-learning tomography, The Leading Edge, 37, 58–66, 2018. a
Asquith, D.: Depositional topography and major marine environments, Late Cretaceous, Wyoming, AAPG Bull., 54, 1184–1224, 1970. a
Athy, L. F.: Density, porosity, and compaction of sedimentary rocks, AAPG Bull., 14, 1–24, 1930. a
Bates, C. C.: Rational theory of delta formation, AAPG Bull., 37, 2119–2162, 1953. a
Bergen, K., Johnson, P., De Hoop, M., and Beroza, G.: Machine learning for data-driven discovery in solid earth geoscience, Science, 363, eaau0323, https://doi.org/10.1126/science.aau0323, 2019. a
Biot, M. A.: General theory of three-dimensional consolidation, J. Appl. Phys., 12, 155–164, 1941. a
Bird, K. J. and Molenaar, C. M.: The North Slope Foreland Basin, Alaska, American Association of Petroleum Geologists, 363–393, https://doi.org/10.1306/M55563C14, 1992. a
Carcione, J. M., Helle, H. B., and Hydro, N.: Rock physics of geopressure and prediction of abnormal pore fluid pressures using seismic data, CSEG Recorder, 27, 8–32, 2002. a
Cummings, D. I. and Arnott, R. W. C.: Growth-faulted shelf-margin deltas: a new (but old) play type, offshore Nova Scotia, Bull. Can. Petrol. Geol., 53, 211–236, 2005. a
Di, H., Shafiq, M., and AlRegib, G.: Patch-level MLP classification for improved fault detection, in: SEG Technical Program Expanded Abstracts 2018, Society of Exploration Geophysicists, 2211–2215, https://doi.org/10.1190/segam2018-2996921.1, 2018. a
Di, H., Li, Z., Maniar, H., and Abubakar, A.: Seismic stratigraphy interpretation by deep convolutional neural networks: A semisupervised workflow, Geophysics, 85, WA77–WA86, 2020. a
Ding, X., Salles, T., Flament, N., and Rey, P.: Quantitative stratigraphic analysis in a source-to-sink numerical framework, Geosci. Model Dev., 12, 2571–2585, https://doi.org/10.5194/gmd-12-2571-2019, 2019. a, b, c, d
Dixit, A. and Mandal, A.: Detection of gas chimney and its linkage with deep-seated reservoir in poseidon, NW shelf, Australia from 3D seismic data using multi-attribute analysis and artificial neural network approach, J. Nat. Gas Sci. Eng., 83, 103586, https://doi.org/10.1016/j.jngse.2020.103586, 2020. a
Fehmers, G. C. and Höcker, C. F.: Fast structural interpretation with structure-oriented filtering, Geophysics, 68, 1286–1293, 2003. a
Gao, H., Wu, X., Zhang, J., Sun, X., and Bi, Z.: huigcig/ClinoformNet: ClinoformNet-1.0, Zenodo [code], https://doi.org/10.5281/zenodo.7123934, 2022a. a
Gao, H., Wu, X., Zhang, J., Sun, X., and Bi, Z.: The synthetic and field siesmic datasets for “ClinoformNet-1.0: stratigraphic forward modeling and deep learning for seismic clinoform delineation”, Zenodo [data set], https://doi.org/10.5281/zenodo.7122471, 2022b. a
Goldberg, I. and Gurevich, B.: A semi-empirical velocity-porosity-clay model for petrophysical interpretation of P- and S-velocities [Link], Geophys. Prospect., 46, 271–285, 2008. a
Guo, J., Li, Y., Jessell, M. W., Giraud, J., Li, C., Wu, L., Li, F., and Liu, S.: 3D geological structure inversion from Noddy-generated magnetic data using deep learning methods, Comput. Geosci., 149, 104701, https://doi.org/10.1016/j.cageo.2021.104701, 2021. a
Hale, D.: Structure-oriented smoothing and semblance, CWP report, 635, 2009. a
Harris, A. D., Covault, J. A., Madof, A. S., Sun, T., Sylvester, Z., and Granjeon, D.: Three-dimensional numerical modeling of eustatic control on continental-margin sand distribution, J. Sediment. Res., 86, 1434–1443, 2016. a
Hawie, N., Barrois, A., Marfisi, E., Murat, B., Hall, J., El-Wazir, Z., Al-Madani, N., and Aillud, G.: Forward stratigraphic modelling, deterministic approach to improve carbonate heterogeneity prediction; Lower Cretaceous, Abu Dhabi, in: Abu Dhabi International Petroleum Exhibition and Conference, Abu Dhabi, UAE, 9–12 November 2015, OnePetro, https://doi.org/10.2118/177519-MS, 2015. a, b, c
Holgate, N. E., Jackson, C. A.-L., Hampson, G. J., and Dreyer, T.: Sedimentology and sequence stratigraphy of the middle–upper jurassic krossfjord and fensfjord formations, Troll Field, northern North Sea, Petrol. Geosci., 19, 237–258, https://doi.org/10.1144/petgeo2012-039, 2013. a
Holgate, N. E., Hampson, G. J., Jackson, C. A.-L., and Petersen, S. A.: Constraining uncertainty in interpretation of seismically imaged clinoforms in deltaic reservoirs, Troll field, Norwegian North Sea: Insights from forward seismic models of outcrop analogsCharacterization of Seismically Imaged Clinoforms Using Forward Seismic Models of Outcrop Analogs, AAPG Bull., 98, 2629–2663, 2014. a
Houseknecht, D. W., Bird, K. J., and Schenk, C. J.: Seismic analysis of clinoform depositional sequences and shelf-margin trajectories in Lower Cretaceous (Albian) strata, Alaska North Slope, Basin Res., 21, 644–654, 2009. a
Huang, L., Dong, X., and Clee, T. E.: A scalable deep learning platform for identifying geologic features from seismic attributes, The Leading Edge, 36, 249–256, 2017. a
Jessell, M., Guo, J., Li, Y., Lindsay, M., Scalzo, R., Giraud, J., Pirot, G., Cripps, E., and Ogarko, V.: Into the Noddyverse: a massive data store of 3D geological models for machine learning and inversion applications, Earth Syst. Sci. Data, 14, 381–392, https://doi.org/10.5194/essd-14-381-2022, 2022. a
Karpatne, A., Ebert-Uphoff, I., Ravela, S., Babaie, H. A., and Kumar, V.: Machine learning for the geosciences: Challenges and opportunities, IEEE T. Knowl. Data En., 31, 1544–1554, 2018. a
Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization, arXiv [preprint], https://doi.org/10.48550/arXiv.1412.6980, 2014. a
Lee, M. W.: Proposed moduli of dry rock and their application to predicting elastic velocities of sandstones, US Department of the Interior, US Geological Survey, https://doi.org/10.3133/sir20055119, 2005. a, b
Liu, Z.: Seismic geomorphology of continental margin evolution in the late Cretaceous to Neogene of the Browse Basin, northwest Australia, Colorado School of Mines, 2018. a
Lorensen, W. E. and Cline, H. E.: Marching cubes: A high resolution 3D surface construction algorithm, ACM Siggraph Computer Graphics, 21, 163–169, 1987. a
Lowell, J. and Paton, G.: Application of deep learning for seismic horizon interpretation, in: 2018 SEG International Exposition and Annual Meeting, Anaheim, California, USA, 14–19 October 2018, OnePetro, https://doi.org/10.1190/segam2018-2998176.1, 2018. a
Martin, J., Paola, C., Abreu, V., Neal, J., and Sheets, B.: Sequence stratigraphy of experimental strata under known conditions of differential subsidence and variable base level, AAPG Bull., 93, 503–533, 2009. a
Muto, T. and Steel, R. J.: Principles of regression and transgression; the nature of the interplay between accommodation and sediment supply, J. Sediment. Res., 67, 994–1000, 1997. a
Nanda, N. C.: Seismic data interpretation and evaluation for hydrocarbon exploration and production, Springer, https://doi.org/10.1007/978-3-319-26491-2, 2021. a
Neal, J. E., Abreu, V., Bohacs, K. M., Feldman, H. R., and Pederson, K. H.: Accommodation succession (
Patruno, S., Reid, W., Jackson, C. A., and Davies, C.: New insights into the unexploited reservoir potential of the Mid North Sea High (UKCS quadrants 35–38 and 41–43): a newly described intra-Zechstein sulphate–carbonate platform complex, in: Geological Society, London, Petroleum Geology Conference Series, vol. 8, 87–124, Geological Society of London, https://doi.org/10.1144/PGC8.9, 2018. a
Pirmez, C., Pratson, L. F., and Steckler, M. S.: Clinoform development by advection-diffusion of suspended sediment: Modeling and comparison to natural systems, J. Geophys. Res.-Sol. Ea., 103, 24141–24157, 1998. a
Puzyrev, V., Salles, T., Surma, G., and Elders, C.: Geophysical model generation with generative adversarial networks, Geoscience Letters, 9, 1–9, 2022. a
Schlager, W.: Accommodation and supply – a dual control on stratigraphic sequences, Sediment. Geol., 86, 111–136, 1993. a
Shi, Y., Wu, X., and Fomel, S.: SaltSeg: Automatic 3D salt segmentation using a deep convolutional neural network, Interpretation, 7, SE113–SE122, 2019. a
Steel, R. and Olsen, T.: Clinoforms, Clinoform Trajectories and Deepwater Sands, in: Sequence Stratigraphic Models for Exploration and Production: Evolving Methodology, Emerging Models and Application Histories, SEPM Society for Sedimentary Geology, ISBN 978-0-9836096-8-1, https://doi.org/10.5724/gcs.02.22, 2002. a, b
Sydow, J. C., Finneran, J., and Bowman, A. P.: Stacked shelf-edge delta reservoirs of the Columbus Basin, Trinidad, West Indies, SEPM Society for Sedimentary Geology, https://doi.org/10.5724/gcs.03.23.0441, 2013. a
Sylvester, Z., Cantelli, A., and Pirmez, C.: Stratigraphic evolution of intraslope minibasins: Insights from surface-based model, AAPG Bull., 99, 1099–1129, 2015. a
Van Vliet, L. J. and Verbeek, P. W.: Estimators for orientation and anisotropy in digitized images, in: ASCI Imaging Workshop, Venray, NL, 25–27 October, 1995. a
Wu, H. and Zhang, B.: A deep convolutional encoder-decoder neural network in assisting seismic horizon tracking, arXiv [preprint], https://doi.org/10.48550/arXiv.1804.06814, 2018. a
Wu, X., Liang, L., Shi, Y., and Fomel, S.: FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation, Geophysics, 84, IM35–IM45, 2019. a
Wu, X., Geng, Z., Shi, Y., Pham, N., Fomel, S., and Caumon, G.: Building realistic structure models to train convolutional neural networks for seismic structural interpretationBuilding realistic structure models, Geophysics, 85, WA27–WA39, 2020. a
Wu, X., Ma, J., Si, X., Bi, Z., Yang, J., Gao, H., Xie, D., Guo, Z., and Zhang, J.: Sensing prior constraints in deep neural networks for
solving exploration geophysical problems, P. Natl. Acad. Sci., in press, 2023. a
Zhao, T. and Mukhopadhyay, P.: A fault detection workflow using deep learning and image processing, in: 2018 SEG international exposition and annual meeting, Anaheim, California, USA, 14–19 October 2018, OnePetro, https://doi.org/10.1190/segam2018-2997005.1, 2018. a
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.
We propose a workflow to automatically generate synthetic seismic data and corresponding...
