Abstract
To enhance the automation and spatial accuracy of geological outcrop information extraction, this study proposes a three-dimensional (3D) modeling method oriented toward multi-class semantic boundary representation. High-resolution outcrop images at the centimeter scale were acquired using UAV-based oblique photogrammetry. A modified U-Net model, integrating a self-attention mechanism and a boundary-weighted IoU loss, was developed to achieve fine-grained semantic segmentation of four explicit classes: microbial reef, grain beach dolomite, micritic dolomite, and background. To address the occlusion and label conflict issues inherent in multi-view imaging, a spatially-constrained projection strategy based on Z-buffer depth testing and weighted majority voting was proposed, accurately mapping 2D semantic labels onto 3D photorealistic model surfaces. Following high-precision 3D reconstruction using ContextCapture, a multi-scale semantic visualization platform was ultimately constructed based on Cesium. Experimental results demonstrate that the proposed method increases the boundary-aware semantic segmentation performance (Boundary F1-Score) to 78.64% and limits the mean projection error to within 3.2 cm, significantly outperforming existing mainstream approaches. This research provides an effective pathway for the automated recognition of complex geological structures and the development of digital twin models.
Similar content being viewed by others
Data availability
The datasets generated and analyzed during the current study are not publicly available due to strict confidentiality provisions associated with the high-resolution geographic surveying data of the specific study area, as well as the regulations of the supporting research grant from the National Natural Science Foundation of China (Grant No. 42402158). However, subsets of the data may be made available by the first author upon reasonable academic request and subject to the signing of a non-disclosure agreement. Interested researchers may contact the authors via email (153,033,338@qq.com) for further details.
References
Howell, J.A., Martinius, A.W., Good, T.R., 2014. The application of outcrop analogues in geological modelling: a review, present status and future outlook..
Villarreal, C. A. et al. Workflow for capturing information and characterizing difficult-to-access geological outcrops using unmanned aerial vehicle-based digital photogrammetric data. J. Ind. Inf. Integr. 26, 100292 (2022).
Fleming, Z. Using virtual outcrop models and Google Earth to teach structural geology concepts. J. Struct. Geol. 156, 104537 (2022).
Seers, T. D. et al. Virtual outcrop geology comes of age: The application of consumer-grade virtual reality hardware and software to digital outcrop data analysis. Comput. Geosci. 159, 105006 (2022).
Bistacchi, A., Mittempergher, S., Martinelli, M., 2022. Digital outcrop model reconstruction and interpretation. 3D digital geological models: from terrestrial outcrops to planetary surfaces, 11–32.
Dong, Z. et al. Synergistic application of digital outcrop characterization techniques and deep learning algorithms in geological exploration. Sci. Rep. 14(1), 22948 (2024).
Corrêa, S. N. et al. 3D geological modeling and reservoir production numerical simulation of multiple scenarios in fractured-karstified carbonate reservoirs using high-resolution outcrop characterization. Geoenergy Sci. Eng. 251, 213866 (2025).
Almukhalfi, H., Noor, A. & Noor, T. H. Traffic management approaches using machine learning and deep learning techniques: A survey. Eng. Appl. Artif. Intell. 133, 108147 (2024).
Shen, J. et al. An anchor-free lightweight deep convolutional network for vehicle detection in aerial images. IEEE Trans. Intell. Transp. Syst. 23(12), 24330–24342 (2022).
Shen, J. et al. Finger vein recognition algorithm based on lightweight deep convolutional neural network. IEEE Trans. Instrum. Meas. 71, 1–13 (2022).
Shen, J., Liu, N., Sun, H., Li, D. & Zhang, Y. An instrument indication acquisition algorithm based on lightweight deep convolutional neural network and hybrid attention fine-grained features. IEEE Trans. Instrum. Meas. 73, 1–16 (2024).
Shen, J., Liu, N., Sun, H., Wu, S., Liang, Z., Han, L., Zhang, Y., & Li, D. (2025). Lightweight semantic feature extraction model with direction awareness for aerial traffic object detection. IEEE Transac. Intell. Transp. Syst..
Zhang, X. et al. FSCMF: A dual-branch frequency-spatial joint perception cross-modality network for visible and infrared image fusion. Neurocomputing 641, 130376 (2025).
Zhang, X., Dong, K., Cheng, D., Hua, Z. & Li, J. STWANet: Spatio-temporal wavelet attention aggregation network for remote sensing change detection. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. https://doi.org/10.1109/jstars.2025.3551093 (2025).
Zhang, K. et al. Adversarial spatio-temporal learning for video deblurring. IEEE Trans. Image Process. 28(1), 291–301 (2018).
Sun, P., Zheng, Y., Xu, W., Li, J. & Yang, J. Completing missing entities: Exploring consistency reasoning for remote sensing object detection. IEEE Trans. Image Process. 35, 569–584 (2026).
Sun, T. et al. Advances and challenges in machine learning for RNA-small molecule interaction modeling: Review. J. Chem. Theory Comput. 21(18), 8615–8633 (2025).
Wu, C. et al. UNet-like remote sensing change detection: A review of current models and research directions. IEEE Geosci. Remote Sens. Mag. https://doi.org/10.1109/mgrs.2024.3412770 (2024).
Yuan, Y. & Cheng, Y. Medical image segmentation with UNet-based multi-scale context fusion. Sci. Rep. 14(1), 15687 (2024).
Jonnala, N. S. et al. DSIA U-Net: Deep shallow interaction with attention mechanism UNet for remote sensing satellite images. Sci. Rep. 15(1), 549 (2025).
He, C. et al. Mapping distribution of fractures and minerals in rock samples using Res-VGG-UNet and threshold segmentation methods. Comput. Geotech. 175, 106675 (2024).
Hou, G., Qin, P., Wang, S., et al., 2024. Processing and implementation of tilted photography 3D model tiles based on cesium. Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), SPIE 13181, 1040–1045.
Qin, J. et al. Design and application of natural resources realistic 3D visualization system based on UAV technology. J. Phys. Conf. Ser. 3055(1), 012041 (2025).
Miao, M. et al. The Lower Cambrian Xiaoerbulake Formation in the Tarim Basin as a potential carbonate source rock. Energy Geosci. 5(2), 100238 (2024).
Ji, T. et al. Sedimentary characteristics, lithofacies, and paleogeography of the Middle–Lower Cambrian in the Tarim Basin, NW China. Can. J. Earth Sci. 61(5), 560–585 (2024).
Yao, Y. et al. Strike‐slip fault architecture and its control on fractured carbonate reservoirs: Insight from outcrops in the North‐western Tarim Basin, NW China. Acta Geol. Sin. (Engl. Ed.) 99(2), 568–581 (2025).
Geng, F. et al. Internal structure characteristics and formation mechanism of reverse fault in the carbonate rock, a case study of outcrops in Xike’er area, Tarim Basin, Northwest China. Front. Earth Sci. 9, 793016 (2021).
Zhou, H. et al. Characteristics and genesis of dolomite in the lower Cambrian Xiaoerbulake formation of the western Tarim Basin, China. Front. Earth Sci. 10, 1075941 (2023).
Acknowledgements
Thank you for the financial support provided by the National Natural Science Foundation of China (Grant No. 42402158)
Author information
Authors and Affiliations
Contributions
Zhicheng Dong: Conceptualization, Methodology, Writing – Original Draft, Validation, Investigation. Hongjun Zhang: Data curation, Writing – Review & Editing, Visualization. Yingwei Qu: Software, Model development, Data analysis. Siwen Yang: Validation, Supervision, Writing – Review & Editing. Pan Tang: Funding acquisition, Project administration, Resources. Haitong Yang：Research Administrator.
Corresponding author
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.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, 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 you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. 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-nc-nd/4.0/.
About this article
Cite this article
Dong, Z., Zhang, H., Qu, Y. et al. Three-dimensional spatial representation method for semantic boundaries in digital outcrop models. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45820-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45820-7
