一种融合半监督深度学习与多点地质统计的三维地质建模及不确定性评估框架

doi:10.3799/dqkx.2026.093

一种融合半监督深度学习与多点地质统计的三维地质建模及不确定性评估框架

doi: 10.3799/dqkx.2026.093

周顺平¹,
袁创¹,
储德平²,
方芳¹,
潘声勇³,
刘兆鑫⁴,
李红⁵,
万波^1, ,

1. 中国地质大学(武汉)计算机学院, 湖北武汉 430078;
2. 中国地质大学(武汉)地理与信息工程学院, 湖北武汉 430078;
3. 武汉中地数码科技有限公司, 湖北武汉 430074;
4. 四川省综合地质调查研究所, 四川成都 610081;
5. 四川省第五地质大队, 四川成都 610081

基金项目:

国家自然科学基金项目（42571535)

详细信息

作者简介:
周顺平（1967-），教授，研究方向为三维地质建模，ORCID:0000-0002-2697-3383，E-mail:zhoushunping@cug.edu.cn，TEL:13507181840

通讯作者:
万波(1975-)，教授，研究方向为三维地质建模，ORCID:0000-0003-2387-5419.E-mail:wanbo@cug.edu.cn，TEL:13971097150

中图分类号: P618.51
计量
- 文章访问数: 41
- HTML全文浏览量: 0
- PDF下载量: 2
- 被引次数: 0
出版历程
- 收稿日期: 2025-12-22
- 网络出版日期: 2026-05-13

A three-dimensional geological modeling framework integrating semi-supervised deep learning and multi-point geological statistics and uncertainty Analysis

1. School of Computer Science, China University of Geosciences, Wuhan 430078, China;
2. School of Geography and Information Engineering, China University of Geosciences, Wuhan 430078, China;
3. Wuhan Zondy Cyber Technology Co., LTD, Wuhan 430074, China;
4. Sichuan Institute of Comprehensive Geological Survey, Chengdu 610081, China;
5. The Fifth Geological Team of Sichuan Province, Chengdu 610081, China

摘要

摘要: 针对钻孔数据稀疏、类别不均衡及复杂地质结构导致的三维地质建模精度低、空间连续性差和不确定性高的问题，提出一种融合半监督深度学习与多点地质统计的分阶段联合建模方法。首先，构建基于邻域空间上下文特征的半监督空间感知注意力网络（Spatial-Aware Attention Net，SAAN），利用伪标签机制提升地层分类精度并生成初始模型；随后，设计多点地质统计随机邻域搜索（Random Neighborhood Search，RNS）策略对低置信度与地质语义冲突区域进行迭代优化；最后，提出协同一致性熵量化两阶段预测一致性及联合不确定性。以成都平原地区钻孔数据为例，所提方法在地层空间分布再现、边界刻画及结构连续性方面优于反距离加权（IDW）、支持向量机（SVM）、随机森林（RF）、多层感知机（MLP）及Kolmogorov-Arnold网络（KAN）等基线方法。此外协同一致性熵能有效识别结构性不确定性，避免高熵值但预测一致的误判。所提出的分阶段联合建模框架能在有限、不均衡钻孔数据条件下实现高精度、结构合理且不确定性可控的三维地质模型重建，为复杂地质环境下的地下结构刻画与工程应用提供有效技术支撑。
- 三维地质建模 /
- 深度学习 /
- 半监督学习 /
- 多点地质统计 /
- 不确定性评估
Abstract: To address the problems of low accuracy, poor spatial continuity and high uncertainty in 3D geological modeling caused by sparse borehole data, unbalanced categories and complex geological structures, a phased joint modeling method integrating semi-supervised deep learning and multi-point geological statistics is proposed. Firstly, a semi-supervised spatial-aware Attention Net (SAAN) based on neighborhood spatial context features is constructed, and the pseudo-label mechanism is utilized to improve the classification accuracy of strata and generate the initial model; Subsequently, the multi-point geological statistics Random Neighborhood Search (RNS) strategy is combined to iteratively optimize the areas with low confidence and geological semantic conflicts; Finally, the collaborative consistency entropy is proposed to quantify the two-stage prediction consistency and joint uncertainty. Taking the borehole data in the Chengdu Plain area as an example, the proposed method outperforms baseline methods such as Inverse Distance Weighting (IDW), Support Vector Machine (SVM), Random Forest (RF), Multilayer Perceptron (MLP), and Kolmogorov-Arnold Networks (KAN) in terms of reproduction of stratum spatial distribution, boundary characterization, and structural continuity. In addition, the collaborative consistency entropy can effectively identify structural uncertainties and avoid misjudgments of high entropy values but consistent predictions. The proposed phased joint modeling framework can achieve high-precision, structurally reasonable and uncertain controllable three-dimensional geological model reconstruction under the conditions of limited and unbalanced borehole data, providing effective technical support for the characterization and engineering applicationof underground structures in complex geological environments.
- three-dimensional geological modeling /
- deep learning /
- semi-supervised learning /
- multi-point geological statistics /
- uncertainty assessment

HTML全文

参考文献(45)

Bai, T., Tahmasebi, P., 2020. Hybrid Geological Modeling: Combining Machine Learning and Multiple-Point Statistics. Computers & Geosciences, 142: 104519. https://doi.org/10.1016/j.cageo.2020.104519
Boyd, D. L., Walton, G., Trainor-Guitton, W., 2019. Quantifying Spatial Uncertainty in Rock through Geostatistical Integration of Borehole Data and a Geologist’s Cross-Section.Engineering Geology, 260: 105246. https://doi.org/10.1016/j.enggeo.2019.105246
Breiman, L., 2001. Random Forests. Machine Learning, 45(1): 5-32. https://doi.org/10.1023/A:1010933404324
Chu, D. P., Wan, B., Liu, Y. Y., et al., 2025. An Integrated Machine Learning Framework using Borehole Descriptions for 3D Lithological Modeling. Engineering Geology, 351: 108050. https://doi.org/10.1016/j.enggeo.2025.108050
Chu, D. P., Fu, J. M., Wan, B., et al., 2024. A Multi-View Ensemble Machine Learning Approach for 3D Modeling using Geological and Geophysical Data. International Journal of Geographical Information Science, 38(12): 2599-2626. https://doi.org/10.1080/13658816.2024.2394228
Comunian, A., Renard, P., Straubhaar, J., 2012. 3D Multiple-Point Statistics Simulation Using 2D Training Images. Computers & Geosciences, 40: 49-65. https://doi.org/10.1016/j.cageo.2011.07.009
Derpanis, K. G., 2008. The Bhattacharyya Measure. Mendeley Computer, 1(4): 1990-1992.
Fu, J. M., Hu, M. S., Fang, F., et al., 2024. Complex Orebody 3D Modeling using Radial Basis Function Surface incorporating Stacking Integration Strategy. Earth Science, 49(3): 1165-1176 (in Chinese with English abstract).
Guo, J. T., Liu, Y. H., Han, Y. F., et al., 2019. Implicit 3D Geological Modeling Method for Borehole Data Based on Machine Learning. Journal of Northeastern University (Natural Science), 40(09): 1337-1342 (in Chinese with English abstract).
Guo, J. T., Wang, Z. X., Li, C. L., et al., 2022. Multiple-Point Geostatistics-Based Three-Dimensional Automatic Geological Modeling and Uncertainty Analysis for Borehole Data. Natural Resources Research, 31(5): 2347-2367. https://doi.org/10.1007/s11053-022-10071-6
Guo, J. T., Xu, X. C., Wang, L. Y., et al., 2024. GeoPDNN 1.0: A Semi-Supervised Deep Learning Neural Network Using Pseudo-Labels for Three-Dimensional Shallow Strata Modelling and Uncertainty Analysis in Urban Areas from Borehole Data. Geoscientific Model Development, 17(3): 957-973. https://doi.org/10.5194/gmd-17-957-2024
Hang, Z. Q., Xue, T., Chen, J. P., et al., 2025. A 3D Geological Modeling Method Using the Transformer Model: A Solution for Sparse Borehole Data. Minerals, 15(3): 301. https://doi.org/10.3390/min15030301
Hou, W. S., Liu, H. G., Zheng, T. C., et al., 2022. Extended GOSIM: MPS-Driven Simulation of 3D Geological Structure Using 2D Cross-Sections. Earth and Space Science, 9(6): e2021EA001801. https://doi.org/10.1029/2021EA001801
Hou, W. S., Liu, H. G., Zheng, T. C., et al., 2021. Hierarchical MPS-Based Three-Dimensional Geological Structure Reconstruction with Two-Dimensional Image(s). Journal of Earth Science, 32(2): 455-467. https://doi.org/10.1007/s12583-021-1443-x
Jia, R., Lv, Y., Wang, G., et al., 2021. A Stacking Methodology of Machine Learning for 3D Geological Modeling with Geological-Geophysical Datasets, Laochang Sn Camp, Gejiu (China). Computers & Geosciences, 151: 104754. https://doi.org/10.1016/j.cageo.2021.104754
Li, H., Wan, B., Chu, D. P., et al., 2024. Integrated Framework for Geological Modeling: Integration of Data, Knowledge, and Methods. Bulletin of Engineering Geology and the Environment, 83(8): 303. https://doi.org/10.1007/s10064-024-03794-8
Li, H., Wan, B., Chu, D. P., et al., 2023. Progressive Geological Modeling and Uncertainty Analysis Using Machine Learning. ISPRS International Journal of Geo-Information, 12(3): 97. https://doi.org/10.3390/ijgi12030097
Liu, Y. M., Durlofsky, L. J., 2020. 3D CNN-PCA: A Deep-Learning-Based Parameterization for Complex Geomodels. Computers & Geosciences, 148: 104676. https://doi.org/10.1016/j.cageo.2020.104676
Liu, Z. M., Wang, Y. X., Vaidya, S., et al., 2024. Kan: Kolmogorov-Arnold Networks. arXiv Preprint arXiv, 2404.19756. https://doi.org/10.48550/arXiv.2404.19756
Lubold, S., Taylor, C. N., 2022. Formal Definitions of Conservative Probability Distribution Functions (PDFs). Information Fusion, 88: 175-183. https://doi.org/10.1016/j.inffus.2022.07.014
Mariethoz, G., Caers, J., 2014. Multiple-Point Geostatistics: Modeling with Training Images. John Wiley & Sons, Ltd.
Mariethoz, G., Renard, P., Straubhaar, J., 2010. The Direct Sampling Method to Perform Multiple-Point Geostatistical Simulations. Water Resources Research, 46(11): e2008WR007621. https://doi.org/10.1029/2008WR007621
Meerschman, E., Pirot, G., Mariethoz, G., et al., 2013. A Practical Guide to Performing Multiple-Point Statistical Simulations with the Direct Sampling Algorithm. Computers & Geosciences, 52: 307-324. https://doi.org/10.1016/j.cageo.2012.09.019
Smirnoff, A., Boisvert, E., Paradis, S. J., 2006. Support Vector Machine for 3D Modelling from Sparse Geological Information of Various Origins. Computers & Geosciences, 34(2): 127-143. https://doi.org/10.1016/j.cageo.2006.12.008
Taud, H., Mas, J. F., 2017. Multilayer Perceptron (MLP). Geomatic Approaches for Modeling Land Change Scenarios, 451-455.
Tahmasebi, P., Hezarkhani, A., Sahimi, M., 2012. Multiple-Point Geostatistical Modeling Based on the Cross-Correlation Functions. Computational Geosciences, 16(3): 779-797. https://doi.org/10.1007/s10596-012-9287-1
Tang, J. F., Tang, M. M., Lu, S. F., et al., 2024. Three-Dimensional Modeling of Estuary Reservoir Based on Coupling Sedimentary Dynamics Simulation and Multipoint Geostatistics Method. Earth Science, 49(1): 174-188 (in Chinese with English abstract).
Tang, B. Y., Wu, C. L., Li, X. C., et al., 2015. A Fast Progressive 3D Geological Modeling Method Based on Borehole Data. Rock and Soil Mechanics, 36(12): 3633-3638 (in Chinese with English abstract).
Tian, J., Xia, Y. B., Zhang, J. H., et al., 2025. Urban Underground Space Geological Suitability-A Theoretical Framework, Index System, and Evaluation Method. Applied Sciences-Basel, 15(8): 4326. https://doi.org/10.3390/app15084326
Wang, B., Lei, C. Y., Liu, Z. X., et al., 2021. A Geological 3D Modeling Method of Comprehensive Geological Section for Chengdu. Sedimentary Geology and Tethyan Geology, 41(1): 112-120 (in Chinese with English abstract).
Yang, F. F., Zuo, R. G., Kreuzer, O. P., 2026. Interpretable Regional-Scale Geological Mapping Using a Contrastive Graph Attention Network for Multimodal Data Fusion and Recognition of Controlling Factors. Engineering Geology, 361: 108508. https://doi.org/10.1016/j.enggeo.2025.108508
Yang, S. H., Hou, W. S., Chen, Y. H., et al., 2025. Three-Dimensional Reconstruction of Geologic Structures Based on Adaptive Fully-Connected Deep Neural Network and Multi-Point Statistics Method. Earth Science Frontiers, 1-25 (in Chinese with English abstract).
Zhang, H., Gui, L., Wang, T. F., et al., 2024. Prediction of Quaternary Cover Thickness and 3D Geological Modeling Based on BP Neural Network. Earth Science, 49(2): 550-559 (in Chinese with English abstract).
Zhou, Y. Z., Zuo, R. G., Liu, G., et al., 2021. The Great-Leap-Forward Development of Mathematical Geoscience During 2010-2019: Big Data and Artificial Intelligence Algorithm Are Changing Mathematical Geoscience. Bulletin of Mineralogy, Petrology and Geochemistry, 40(3): 556-573+777(in Chinese with English abstract).
Zuo, R. G., Peng, Y., Li, T., et al., 2020. Challenges of Geological Prospecting Big Data Mining and IntegrationUsing Deep Learning Algorithms. Earth Science, 46(1): 350-358 (in Chinese with English abstract).
附中文参考文献
扶金铭, 胡茂胜, 方芳, 等, 2024.Stacking集成策略下的径向基函数曲面复杂矿体三维建模方法.地球科学, 49(3):1165-1176.
郭甲腾, 刘寅贺, 韩英夫, 等, 2019.基于机器学习的钻孔数据隐式三维地质建模方法.东北大学学报(自然科学版), 40(09):1337-1342.
唐丙寅, 吴冲龙, 李新川, 等, 2015.一种基于钻孔地质数据的快速递进三维地质建模方法.岩土力学, 36(12):3633-3638.
唐佳凡, 唐明明, 卢双舫, 等, 2024.基于耦合沉积动力学模拟与多点地质统计学方法的河口湾储层三维建模.地球科学, 49(1):174-188.
王波, 雷传扬, 刘兆鑫, 等, 2021.三维地质建模过程中综合地质剖面构建方法研究.沉积与特提斯地质, 41(01):112-120.
杨松桦, 侯卫生, 陈勇华, 等, 2025.基于自适应全连接深度神经网络和多点地质统计学方法的地质结构三维重建研究.地学前缘, 1-25.
左仁广, 彭勇, 李童, 等, 2020.基于深度学习的地质找矿大数据挖掘与集成的挑战.地球科学, 46(1):350-358.
张瀚, 桂蕾, 王腾飞, 等, 2024.基于BP神经网络的第四系覆盖物厚度预测及三维地质建模.地球科学, 49(2):550-559.
周永章, 左仁广, 刘刚, 等, 2021.数学地球科学跨越发展的十年：大数据、人工智能算法正在改变地质学.矿物岩石地球化学通报, 40(03):556-573+777.

施引文献

资源附件(0)

访问统计

点击查看大图

计量

文章访问数: 41
HTML全文浏览量: 0
PDF下载量: 2
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

一种融合半监督深度学习与多点地质统计的三维地质建模及不确定性评估框架

doi: 10.3799/dqkx.2026.093

作者简介:
周顺平（1967-），教授，研究方向为三维地质建模，ORCID:0000-0002-2697-3383，E-mail:zhoushunping@cug.edu.cn，TEL:13507181840

通讯作者:
万波(1975-)，教授，研究方向为三维地质建模，ORCID:0000-0003-2387-5419.E-mail:wanbo@cug.edu.cn，TEL:13971097150

计量

A three-dimensional geological modeling framework integrating semi-supervised deep learning and multi-point geological statistics and uncertainty Analysis

计量

目录

留言板

一种融合半监督深度学习与多点地质统计的三维地质建模及不确定性评估框架

doi: 10.3799/dqkx.2026.093

作者简介: 周顺平（1967-） ，教授，研究方向为三维地质建模，ORCID:0000-0002-2697-3383，E-mail:zhoushunping@cug.edu.cn，TEL:13507181840

通讯作者: 万波(1975-)，教授，研究方向为三维地质建模，ORCID:0000-0003-2387-5419.E-mail:wanbo@cug.edu.cn，TEL:13971097150

计量

出版历程

A three-dimensional geological modeling framework integrating semi-supervised deep learning and multi-point geological statistics and uncertainty Analysis

计量

出版历程

目录

作者简介:
周顺平（1967-），教授，研究方向为三维地质建模，ORCID:0000-0002-2697-3383，E-mail:zhoushunping@cug.edu.cn，TEL:13507181840

通讯作者:
万波(1975-)，教授，研究方向为三维地质建模，ORCID:0000-0003-2387-5419.E-mail:wanbo@cug.edu.cn，TEL:13971097150