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

周顺平; 袁创; 储德平; 方芳; 潘声勇; 刘兆鑫; 李红; 万波

doi:10.3799/dqkx.2026.093

您当前的位置：

首页 >

文章列表页 >

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

更新时间：2026-10-15

- 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
- A Three⁃Dimensional Geological Modeling and Uncertainty Analysis Framework Integrating Semi⁃Supervised Deep Learning and Multiple⁃Point Geostatistics
- 地球科学 2026年51卷第9期页码：3547-3561
- 作者机构：
  
  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
- 作者简介：
  
  周顺平（1967-），男，教授，研究方向为三维地质建模.ORCID： 0000⁃0002⁃2697⁃3383. E⁃mail： zhoushunping@cug.edu.cn
  万波，ORCID: 0000⁃0003⁃2387⁃5419. E⁃mail: wanbo@cug.edu.cn
- 基金信息：
  
  国家自然科学基金项目(42571535)
- DOI：10.3799/dqkx.2026.093
  中图分类号： P628
- 收稿：2025-12-22，
  
  纸质出版：2026-09-30
- 稿件说明：
移动端阅览
周顺平，袁创，储德平，方芳，潘声勇，刘兆鑫，李红，万波，2026.一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.地球科学，51（9）：3547-3561.

Zhou Shunping，Yuan Chuang，Chu Deping，Fang Fang，Pan Shengyong，Liu Zhaoxin，Li Hong，Wan Bo，2026.A Three⁃Dimensional Geological Modeling and Uncertainty Analysis Framework Integrating Semi⁃Supervised Deep Learning and Multiple⁃Point Geostatistics.Earth Science，51（9）：3547-3561.
周顺平，袁创，储德平，方芳，潘声勇，刘兆鑫，李红，万波，2026.一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.地球科学，51（9）：3547-3561. DOI： 10.3799/dqkx.2026.093.

Zhou Shunping，Yuan Chuang，Chu Deping，Fang Fang，Pan Shengyong，Liu Zhaoxin，Li Hong，Wan Bo，2026.A Three⁃Dimensional Geological Modeling and Uncertainty Analysis Framework Integrating Semi⁃Supervised Deep Learning and Multiple⁃Point Geostatistics.Earth Science，51（9）：3547-3561. DOI： 10.3799/dqkx.2026.093.

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（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（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.

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 multiple-point geostatistics is proposed in this paper. 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 to generate the initial model; Subsequently

the multiple-point geostatistics 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)

Multi-layer 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 uncertainty controllable three-dimensional geological model reconstruction under the conditions of limited and unbalanced borehole data

providing effective technical support for the characterization and engineering application of underground structures in complex geological environments.

关键词

Keywords

references

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.2025.10805 0

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 ( 9 ): 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. K., Wang, G. W., 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., 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

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

Liu, Y. M., Durlofsky, L. J., 2021. 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 , 2404.19756. https://arxiv.org/abs/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: Stochastic Modeling with Training Images. Wiley, Hoboken. https://doi.org/10.1002/9781118662953

Mariethoz, G., Renard, P., Straubhaar, J., 2010. The Direct Sampling Method to Perform Multiple⁃Point Geostatistical Simulations. Water Resources Research , 46(11): 2008WR007621. 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., 2008. 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

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, 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) .

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) .

Taud, H., Mas, J. F., 2017. Multilayer Perceptron (MLP). Geomatic Approaches for Modeling Land Change Scenarios . Cham: Springer International Publishing: 451-455. https://doi.org/10.1007/978⁃3⁃319⁃60801⁃3_27

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 , 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., 2026. Three⁃Dimensional Reconstruction of Geologic Structures Based on Adaptive Fully⁃Connected Deep Neural Network and Multi⁃Point Statistics Method. Earth Science Frontiers , 33 ( 5 ): 99 - 114 (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 (in Chinese with English abstract) .

Zuo, R. G., Peng, Y., Li, T., et al., 2021. Challenges of Geological Prospecting Big Data Mining and Integration Using Deep Learning Algorithms. Earth Science , 46 ( 1 ): 350 - 358 (in Chinese with English abstract) .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于层次化堆叠自动编码器的钻井实时岩性识别方法

基于多普勒雷达的突发性灾害体智能识别

高寒山区溜砂坡遥感数据集构建与智能识别算法评估

融合多源特征的轻量化深度学习跨场景滑坡智能识别

数据-知识协同驱动的共伴生矿产知识图谱构建方法