Three-Dimensional Mineral Prospectivity Modeling of Skarn-Type Copper Deposits in the Anqing Area Based on Causal Inference and Graph Attention Networks
-
摘要:
本文提出了一种融合因果推理与图注意力网络的三维成矿预测方法，旨在提升复杂地质环境下对深部隐伏矽卡岩型铜矿床的预测精度与效率.研究以长江中下游成矿带的安庆地区为例，基于地质图、钻孔资料和地球物理数据，采用显式与隐式相结合的建模方法，构建了涵盖地层、岩体、断层及矿体的高精度三维地质模型.在此基础上，利用基于非高斯假设的RESIT因果推理算法，对62类控矿要素进行分析，识别并构建因果图，最终筛选出14个核心控矿变量.随后，结合三维空间邻接关系构建预测数据集，并将因果结构引入GAT模型以进行矿化概率预测.对比实验结果表明，该方法在准确率、AUC值及成功率曲线等指标上均优于随机森林、支持向量机、图卷积网络和三维卷积网络等常用方法.基于该模型预测，本文圈定了四个与闪长岩侵入体及三叠系碳酸盐岩接触带密切相关的深部高潜力成矿靶区.研究成果表明，因果推理与深度图学习的结合不仅能够提升预测性能，还增强了模型的地质可解释性，为深部矿产资源勘查提供了一条新的技术路径.
Abstract:This study proposes a three-dimensional mineral prospectivity modeling method that integrates causal inference with Graph Attention Networks (GAT) to improve the accuracy and efficiency of deep concealed skarn-type copper deposits prediction in complex geological settings. Using the Anqing area of the Middle-Lower Yangtze Metallogenic Belt as a case, a high-precision 3D geological model involving strata, intrusions, faults, and ore bodies was constructed based on geological maps, borehole data, and geophysical information through a hybrid explicit-implicit modeling approach. On this basis, the RESIT causal inference algorithm, which is built upon non-Gaussian assumptions, was employed to analyze 62 ore-controlling factors. A causal graph was established, and 14 key controlling variables were identified. Subsequently, a 3D prediction dataset incorporating spatial adjacency relationships was developed, and the causal structure was introduced into the GAT model for mineralization probability prediction. Comparative experiments demonstrate that the proposed method outperforms commonly used approaches-including Random Forest, Support Vector Machine, Graph Convolutional Networks, and 3D Convolutional Neural Networks-in terms of accuracy, AUC, and success rate curves. Based on the predictions, four deep high-potential target zones were delineated, which are closely associated with diorite intrusions and Triassic carbonate contact zones. The results indicate that integrating causal inference with deep graph learning not only enhances prediction performance but also improves the geological interpretability of the model, providing a promising technical pathway for deep mineral exploration.
-
图 1 长江中下游成矿带矿集区与矿床分布简图(据翟裕生等，1992)
Fig. 1. Simplified diagram of ore districts and ore deposits in the middle and lower Yangtze metallogenic belt (modified after Zhai et al., 1992)
图 2 安庆铜矿主矿体剖面示意图
据安徽省地矿局326地质队（1976）安庆铜矿储量报告
Fig. 2. Cross-section of the No.1 orebody, Anqing copper deposit
图 4 安庆地区各地质体三维模型
a. 研究区三维地质模型；b. 研究区地表地质图三维展示；c. 岩体三维模型；d. 第四系三维地质模型；e. 侏罗系三维地质模型；f. 三叠系三维地质模型；g. 二叠系三维地质模型；h. 石炭系及泥盆系三维地质模型；i. 志留系三维地质模型；j. 奥陶系及寒武系三维地质模型
Fig. 4. 3D geological model of Anqing area and geological bodies
图 13 去除核心要素GAT网络ROC曲线
Fig. 13. ROC curve of the GAT network after removing core elements
图 14 三维成矿预测靶区图
a. 预测靶区与闪长岩；b.预测靶区与三叠系；c.预测靶区平面图；d.预测靶区俯视图
Fig. 14. Three-dimensional mineralization prediction results
表 1 相关性数据分析结果
Table 1. The results of the correlation data analysis
相关性 相关性系数 要素量 重复数据 正相关 0.050至0.053 1 0 0.04至0.05 2 0 0.03至0.04 18 12 0.02至0.03 2 1 0.01至0.02 11 1 0至0.01 5 0 负相关 0至‒0.01 16 5 ‒0.01至‒0.02 0 0 ‒0.02至‒0.03 1 0 ‒0.03至‒0.04 3 1 ‒0.04至‒0.05 1 0 
下载: 导出CSV
表 2 Jarque-Bera（JB）、D’Agostino K2检验
Table 2. Jarque-Bera (JB), D'Agostino K2 test
序号 变量 p-value（10‒3） RESET_p 拒绝线性? 0 闪长岩膨胀 2.20 0 TRUE 1 闪长岩隆起膨胀 4.80 0 TRUE 2 闪长岩隆起闭运算 6.90 0 TRUE 3 闪长岩隆起粗糙度 4.70 1.78×10‒167 TRUE 4 闪长岩隆起倾角分析 4.60 3.54×10‒265 TRUE 5 闪长岩隆起 4.60 0 TRUE 6 闪长岩闭运算 1.30 0 TRUE 7 闪长岩隆起走向曲率 4.70 0 TRUE 8 闪长岩相对高差分析 0.80 0 TRUE 9 闪长岩距离场 2.10 2.40×10‒41 TRUE 10 闪长岩隆起距离场 4.70 0 TRUE 11 三叠系膨胀 2.10 0 TRUE 12 三叠系距离场 2.20 2.12×10‒37 TRUE 13 三叠系隆起距离场 2.50 3.46×10‒52 TRUE
下载: 导出CSV
表 3 安庆地区样本集
Table 3. The sample set of Anqing area
样品类别 训练集 验证集 总计 正样本(个) 3 486 871 4 357 负样本(个) 3 486 871 4 357 总计 6 972 1 742 8 714
下载: 导出CSV
-
Agterberg, F. P., Bonham-Carter, G. F., 2005. Measuring the Performance of Mineral-Potential Maps. Natural Resources Research, 14(1): 1-17. https://doi.org/10.1007/s11053-005-4674-0 Athey, S., Imbens, G. W., 2017. The State of Applied Econometrics: Causality and Policy Evaluation. Journal of Economic Perspectives, 31(2): 3-32. https://doi.org/10.1257/jep.31.2.3 Caumon, G., Collon-Drouaillet, P., Le Carlier de Veslud, C., et al., 2009. Surface-Based 3D Modeling of Geological Structures. Mathematical Geosciences, 41(8): 927-945. https://doi.org/10.1007/s11004-009-9244-2 Deng, H., Huang, X. F., Mao, X. C., et al., 2022a. Generalized Mathematical Morphological Method for 3D Shape Analysis of Geological Boundaries: Application in Identifying Mineralization-Associated Shape Features. Natural Resources Research, 31(4): 2103-2127. https://doi.org/10.1007/s11053-021-09975-6 Deng, H., Zheng, Y., Chen, J., et al., 2022b. Learning 3D Mineral Prospectivity from 3D Geological Models Using Convolutional Neural Networks: Application to a Structure-Controlled Hydrothermal Gold Deposit. Computers & Geosciences, 161: 105074. https://doi.org/10.1016/j.cageo.2022.105074 He, H., Ma, C., Ye, S., et al., 2024. Low Resource Chinese Geological Text Named Entity Recognition Based on Prompt Learning. Journal of Earth Science, 35(3): 1035-1043. https://doi.org/10.1007/s12583-023-1944-8 Hu, X. Y., Li, X. H., Yuan, F., et al., 2020. 3D Numerical Simulation-Based Targeting of Skarn Type Mineralization within the Xuancheng-Magushan Orefield, Middle-Lower Yangtze Metallogenic Belt, China. Lithosphere, 2020: 8351536. https://doi.org/10.2113/2020/8351536 Hu, X. Y., Yuan, F., Li, X. H., et al., 2018. 3D Characteristic Analysis-Based Targeting of Concealed Kiruna-Type Fe Oxide-Apatite Mineralization within the Yangzhuang Deposit of the Zhonggu Orefield, Southern Ningwu Volcanic Basin, Middle-Lower Yangtze River Metallogenic Belt, China. Ore Geology Reviews, 92: 240-256. https://doi.org/10.1016/j.oregeorev.2017.11.019 Hyvärinen, A., Zhang, K., Shimizu, S., et al., 2010. Estimation of a Structural Vector Autoregression Model Using Non-Gaussianity. Journal of Machine Learning Research, 11(5): 1709-1731. Kipf, T. N., Welling, M., 2016. Semi-Supervised Classification with Graph Convolutional Networks. arXiv Preprint, arXiv: 1609.02907. https://doi.org/10.48550/arXiv.1609.02907 Lee, C., Oh, H. J., Cho, S. J., et al., 2019. Three-Dimensional Prospectivity Mapping of Skarn-Type Mineralization in the Southern Taebaek Area, Korea. Geosciences Journal, 23(2): 327-339. https://doi.org/10.1007/s12303-018-0035-y Li, H., Li, X. H., Yuan, F., et al., 2020. Convolutional Neural Network and Transfer Learning Based Mineral Prospectivity Modeling for Geochemical Exploration of Au Mineralization within the Guandian-Zhangbaling Area, Anhui Province, China. Applied Geochemistry, 122: 104747. https://doi.org/10.1016/j.apgeochem.2020.104747 Li, H., Li, X. H., Yuan, F., et al., 2022. Knowledge-Driven Based Three-Dimensional Prospectivity Modeling of Fe-Cu Skarn Deposits: A Case Study of the Fanchang Volcanic Basin, Anhui Province, Eastern China. Ore Geology Reviews, 149: 105065. https://doi.org/10.1016/j.oregeorev.2022.105065 Li, H., Li, X. H., Yuan, F., et al., 2023. Genetic Algorithm Optimized Light Gradient Boosting Machine for 3D Mineral Prospectivity Modeling of Cu Polymetallic Skarn-Type Mineralization, Xuancheng Area, Anhui Province, Eastern China. Natural Resources Research, 32(5): 1897-1916. https://doi.org/10.1007/s11053-023-10227-y Li, N., Bagas, L., Li, X. H., et al., 2016. An Improved Buffer Analysis Technique for Model-Based 3D Mineral Potential Mapping and Its Application. Ore Geology Reviews, 76: 94-107. https://doi.org/10.1016/j.oregeorev.2015.12.002 Li, S., Chen, J. P., Liu, C., et al., 2021a. Mineral Prospectivity Prediction via Convolutional Neural Networks Based on Geological Big Data. Journal of Earth Science, 32(2): 327-347. https://doi.org/10.1007/s12583-020-1365-z Li, T., Zuo, R. G., Xiong, Y. H., et al., 2021b. Random-Drop Data Augmentation of Deep Convolutional Neural Network for Mineral Prospectivity Mapping. Natural Resources Research, 30(1): 27-38. https://doi.org/10.1007/s11053-020-09742-z Li, X. H., Yuan, F., Zhang, M. M., et al., 2015. Three-Dimensional Mineral Prospectivity Modeling for Targeting of Concealed Mineralization within the Zhonggu Iron Orefield, Ningwu Basin, China. Ore Geology Reviews, 71: 633-654. https://doi.org/10.1016/j.oregeorev.2015.06.001 Li, Y., Yuan, F., Jowitt, S. M., et al., 2025. Genesis of the Maweishan Pb-Zn Deposit, Eastern China and Controls on the Distribution and Formation of Sphalerite-Hosted Critical Metal (Cd, Ga, and in) Mineralization. Ore Geology Reviews, 181: 106600. doi: 10.1016/j.oregeorev.2025.106600 Luo, Z. J., Zuo, R. G., Xiong, Y. H., et al., 2021. Detection of Geochemical Anomalies Related to Mineralization Using the GANomaly Network. Applied Geochemistry, 131: 105043. https://doi.org/10.1016/j.apgeochem.2021.105043 Ma, S. S., Statnikov, A., 2017. Methods for Computational Causal Discovery in Biomedicine. Behaviormetrika, 44(1): 165-191. https://doi.org/10.1007/s41237-016-0013-5 Mao, X. C., Ren, J., Liu, Z. K., et al., 2019. Three-Dimensional Prospectivity Modeling of the Jiaojia-Type Gold Deposit, Jiaodong Peninsula, Eastern China: A Case Study of the Dayingezhuang Deposit. Journal of Geochemical Exploration, 203: 27-44. https://doi.org/10.1016/j.gexplo.2019.04.002 Mao, X. C., Zhang, B., Deng, H., et al., 2016. Three-Dimensional Morphological Analysis Method for Geologic Bodies and Its Parallel Implementation. Computers & Geosciences, 96: 11-22. https://doi.org/10.1016/j.cageo.2016.07.004 Mao, X. C., Zhang, W., Liu, Z. K., et al., 2020.3D Mineral Prospectivity Modeling for the Low-Sulfidation Epithermal Gold Deposit: A Case Study of the Axi Gold Deposit, Western Tianshan, NW China. Minerals, 10(3): 233. https://doi.org/10.3390/min10030233 Mejía-Herrera, P., Royer, J. J., Caumon, G., et al., 2015. Curvature Attribute from Surface-Restoration as Predictor Variable in Kupferschiefer Copper Potentials: An Example from the Fore-Sudetic Region. Natural Resources Research, 24(3): 275-290. https://doi.org/10.1007/s11053-014-9247-7 Shao, R. Q., Lin, P., Xu, Z. H., et al., 2025. Machine Learning of Element Geochemical Anomalies for Adverse Geology Identification in Tunnels. Journal of Earth Science, 36(3): 1261-1276. https://doi.org/10.1007/s12583-024-0090-4 Shimizu, S., Hoyer, P. O., Hyvärinen, A., et al., 2006. A Linear Non-Gaussian Acyclic Model for Causal Discovery. Journal of Machine Learning Research, 7(10): 2003-2030. Spirtes, P., 2001. An Anytime Algorithm for Causal Inference. International Workshop on Artificial Intelligence and Statistics. Key West. Sun, K., Chen, Y. S., Geng, G. S., et al., 2024. A Review of Mineral Prospectivity Mapping Using Deep Learning. Minerals, 14(10): 1021. https://doi.org/10.3390/min14101021 Sun, T., Li, H., Wu, K. X., et al., 2020. Data-Driven Predictive Modelling of Mineral Prospectivity Using Machine Learning and Deep Learning Methods: A Case Study from Southern Jiangxi Province, China. Minerals, 10(2): 102. https://doi.org/10.3390/min10020102 Varian, H. R., 2016. Causal Inference in Economics and Marketing. Proceedings of the National Academy of Sciences, 113(27): 7310-7315. https://doi.org/10.1073/pnas.1510479113 Xu, X. Y., Xu, X. C., Xie, Q. Q., et al., 2022. Geological Features and Ore-Forming Mechanisms of the Chating Cu-Au Deposit: A Rare Case of Porphyry Deposit in the Middle-Lower Yangtze River Metallogenic Belt. Ore Geology Reviews, 144: 104860. https://doi.org/10.1016/j.oregeorev.2022.104860 Zhai, Y. S., Yao, S. Z., Lin, X. D., 1992. Metallogenic Regularities of Iron-Copper (Gold) Depositst in the Middle and Lower Reaches of the Yangtze River. Geological Publishing House, Beijing (in Chinese). Zhang, M. M., Zhou, G. Y., Shen, L., et al., 2019. Comparison of 3D Prospectivity Modeling Methods for Fe-Cu Skarn Deposits: A Case Study of the Zhuchong Fe-Cu Deposit in the Yueshan Orefield (Anhui), Eastern China. Ore Geology Reviews, 114: 103126. https://doi.org/10.1016/j.oregeorev.2019.103126 Zhou, T. F., Fan, Y., Chen, J., et al., 2020. Critical Metal Resources in the Middle-Lower Yangtze River Valley Metallogenic Belt. Chinese Science Bulletin, 65(33): 3665-3677 (in Chinese with English abstract). doi: 10.1360/TB-2020-0347 Zhou, T. F., Fan, Y., Wang, S. W., et al., 2017. Metallogenic Regularity and Metallogenic Model of the Middle-Lower Yangtze River Valley Metallogenic Belt. Acta Petrologica Sinica, 33(11): 3353-3372 (in Chinese with English abstract). 周涛发, 范裕, 陈静, 等, 2020. 长江中下游成矿带关键金属矿产研究现状与进展. 65(33): 3665-3677. 周涛发, 范裕, 王世伟, 等, 2017. 长江中下游成矿带成矿规律和成矿模式. 岩石学报, 33(11): 3353-3372. 翟裕生, 姚书振, 林新多, 1992. 长江中下游地区铁铜(金)成矿规律. 北京: 地质出版社. -
点击查看大图
计量
- 文章访问数: 777
- HTML全文浏览量: 182
- PDF下载量: 165
- 被引次数: 0
