基于成矿过程数值模拟与机器学习的三维找矿预测:以内蒙古毛登矿床为例
孙会玲 , 唐瑞 , 李杨 , 赵静 , 张彤 , 肖克炎 , 陈江均 , 赵婧 , 李耀永 , 闫瑞花 , 佟卉 , 安艳丽 , 白立兵
地球科学 ›› 2026, Vol. 51 ›› Issue (03) : 921 -939.
基于成矿过程数值模拟与机器学习的三维找矿预测:以内蒙古毛登矿床为例
Three⁃Dimensional Mineral Prospectivity Prediction Based on Mineralization Process Numerical Simulation and Machine Learning: A Case Study of the Maodeng Deposit in Inner Mongolia
,
,
针对深部矿体预测困难的问题,本研究以内蒙古毛登铜锡矿床为例,旨在建立一套融合成矿过程数值模拟与机器学习的三维矿产预测方法.本研究采用Flac3D进行成矿过程的数值模拟,获取了控矿的物理场参数,如应力、温度和流体压力等;随后,结合这些物理结果与地质数据,利用XGBoost机器学习模型进行三维定量矿产预测.结果表明:该方法成功模拟了矿区的应力场、温度场和流体运移过程,XGBoost模型的AUC值达到了99.26%,表现出卓越的预测能力;通过SHAP分析,发现剪切应力、孔隙压力和温度是影响矿体分布的主要因素;预测结果与已知矿体高度重合,为矿体预测提供了可靠的依据,最终圈定出两处找矿靶区.研究证明,结合成矿过程数值模拟与机器学习的预测方法可以有效提高深部矿产资源的预测精度,为类似地区的矿产资源评估提供了新的技术思路.
To address the challenges of deep mineral body prediction, this study proposes a three-dimensional mineral prospectivity prediction method that integrates mineralization process numerical simulation and machine learning, using the Maodeng copper-tin deposit in Inner Mongolia as a case study. The Flac3D is used for numerical simulation of the mineralization process to obtain key physical field parameters that control mineralization, such as stress, temperature, and fluid pressure. These physical results, combined with geological data, are then used in the XGBoost machine learning model for three-dimensional quantitative mineral prospectivity prediction. It is demonstrated that the method successfully simulated the stress field, temperature field, and fluid migration process of the mining area. The AUC value of the XGBoost model reached 99.26%, showing excellent predictive ability. SHAP analysis reveals that shear stress, pore pressure, and temperature are the main factors affecting the distribution of mineral bodies. The predicted results highly correlate with the known mineral bodies, providing a reliable basis for mineral body prediction and ultimately identifying two mineral prospecting target areas. The study demonstrates that the combination of mineralization process numerical simulation and machine learning prediction methods can effectively improve the accuracy of deep mineral resource predictions, offering new technical insights into mineral resources assessment in similar regions.
| [1] |
An, W. T., Chen, J. P., Zhu, P. F., 2021. A Two⁃Way Forecasting Method Based on Numerical Simulation of Mineralization Process for the Prediction of Concealed Ore Deposits. Earth Science Frontiers, 28(3): 97-111 (in Chinese with English abstract). |
| [2] |
Carranza, E. J. M., 2017. Natural Resources Research Publications on Geochemical Anomaly and Mineral Potential Mapping, and Introduction to the Special Issue of Papers in these Fields. Natural Resources Research, 26(4): 379-410. https://doi.org/10.1007/s11053⁃017⁃9348⁃1 |
| [3] |
Chen, G. Z., Wu, G., Li, T. G., et al., 2021. Mineralization of the Daolundaba Cu⁃Sn⁃W⁃Ag Deposit in the Southern Great Xing’an Range, China: Constraints from Geochronology, Geochemistry, and Hf Isotope. Ore Geology Reviews, 133: 104117. https://doi.org/10.1016/j.oregeorev.2021.104117 |
| [4] |
Chen, J. P., Lü, P., Wu, W., et al., 2007. A 3D Method for Predicting Blind Orebodies, Based on a 3D Visualization Model and Its Application. Earth Science Frontiers, 14(5): 54-62 (in Chinese with English abstract). |
| [5] |
Chen, J. P., Shi, R., Wang, L. M., et al., 2012a. 3D Metallogenic Prediction for Western Section of Q8 Gold Deposit in Tongguan County of Shaanxi Based on Digital Mineral Deposit Model. Journal of Geology, 36(3): 237-242 (in Chinese with English abstract). |
| [6] |
Chen, J. P., Wang, C. N., Shang, B. C., et al., 2012b. Three⁃Dimensional Metallogenic Prediction in Yongmei Region Based on Digital Ore Deposit Model. Scientific and Technological Management of Land and Resources, 29(6): 14-20 (in Chinese with English abstract). |
| [7] |
Chen, J. P., Yan, Q., Shang, B. C., et al., 2012c. On 3D Prediction of Lead⁃Zinc Deposit in Huangshaping Ore District in Hunan. Journal of Geology, 36(3): 243-249 (in Chinese with English abstract). |
| [8] |
Chen, J. P., Yu, P. P., Shi, R., et al., 2014. Research on Three⁃Dimensional Quantitative Prediction and Evaluation Methods of Regional Concealed Ore Bodies. Earth Science Frontiers, 21(5): 211-220 (in Chinese with English abstract). |
| [9] |
Deng, Y. X., 2013. Study on Hydrocarbon Generation Mechanism and Its Controlling Factor on Hydrocarbon Accumulation in Baiyinchagan Depression, Erlian Basin (Dissertation). China University of Geosciences, Beijing (in Chinese with English abstract). |
| [10] |
Gao, M., Wang, G. W., Tang, D. M., 2025. Three⁃Dimensional Mineral Prospectivity Mapping and Uncertainty Evaluation in the Kalatongke Copper⁃Nickel District, Xinjiang, China. Earth Science Frontiers, Online (in Chinese with English abstract). https://doi.org/10.13745/j.esf.sf.2025.4.2 |
| [11] |
Guo, S., He, P., Zhang, X. B., et al., 2019. Geochronology and Geochemistry of Maodeng⁃Xiaogushan Tin⁃Polymetallic Orefield in Southern Da Hinggan Mountains and Their Geological Significances. Mineral Deposits, 38(3): 509-525 (in Chinese with English abstract). |
| [12] |
Hu, X. Y., Li, X. H., Yuan, F., et al., 2020. Numerical Modeling of Ore⁃Forming Processes within the Chating Cu⁃Au Porphyry⁃Type Deposit, China: Implications for the Longevity of Hydrothermal Systems and Potential Uses in Mineral Exploration. Ore Geology Reviews, 116: 103230. https://doi.org/10.1016/j.oregeorev.2019.103230 |
| [13] |
Ji, G. Y., Jiang, S. H., Li, G. F., et al., 2021a. Metallogenetic Control of Magmatism on the Maodeng Sn⁃Cu Deposit in the Southern Great Xing’an Range: Evidence from Geochronology, Geochemistry, and Sr⁃Nd⁃Pb Isotopes. Geotectonica et Metallogenia, 45(4): 681-704 (in Chinese with English abstract). |
| [14] |
Ji, G. Y., Jiang, S. H., Zhang, L. S., et al., 2021b. Petrogenic and Metallogenic Significance of Alubaogeshan Granite in Maodeng Deposit of Southern Da Hinggan Mountains: Evidence from Mineralogy of Zircon, Amphibole and Biotite. Mineral Deposits, 40(3): 449-474 (in Chinese with English abstract). |
| [15] |
Ji, G. Y., Jiang, S. H., Zhang, L. S., et al., 2022. Chronology and Geochemical Characteristics of the Highly Fractionated Alkali Feldspar Granite from the Maodeng Deposit in the Southern Great Xing’an Range. Acta Petrologica Sinica, 38(3): 855-882 (in Chinese with English abstract). |
| [16] |
Li, C., Xiao, K. Y., Sun, L., et al., 2024. CNN⁃Transformers for Mineral Prospectivity Mapping in the Maodeng⁃Baiyinchagan Area, Southern Great Xing’an Range. Ore Geology Reviews, 167: 106007. https://doi.org/10.1016/j.oregeorev.2024.106007 |
| [17] |
Li, X. C., Zhou, M. F., Williams⁃Jones, A. E., et al., 2019. Timing and Genesis of Cu⁃(Au) Mineralization in the Khetri Copper Belt, Northwestern India: Constraints from in Situ U⁃Pb Ages and Sm⁃Nd Isotopes of Monazite⁃(Ce). Mineralium Deposita, 54(4): 553-568. https://doi.org/10.1007/s00126⁃018⁃0823⁃3 |
| [18] |
Li, Z. K., Zhou, Z., Tang, X. F., et al., 2009. Stability Analysis and Considerations of Underground Powerhouse Caverns Group of Jinping I Hydropower Station. Chinese Journal of Rock Mechanics and Engineering, 28(11): 2167-2175 (in Chinese with English abstract). |
| [19] |
Li, Z. S., Liu, Z. G., 2019. Feature Selection Algorithm Based on XGBoost. Journal on Communications, 40(10): 101-108 (in Chinese with English abstract). |
| [20] |
Liu, R. L., Wu, G., Li, T. G., et al., 2018. LA⁃ICP⁃MS Cassiterite and Zircon U⁃Pb Ages of the Weilasituo Tin⁃Polymetallic Deposit in the Southern Great Xing’an Range and Their Geological Significance. Earth Science Frontiers, 25(5): 183-201 (in Chinese with English abstract). |
| [21] |
Mao, J. W., Xie, G. Q., Zhang, Z. H., et al., 2005. Mesozoie Large⁃Scale Metallogenic Pulses in North China and Corresponding Geodynamic Settings. Acta Petrologica Sinica, 21(1): 169-188 (in Chinese with English abstract). |
| [22] |
Mao, X. C., Duan, X. M., Deng, H., et al., 2026. Intelligent 3D Prediction of Deep Mineral Resources: Theory, Methods, and Challenge. Earth Science, 51(3): 793-815 (in Chinese with English abstract). |
| [23] |
Mao, X. C., Zhang, M. M., Deng, H., et al., 2016. Three⁃Dimensional Visualization Prediction Method for Concealed Ore Bodies in Deep Mining Areas. Journal of Geology, 40(3): 363-371 (in Chinese with English abstract). |
| [24] |
Oliver, N. H. S., McLellan, J. G., Hobbs, B. E., et al., 2006. 100th Anniversary Special Paper: Numerical Models of Extensional Deformation, Heat Transfer, and Fluid Flow across Basement⁃Cover Interfaces during Basin⁃Related Mineralization. Economic Geology, 101(1): 1-31. https://doi.org/10.2113/gsecongeo.101.1.1 |
| [25] |
Ord, A., Hobbs, B. E., Zhang, Y., et al., 2002. Geodynamic Modelling of the Century Deposit, Mt Isa Province, Queensland. Australian Journal of Earth Sciences, 49(6): 1011-1039. https://doi.org/10.1046/j.1440⁃0952.2002.00968.x |
| [26] |
Ouyang, H. G., Li, R. H., Zhou, Z. H., 2016. The Jurassic Mineralization of the Shuangjianzisha Ag⁃Polymetallic Deposit and Its Significance in Prospecting: Evidence from Geochronology. Acta Geologica Sinica, 90(8): 1835-1845 (in Chinese with English abstract). |
| [27] |
Teng, J. W., Xue, G. Q., Song, M. C., 2022. Theory on Exploring Mineral Resources in the Second Deep Space and Practices with Electromagnetic Method. Chinese Journal of Geophysics, 65(10): 3975-3985 (in Chinese with English abstract). |
| [28] |
Touloukian, Y. S., 1990. Physical Properties of Rocks and Minerals. Translated by Shan, J. Z., et al., Petroleum Industry Press, Beijing (in Chinese). |
| [29] |
Xiao, F., Chen, X. Y., Cheng, Q. M., 2024. Combining Numerical Modeling and Machine Learning to Predict Mineral Prospectivity: A Case Study from the Fankou Pb⁃Zn Deposit, Southern China. Applied Geochemistry, 160: 105857. https://doi.org/10.1016/j.apgeochem.2023.105857 |
| [30] |
Xiao, K. Y., Li, N., Sun, L., et al., 2012. Large Scale 3D Mineral Prediction Methods and Channels Based on 3D Information Technology. Journal of Geology, 36(3): 229-236 (in Chinese with English abstract). |
| [31] |
Xiao, K. Y., Lou, D. B., Sun, L., et al., 2013. Some Progresses of Mineral Prediction Theory and Method in Important Mineral Resource Potential Assessment of China. Journal of Jilin University (Earth Science Edition), 43(4): 1073-1082 (in Chinese with English abstract). |
| [32] |
Yao, L., Lü, Z. C., Ye, T. Z., et al., 2017. Zircon U⁃Pb Age, Geochemical and Nd⁃Hf Isotopic Characteristics of Quartz Porphyry in the Baiyinchagan Sn Polymetallic Deposit, Inner Mongolia, Southern Great Xing’an Range, China. Acta Petrologica Sinica, 33(10): 3183-3199 (in Chinese with English abstract). |
| [33] |
Ye, T. Z., 2013. Theoretical Framework of Methodology of Deposit Modeling and Integrated Geological Information for Mineral Resource Potential Assessment. Journal of Jilin University (Earth Science Edition), 43(4): 1053-1072 (in Chinese with English abstract). |
| [34] |
Ye, T. Z., Xiao, K. Y., Yan, G. S., 2007. Methodology of Deposit Modeling and Mineral Resource Potential Assessment Using Integrated Geological Information. Earth Science Frontiers, 14(5): 11-19 (in Chinese with English abstract). |
| [35] |
Yuan, F., Li, X. H., Tian, W. D., et al., 2024. Key Issues in Three⁃Dimensional Predictive Modeling of Mineral Prospectivity. Earth Science Frontiers, 31(4): 119-128 (in Chinese with English abstract). |
| [36] |
Yuan, F., Li, X. H., Zhang, M. M., et al., 2014. Three Dimension Prospectivity Modelling Based on Integrated Geoinformation for Prediction of Buried Orebodies. Acta Geologica Sinica, 88(4): 630-643 (in Chinese with English abstract). |
| [37] |
Yuan, F., Li, X. H., Zhang, M. M., et al., 2018. Research Progress of 3D Prospectivity Modeling. Gansu Geology, 27(1): 32-36 (in Chinese with English abstract). |
| [38] |
Yuan, F., Zhang, M. M., Li, X. H., et al., 2019. Prospectivity Modeling: From Twodimension to Three⁃ Dimension. Acta Petrologica Sinica, 35(12): 3863-3874 (in Chinese with English abstract). |
| [39] |
Zhai, M. G., Wu, F. Y., Hu, R. Z., et al., 2019. Critical Metal Mineral Resources: Current Research Status and Scientific Issues. Bulletin of National Natural Science Foundation of China, 33(2): 106-111 (in Chinese with English abstract). |
| [40] |
Zhang, Q. P., Chen, J. P., Xu, H., et al., 2022. Three⁃ Dimensional Mineral Prospectivity Mapping by XGBoost Modeling: A Case Study of the Lannigou Gold Deposit, China. Natural Resources Research, 31(3): 1135-1156. https://doi.org/10.1007/s11053⁃022⁃10054⁃7 |
| [41] |
Zhang, X. N., Zhang, Y. F., Peng, R., et al., 2025. Whole⁃Rock Geochemistry, Zircon U⁃Pb Ages, and Hf Isotopic Characteristics of Ore⁃Related Intrusions of the Tin Polymetallic Deposits in the Southern Great Xing’an Range and Their Geological Significance: Case Studies of the Bianjiadayuan, Maodeng, and Baog. Acta Geoscientica Sinica, 46(2): 343-360 (in Chinese with English abstract). |
| [42] |
Zhang, Z. Q., Wang, G. W., Carranza, E. J. M., et al., 2024. An Uncertainty⁃Quantification Machine Learning Framework for Data⁃Driven Three⁃Dimensional Mineral Prospectivity Mapping. Natural Resources Research, 33(4): 1393-1411. https://doi.org/10.1007/s11053⁃024⁃10349⁃x |
| [43] |
Zhao, S. J., Cao, Y., Zhang, J., et al., 2025. Polymetallic Mineralization Model of Copper and Tin in the Maodeng Area of the Daxing’anling Metallogenic Belt. Geological Review, 71(S1): 121-123 (in Chinese with English abstract). |
| [44] |
Zhou, G. Y., Chen, J. P., An, W. T., et al., 2024. Three⁃Dimensional Mineral Prospectivity Mapping Based on Natural Language Processing and Random Forests: A Case Study of the Xiyu Diamond Deposit, China. Ore Geology Reviews, 169: 106082. https://doi.org/10.1016/j.oregeorev.2024.106082 |
| [45] |
Zhou, J. T., Yu, W. C., Du, Y. S., et al., 2025. Occurrence Forms of Rare Earth Elements in Aluminum⁃Bearing Rock Series in China: Ensemble Machine Learning Analysis Driven by Major Element Data. Journal of Palaeogeography (Chinese Edition), 27(2): 307-320 (in Chinese with English abstract). |
| [46] |
Zuo, R. G., 2017. Machine Learning of Mineralization⁃Related Geochemical Anomalies: A Review of Potential Methods. Natural Resources Research, 26(4): 457-464. https://doi.org/10.1007/s11053⁃017⁃9345⁃4 |
2025年度内蒙古自治区自然资源厅综合项目(2025KJTW0020)
/
| 〈 |
|
〉 |