基于WOA-CNN的到时预测方法及其在金川矿区金属矿探测中的应用

A WOA-CNN-Based Arrival Time Prediction Method and Its Application to Metal Mineral Exploration in the Jinchuan Mining Area

摘要

摘要:地震勘探方法广泛应用于浅层地壳结构研究,其中双差层析成像是一种常用的高精度成像技术.然而,野外数据存在到时数量不足和射线密度覆盖范围有限等问题,往往导致双差层析成像的反演结果存在不确定性.为此,本文采取基于鲸鱼优化算法(WOA)优化的卷积神经网络(CNN)方法(WOA-CNN)预测地震到时,提高双差层析成像结果的可靠性;并利用在金川矿区速度结构成像中的应用验证方法的可行性.金川大型镍铜铂族元素硫化物矿床位于中国甘肃省,已开采50余年,随着浅部矿体日益枯竭,深部矿产勘探需求愈加迫切.为了研究矿区深部结构,在金川矿区布设了69台短周期三分量地震仪,连续采集了27 d的地震数据.通过LOC FLOW定位方法精准定位了309个矿震事件,包含4316个P波到时,将其作为双差层析成像方法的输入,但因P波数量较少,成像效果不佳.随后,利用WOA-CNN预测了309个事件的到时,共获得11124个P波到时数据,加入预测到时,成功反演了研究区的三维P波速度结构.结合以往研究结果,验证该矿区深部存在两个独立岩体,并且这一发现与已有的地质资料高度吻合;同时验证了Ⅱ36测线浅层矿体的典型“漏斗状”结构,并依据速度变化规律推测金川矿区东段岩体2 km以下仍有较大的找矿潜力.

Abstract

Abstract: Seismic exploration methods are widely used to investigate shallow crustal structures, and double-difference tomography is a commonly employed high-precision imaging technique. However, due to issues such as insufficient arrival-time picks and limited ray-density coverage in field data, the inversion results of double-difference tomography often exhibit uncertainties. To address this problem, this paper proposes a method based on the whale optimization algorithm (WOA)-optimized convolutional neural network (CNN) (WOA-CNN) for predicting seismic arrival times, thereby improving the reliability of double-difference tomography results. The feasibility of this method is evaluated through its application to velocity-structure imaging in the Jinchuan mining area. The Jinchuan large nickel-copper-platinum group element sulfide deposit is located in Gansu Province, China, and has been mined for over 50 years. As shallow ore bodies become depleted, the demand for deep mineral exploration has become increasingly urgent. To investigate the deep structure of the mining area, 69 short-period three-component seismometers were deployed in the Jinchuan mining area, continuously collecting seismic data for 27 days. Using the LOC-FLOW location method, 309 mining-induced seismic events were accurately located, including 4316 P-wave arrival-time picks as input for the double-difference tomography. However, due to the limited number of P-wave arrivals, the imaging results were unsatisfactory. Subsequently, the WOA-CNN was used to predict the arrival times of the 309 events, obtaining a total of 11124 P-wave arrival-time picks. By incorporating the predicted arrival times, the three-dimensional P-wave velocity structure of the study area was successfully constructed. Analysis combined with previous research results verifies the existence of two independent rock bodies in the deep part of the mining area, and this finding is highly consistent with existing geological data. Additionally, the typical “funnel-shaped” structure of the shallow ore body along the II-36 survey line was verified. Based on the velocity variation patterns, it is inferred that there is still significant exploration potential below 2 km in the eastern section of the Jinchuan mining area.

关键词

WOA-CNN / 到时预测 / 三维P波速度结构 / 矿震定位 / 金属矿勘探 / 金川矿区

Key words

WOA-CNN / arrival time prediction / 3D P-wave velocity structure / mine seismic location / metallic mineral exploration / Jinchuan mining area

参考文献

[1] Zhang H, Thurber C H. Double-Difference Tomography: The Method and Its Application to the Hayward Fault, California[J]. Bulletin of the Seismological Society of America, 2003, 93(5): 1875-1889.

[2] Yan D, Tian Y, Zhao D, et al. Seismicity and Magmatic System of the Changbaishan Intraplate Volcano in East Asia[J]. Journal of Geophysical Research: Solid Earth, 2023, 128(9): e2023JB026853.

[3] Guo Y, Peng S, Du W, et al. Fault and Horizon Automatic Interpretation by CNN: A Case Study of Coalfield[J]. Journal of Geophysics and Engineering, 2020, 17(6): 1016-1025.

[4] LeCun Y, Bottou L, Bengio Y, et al. Gradient-Based Learning Applied to Document Recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

[5] 林雨准, 刘智, 王淑香, 等. 基于卷积神经网络的光学遥感影像道路提取方法研究进展[J]. 吉林大学学报(地球科学版), 2024, 54(3): 1068-1080.

[6] Lin Yuzhun, Liu Zhi, Wang Shuxiang, et al. Research Progress of Road Extraction Method for Optical Remote Sensing Images Based on Convolutional Neural Network[J]. Journal of Jilin University (Earth Science Edition), 2024, 54(3): 1068-1080.

[7] 刘霞, 孙英杰. 基于融合残差注意力机制的卷积神经网络地震信号去噪[J]. 吉林大学学报(地球科学版), 2023, 53(2): 609-621.

[8] Liu Xia, Sun Yingjie. Seismic Signal Denoising Based on Convolutional Neural Network with Residual and Attention Mechanism[J]. Journal of Jilin University (Earth Science Edition), 2023, 53(2): 609-621.

[9] Mirjalili S, Lewis A. The Whale Optimization Algorithm[J]. Advances in Engineering Software, 2016, 95: 51-67.

[10] Nadimi-Shahraki M H, Zamani H, Asghari Varzaneh Z, et al. A Systematic Review of the Whale Optimization Algorithm: Theoretical Foundation, Improvements, and Hybridizations[J]. Archives of Computational Methods in Engineering, 2023, 30(7): 4113-4159.

[11] Zhang K, Zuo W, Zhang L. FFDNet: Toward a Fast and Flexible Solution for CNN Based Image Denoising[J]. IEEE Transactions on Image Processing, 2018, 27(9): 4608-4622.

[12] Zhang K, Zuo W, Chen Y, et al. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising[J]. IEEE Transactions on Image Processing, 2017, 26(7): 3142-3155.

[13] Gharehchopogh F S, Gholizadeh H. A Comprehensive Survey: Whale Optimization Algorithm and Its Applications[J]. Swarm and Evolutionary Computation, 2019, 48: 1-24.

[14] Liu W, Ren Y, Meng X, et al. Analysis of Potential Water Inflow Rates at an Underground Coal Mine Using a WOA-CNN-SVM Approach[J]. Water, 2024, 16(6): 813.

[15] Song X. Current Research Status and Important Issues of Magmatic Sulfide Deposits[J]. Mineral Deposits, 2019, 38(4): 699-710.

[16] 宋谢炎, 康健, 隆廷茂, 等. 甘肃金川超大型Ni-Cu-PGE硫化物矿床岩浆通道分枝构造及其深部找矿意义[J]. 地球科学与环境学报, 2023, 45(5): 1049-1062.

[17] Song Xieyan, Kang Jian, Long Tingmao, et al. Bifurcate Magma Conduit of Jinchuan Super-Large Ni-Cu-PGE Sulfide Deposit in Gansu, China and Its Implications for Deep Ore Prospecting[J]. Journal of Earth Sciences and Environment, 2023, 45(5): 1049-1062.

[18] Zhang J, Zeng Z, Zhao X, et al. Deep Mineral Exploration of the Jinchuan Cu-Ni Sulfide Deposit Based on Aeromagnetic, Gravity, and CSAMT Methods[J]. Minerals, 2020, 10(2): 168.

[19] Long T M, Song X Y, Kang J, et al. Genesis of No.2 Orebody of the Jinchuan Magmatic Ni-Cu (PGE) Sulfide Deposit, NW China: New Constraints from the Newly Discovered Deep Extension[J]. Mineralium Deposita, 2023, 58(7): 1317-1332.

[20] Su S G, Tang Z L, Song X Y. Magmatic Conduit Metallogenesis of Jinchuan Ni-Cu Deposit Derived from High-Mg Basaltic Parent Magma[J]. Acta Petrologica Sinica, 2014, 30(11): 3120-3130.

[21] 闫海卿, 王强, 胡彦强, 等. 金川铜镍硫化物岩浆矿床前锋岩浆与岩浆通道[J]. 中国地质, 2013, 40(3): 806-819.

[22] Yan Haiqing, Wang Qiang, Hu Yanqiang, et al. Striker Magma and Magma Channel in the Jinchuan Copper-Nickel Sulfide Magmatic Deposit[J]. Geology in China, 2013, 40(3): 806-819.

[23] Kang J, Song X Y, Long T M, et al. Lithologic and Geochemical Constraints on the Genesis of a Newly Discovered Orebody in the Jinchuan Intrusion, NW China[J]. Economic Geology, 2022, 117(8): 1809-1825.

[24] Jiao J, Rui H, Duan J. Genesis of the Main Types of Sulphide Ore in the Jinchuan Ni-Cu-PGE Deposit, NW China: Constraints from Texture and Mineral Chemistry of Pyrrhotite[J]. Geological Journal, 2018, 53(S1): 147-158.

[25] Li C, Xu Z, de Waal S A, et al. Compositional Variations of Olivine from the Jinchuan Ni-Cu Sulfide Deposit, Western China: Implications for Ore Genesis[J]. Mineralium Deposita, 2004, 39(2): 159-172.

[26] 文美兰, 罗先熔. 金川铜镍矿床多元地学信息找矿研究[J]. 中国地质, 2013, 40(2): 594-601.

[27] Wen Meilan, Luo Xianrong. A Study of the Ore-Prospecting Work Based on Multiple Geosciences Information in the Jinchuan Cu-Ni Deposit[J]. Geology in China, 2013, 40(2): 594-601.

[28] Porter T M. Regional Tectonics, Geology, Magma Chamber Processes and Mineralisation of the Jinchuan Nickel-Copper-PGE Deposit, Gansu Province, China: A Review[J]. Geoscience Frontiers, 2016, 7(3): 431-451.

[29] Zhang M, Liu M, Feng T, et al. LOC-FLOW: An End-to-End Machine Learning-Based High-Precision Earthquake Location Workflow[J]. Seismological Research Letters, 2022, 93(5): 2426-2438.

[30] 张宇, 冯晅, 恩和得力海, 等. 金川矿区及周边地球物理特征和背景噪声成像的应用[J]. 世界地质, 2021, 40(2): 419-427.

[31] Zhang Yu, Feng Xuan, Enhedelihai, et al. Geophysical Characteristics and Application of Ambient Noise Tomography in Jinchuan Mining Area and Surroundings[J]. Global Geology, 2021, 40(2): 419-427.

[32] Zhu W, Beroza G C. PhaseNet: A Deep-Neural-Network-Based Seismic Arrival-Time Picking Method[J]. Geophysical Journal International, 2018, 216(1): 261-273.

[33] Zhang M, Ellsworth W L, Beroza G C. Rapid Earthquake Association and Location[J]. Seismological Research Letters, 2019, 90(6): 2276-2284.

[34] Klein F W. User’s Guide to HYPOINVERSE-2000: A Fortran Program to Solve for Earthquake Locations and Magnitudes[R/OL]. https://pubs.usgs.gov/publication/ofr02171.

[35] Geiger L. Probability Method for the Determination of Earthquake Epicentres from the Arrival Time Only[J]. Bull St Louis Univ, 1912, 8: 60.

[36] Waldhauser F, Ellsworth W L. A Double-Difference Earthquake Location Algorithm: Method and Application to the Northern Hayward Fault, California[J]. Bulletin of the Seismological Society of America, 2000, 90(6): 1353-1368.

[37] Toomey D R, Foulger G R. Tomographic Inversion of Local Earthquake Data from the Hengill-Grensdalur Central Volcano Complex, Iceland[J]. Journal of Geophysical Research: Solid Earth, 1989, 94(B12): 17497-17510.

[38] 王睿, 陈列锰, 宋谢炎. 甘肃金川超基性岩体原始产状的恢复[J]. 矿物学报, 2015, 35(增刊1): 1040-1041.

[39] Wang Rui, Chen Liemeng, Song Xieyan. The Restoration of the Original Occurrence of the Jinchuan Ultramafic Rock Mass in Gansu Province[J]. Acta Mineralogica Sinica, 2015, 35(Sup.1): 1040-1041.

[40] Song X, Danyushevsky L V, Keays R R, et al. Structural, Lithological, and Geochemical Constraints on the Dynamic Magma Plumbing System of the Jinchuan Ni-Cu Sulfide Deposit, NW China[J]. Mineralium Deposita, 2012, 47(3): 277-297.

[41] Chen L M, Song X Y, Danyushevsky L V, et al. A Laser Ablation ICP-MS Study of Platinum-Group and Chalcophile Elements in Base Metal Sulfide Minerals of the Jinchuan Ni-Cu Sulfide Deposit, NW China[J]. Ore Geology Reviews, 2015, 65: 955-967.

[42] De Waal S A, Xu Z, Li C, et al. Emplacement of Viscous Mushes in the Jinchuan Ultramafic Intrusion, Western China[J]. The Canadian Mineralogist, 2004, 42(2): 371-392.

基金资助

国家重点研发计划(2022YFC3003402)