基于高斯混合聚类的综合物探方法及其在岩溶勘探中的应用

doi:10.16183/j.cnki.jsjtu.2023.020

摘要/Abstract

摘要：

综合物探是一种有效的岩溶勘探技术,但其预测结果中存在人为影响大、溶洞边界模糊等缺点.首先,基于机器学习技术,采用高斯混合模型,分别对高密度电法和面波法勘探数据做分类处理;然后,提出Category-boundary算法,进一步细分上述分类得到的边界,提高高斯混合模型分类精度;最后,根据专家经验与地勘资料制定分类融合规则,在勘察数据驱动和工程地质知识引导的有机结合下,形成一套综合物探的高精度分类融合新方法.将新方法应用于浙南某岩溶勘探工程,获得了边界清晰的溶洞探测结果,与实际钻孔信息对比高度吻合,验证了新方法的有效性.

关键词: 综合物探技术, 高斯混合聚类, 分类融合, 岩溶勘探, 机器学习

Abstract:

Comprehensive geophysical prospection is an effective technique for karst exploration, but its prediction results usually suffer from significant artificial influence and fuzzy boundaries of karst caves. Based on the machine learning technology, a Gaussian mixture model is used to classify the exploration data of high-density electrical method and data of surface wave method respectively. Then, a Category-boundary algorithm is proposed to further subdivide the classification results, which improves the accuracy of Gaussian mixture model classification. Finally, the classification fusion rules are formulated based on expert experience and geological exploration data. Under the organic combination of survey data-driven and engineering geological knowledge guidance, a new set of high-precision classification and fusion methods is proposed for comprehensive geophysical exploration. By applying this new method to the karst exploration project in southern Zhejiang, a karst cave prediction is made with clearer boundaries. Compared with the actual drilling information, cave prediction and drilling information are highly consistent, which verifies the effectiveness of the method proposed.

Key words: comprehensive geophysical prospection, Gaussian mixture clustering, classification fusion, karst exploration, machine learning

中图分类号:

TU42

何文, 高斌, 王强强, 冯少孔, 叶冠林. 基于高斯混合聚类的综合物探方法及其在岩溶勘探中的应用[J]. 上海交通大学学报, 2024, 58(11): 1724-1734.

HE Wen, GAO Bin, WANG Qiangqiang, FENG Shaokong, YE Guanlin. A Comprehensive Geophysical Prospection Method Based on Gaussian Mixture Clustering and its Application in Karst Exploration[J]. Journal of Shanghai Jiao Tong University, 2024, 58(11): 1724-1734.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

表1

图12

图13

参考文献 30

[1]	FORD D, WILLIAMS P W. Karst hydrogeology and geomorphology[M]. Chichester, England: John Wiley & Sons, 2007.
[2]	黄毓铭, 张晓峰, 谢尚平, 等. 综合物探方法在南宁地铁溶洞探测中的应用[J]. 地球物理学进展, 2017, 32(3): 1352-1359.
	HUANG Yuming, ZHANG Xiaofeng, XIE Shangping, et al. Application of integrated geophysical method to Karst cave exploration of metro engineering in Nanning[J]. Progress in Geophysics, 2017, 32(3): 1352-1359.
[3]	雷旭友, 李正文, 折京平. 超高密度电阻率法在土洞、煤窑采空区和岩溶勘探中应用研究[J]. 地球物理学进展, 2009, 24(1): 340-347.
	LEI Xuyou, LI Zhengwen, ZHE Jingping. Applications and research of the high resolution resistivity method in explovation of caves, mined regions and Karst region[J]. Progress in Geophysics, 2009, 24(1): 340-347.
[4]	何禹, 李永涛, 朱亚军. 钻孔电磁波CT技术在深部岩溶勘探中的应用[J]. 工程地球物理学报, 2010, 7(4): 451-455.
	HE Yu, LI Yongtao, ZHU Yajun. Application of drilling electromagnetic CT to deep cavern and fracture prospecting[J]. Chinese Journal of Engineering Geophysics, 2010, 7(4): 451-455.
[5]	柴明锐, 程丹, 张昌民, 等. 机器学习方法对砂砾岩岩屑成分的预测: 以西北缘X723井百口泉组为例[J]. 西安石油大学学报(自然科学版), 2017, 32(5): 22-28.
	CHAI Mingrui, CHENG Dan, ZHANG Changmin, et al. Prediction of debris composition in glutenite by machine learning method: A case study in baikouquan formation of well X723 in the NW margin of Junggar Basin[J]. Journal of Xi’an Shiyou University (Natural Science Edition), 2017, 32(5): 22-28.
[6]	LIU M Y, YANG J, ZHENG W, et al. Using novel complex-efficient FastICA blind deconvolution method for urban water pipe leak localization in the presence of branch noise[J]. Journal of Water Resources Planning and Management, 2021, 147(10): 04021072.
[7]	干磊, 何东博, 郭建林, 等. 机器学习方法在储层分类中的应用[J]. 数学的实践与认识, 2019, 49(13): 138-144.
	GAN Lei, HE Dongbo, GUO Jianlin, et al. Application of machine learning method in reservoir classification[J]. Mathematics in Practice and Theory, 2019, 49(13): 138-144.
[8]	CHOU J S, TSAI C F, PHAM A D, et al. Machine learning in concrete strength simulations: Multi-nation data analytics[J]. Construction and Building Materials, 2014, 73: 771-780.
[9]	GUI G Q, PAN H, LIN Z B, et al. Data-driven support vector machine with optimization techniques for structural health monitoring and damage detection[J]. KSCE Journal of Civil Engineering, 2017, 21(2): 523-534.
[10]	AZIMI M, ESLAMLOU A D, PEKCAN G. Data-driven structural health monitoring and damage detection through deep learning: State-of-the-art review[J]. Sensors (Basel, Switzerland), 2020, 20(10): 2778.
[11]	PATHIRAGE C S N, LI J, LI L, et al. Structural damage identification based on autoencoder neural networks and deep learning[J]. Engineering Structures, 2018, 172: 13-28.
[12]	周永章, 陈烁, 张旗, 等. 大数据与数学地球科学研究进展: 大数据与数学地球科学专题代序[J]. 岩石学报, 2018, 34(2): 255-263.
	ZHOU Yongzhang, CHEN Shuo, ZHANG Qi, et al. Advances and prospects of big data and mathematical geoscience[J]. Acta Petrologica Sinica, 2018, 34(2): 255-263.
[13]	KUANG L C, LIU H, REN Y L, et al. Application and development trend of artificial intelligence in petroleum exploration and development[J]. Petroleum Exploration and Development, 2021, 48(1): 1-14.
[14]	KUBOTA L, REINERT D. Machine learning forecasts oil rate in mature onshore field jointly driven by water and steam injection[C]//SPE Annual Technical Conference and Exhibition. Calgary, Alberta, Canada: SPE, 2019: D021S020R003.
[15]	SHAHKARAMI A, MOHAGHEGH S. Applications of smart proxies for subsurface modeling[J]. Petroleum Exploration and Development, 2020, 47(2): 400-412.
[16]	ARTUN E, KULGA B. Selection of candidate wells for re-fracturing in tight gas sand reservoirs using fuzzy inference[J]. Petroleum Exploration and Development, 2020, 47(2): 413-420.
[17]	李希元, 崔健, 胡望水, 等. 基于多源地球物理数据的机器学习方法在地质体分类中的应用: 以黑龙江多宝山矿集区为例[J]. 地球物理学报, 2022, 65(9): 3634-3649.
	LI Xiyuan, CUI Jian, HU Wangshui, et al. Application of machine learning method based on multi-source geophysical data to geological body classification—A case study of Duobaoshan ore concentration area (Heilongjiang, China)[J]. Chinese Journal of Geophysics, 2022, 65(9): 3634-3649.
[18]	ABUBAKAR A. Machine learning for geoscience applications[C]//81st EAGE Conference and Exhibition 2019 Workshop Programme. London, UK: European Association of Geoscientists & Engineers, 2019: 1.
[19]	FOWLER J, STROBEL J. Scaling well log interpretation for faster results with AI[C]//First EAGE Digitalization Conference and Exhibition. Vienna, Austria: European Association of Geoscientists & Engineers, 2020: 1-5.
[20]	胡琪鑫, 徐亚. 地球物理信号特征识别与解释的机器学习方法及应用综述[J]. 地球物理学进展, 2022, 37(6): 2395-2407.
	HU Qixin, XU Ya. Review of machine learning and application of geophysical signal feature recognition and interpretation[J]. Progress in Geophysics, 2022, 37(6): 2395-2407.
[21]	FAHAD A, ALSHATRI N, TARI Z, et al. A survey of clustering algorithms for big data: Taxonomy and empirical analysis[J]. IEEE Transactions on Emerging Topics in Computing, 2014, 2(3): 267-279.
[22]	NGUYEN T T T, ARMITAGE G. A survey of techniques for Internet traffic classification using machine learning[J]. IEEE Communications Surveys & Tutorials, 2008, 10(4): 56-76.
[23]	KANUNGO T, MOUNT D M, NETANYAHU N S, et al. An efficient k-means clustering algorithm: Analysis and implementation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 881-892.
[24]	何清, 李宁, 罗文娟, 等. 大数据下的机器学习算法综述[J]. 模式识别与人工智能, 2014, 27(4): 327-336.
	HE Qing, LI Ning, LUO Wenjuan, et al. A survey of machine learning algorithms for big data[J]. Pattern Recognition and Artificial Intelligence, 2014, 27(4): 327-336.
[25]	王元卓, 靳小龙, 程学旗. 网络大数据: 现状与展望[J]. 计算机学报, 2013, 36(6): 1125-1138.
	WANG Yuanzhuo, JIN Xiaolong, CHENG Xueqi. Network big data: Present and future[J]. Chinese Journal of Computers, 2013, 36(6): 1125-1138.
[26]	王光宏, 蒋平. 数据挖掘综述[J]. 同济大学学报(自然科学版), 2004, 32(2): 246-252.
	WANG Guanghong, JIANG Ping. Survey of data mining[J]. Journal of Tongji University, 2004, 32(2): 246-252.
[27]	王千年, 车爱兰, 冯少孔, 等. 高密度面波法在堆石体结构密实度检测中的应用[J]. 上海交通大学学报, 2013, 47(10): 1574-1579.
	WANG Qiannian, CHE Ailan, FENG Shaokong, et al. Application of high-density Rayleigh-wave exploration to evaluaton of rockfill density[J]. Journal of Shanghai Jiao Tong University, 2013, 47(10): 1574-1579.
[28]	刘红帅, 郑桐, 齐文浩, 等. 常规土类剪切波速与埋深的关系分析[J]. 岩土工程学报, 2010, 32(7): 1142-1149.
	LIU Hongshuai, ZHENG Tong, QI Wenhao, et al. Relationship between shear wave velocity and depth of conventional soils[J]. Chinese Journal of Geotechnical Engineering, 2010, 32(7): 1142-1149.
[29]	高印立, 阎澍旺, 王金英. 剪切波速与土性指标间的统计关系[J]. 建筑科学, 1998, 14(5): 20-22.
	GAO Yinli, YAN Shuwang, WANG Jinying. The statistical relation of shear velocity with soil properties[J]. Building Science, 1998, 14(5): 20-22.
[30]	刘国华, 王振宇, 黄建平. 土的电阻率特性及其工程应用研究[J]. 岩土工程学报, 2004, 26(1): 83-87.
	LIU Guohua, WANG Zhenyu, HUANG Jianping. Research on electrical resistivity feature of soil and it’s application[J]. Chinese Journal of Geotechnical Engineering, 2004, 26(1): 83-87.

电法分类	面波法分类
电法分类	土层 v_s≤ 340 m/s	溶洞(h>5 m) 340<v_s≤455	岩层(h>5 m) v_s>455 m/s
土层 ρ≤75 Ω·m	砂土~黏土	杂填土	未知
溶洞(h>5 m) 75<ρ≤ 190	杂填土	溶洞	粗砾~砂砾
岩层(h>5 m) ρ>190 Ω·m	未知	粗砾~砂砾	基岩