Experimental research on big data-based intelligent exploration models and advance

doi:10.13745/j.esf.sf.2024.9.10

Abstract

Abstract:

This paper presents a comprehensive summary of exploratory experimental research conducted by the ‘Industry-college-institute Cooperation’ technology innovation talent team in Guizhou Province, focusing on a novel intelligent exploration model leveraging big data. Utilizing a collaborative innovation system integrating industry-college-institute cooperation, the team undertook a retrospective analysis of mineral exploration processes employing big data for the famous ‘Datangpo’ manganese ore concentration area in China, as well as several concealed giant manganese deposits. Their research aimed to explore intelligent predictive methodologies and digital exploration techniques for deep-seated mineral resources, with the goal of cultivating and developing new quality productivity in the field of geological and mineral exploration. The team developed a big data-based metallogenic schema and exploration model, established a comprehensive geological big data resource system. They refined and widely promoted digital exploration technologies system, created a province-wide three-dimensional glass earth in Guizhou Province, and developed multi-scale, multi-objective progressive mineral prediction techniques. These efforts have significantly accelerated the digital transformation of geological and mineral exploration in Guizhou Province. Their efforts led to the discovery of multiple concealed exploration targets, including manganese, phosphate, bauxite, lead-zinc (germanium), barite, and newly identified altered limestone-type lithium deposits, contributing to significant advancements in Guizhou new round of prospecting breakthrough strategic action. The key outcomes indicate that the team’s research not only accelerates the digital transformation of geological mineral exploration but also fosters a deep integration with big data, cultivating and developing new quality productivity in the field of geological and mineral exploration and supporting breakthroughs in the exploration of concealed minerals. To further advance this digital transformation and develop a digital economy in geology, it is crucial to continue initiatives aimed at enhancing ‘Data cloud service, Deep integration of big data, and Enterprise intelligent transformation’ in exploration, strengthen the key technology research and development, and vigorously promote these applications, while continuously exploring, improving, and developing in practice.

Key words: intelligent exploration, digital exploration, Glass Earth in Guizhou Province, Data Resource System, intelligent prediction

CLC Number:

ZHOU Qi, WU Chonglong. Experimental research on big data-based intelligent exploration models and advance[J]. Earth Science Frontiers, 2024, 31(6): 350-367.

Figures/Tables 16

Fig.1 Conceptual model and overall application framework of digital transformation of geological and mineral exploration in Guizhou Province

Fig.2 Technical method and application model laminated composite structure. Modified after [2].

Fig.3 Formation of data link and information loop in geological exploration. Modified after [7-8].

Fig.4 Geological big data scheduling management method system and overall framework

Fig.5 The overall framework of the geological cloud platform of Guizhou Bureau of Geology and Mineral Resources and its geological prospecting unit

Fig.6 The working mode of Guizhou digital exploration system

Fig.7 A 3D visualized structure-attribute integrated geological model of some deposits in Guizhou Province

Fig.8 Technical route and work flow of multi-scale provincial glass earth in Guizhou Province

Fig.9 Multi-scale three-dimensional structure-stratigraphic framework model in Guizhou Province

Fig.10 The spatial characteristics of ground temperature field are visualized based on 1∶500000 structure-attribute integrated 3D model

Fig.11 The logical process from ore-forming geological anomaly (metallogenic conditions) to ore-indicating geological anomaly (ore-controlling factors)

Fig.12 Logical relationship model of multi-scale and multi-objective progressive mineral resource prediction. Modified after [40].

Fig.13 Excavation of regional metallogenic tectonic background conditions without model from geological,geophysical, geochemical and remote sensing data (1P problem).

Fig.14 The spatial distribution of the early basement rift and manganese deposit intersecting Wuling secondary rift in NW direction discovered by 3D modeling. Modified after [44].

Fig.15 Two sets of linear body clusters extracted from aeromagnetic ΔT anomalies extending up 10 km. Modified after [44].

Fig.16 Prediction of favorable areas (3P) of manganese ore concentration in Northeast Guizhou (top) and gold deposit concentration in southwest Guizhou (bottom) based on multi-spectral remote sensing information

References 50

[1]	周琦, 袁良军, 吴冲龙, 等. 贵州新元古代锰、重晶石等矿床成矿系列及找矿突破[J]. 地球学报, 2023, 44(5): 943-954.
[2]	吴冲龙, 刘刚, 田宜平, 等. 地矿勘查工作信息化的理论与方法问题[J]. 地球科学: 中国地质大学学报, 2005, 30(3): 359-365.
[3]	吴冲龙, 刘刚, 田宜平, 等. 论地质信息科学[J]. 地质科技情报, 2005, 24(3): 1-8.
[4]	吴冲龙, 刘刚, 田宜平, 等. 地质信息科学与技术概论[M]. 北京: 科学出版社, 2014.
[5]	吴冲龙, 刘刚, 周琦, 等. 地质科学大数据统合应用的基本问题[J]. 地质科技通报, 2020, 39(4): 1-11.
[6]	吴冲龙, 张夏林, 周琦, 等. 数字勘查与地质矿产勘查行业数字化转型[J]. 贵州地质, 2021, 38(2): 119-128.
[7]	吴冲龙, 张夏林, 李章林, 等. 固体矿产勘查信息系统[M]. 北京: 科学出版社, 2019.
[8]	吴冲龙, 刘刚, 张夏林, 等. 地质科学大数据及其利用的若干问题探讨[J]. 科学通报, 2016, 61(16): 1797-1807.
[9]	WALKER C. Personal data lake with data gravity pull[C]//2015 IEEE Fifth International Conference on Big Data and Cloud Computing (BdCloud 2015):Dalian Ch. Piscataway, N.J. : IEEE Computer Society, 2015, 160-173.
[10]	MUNSHI A A, MOHAMED Y A R I. Data lake lambda architecture for smart grids big data analytics[J]. IEEE Access, 2018, 6: 40463-40471.
[11]	孙卡. 海量地质空间数据的动态调度技术研究[D]. 武汉: 中国地质大学(武汉), 2010.
[12]	彭诗杰. 基于微服务体系结构和面向多地质主题的数据云服务关键技术研究[D]. 武汉: 中国地质大学(武汉), 2017.
[13]	何文娜, 王永志. 地质云计算原型系统[J]. 地球物理学进展, 2014, 29(6): 2886-2896.
[14]	陈建平, 李婧, 崔宁, 等. 大数据背景下地质云的构建与应用[J]. 地质通报, 2015, 34(7): 1260-1265.
[15]	谭永杰. 地质大数据与信息服务工程技术框架[J]. 地理信息世界, 2016, 23(1): 1-9.
[16]	谭永杰. 地质大数据体系建设的总体框架研究[J]. 中国地质调查, 2016, 3(3): 1-6.
[17]	陈根深, 刘军旗, 何忆, 等. 基于World Wind移动端的地质数据野外采集系统[J]. 计算机系统应用, 2019, 28(4): 96-104.
[18]	张夏林, 师志龙, 吴冲龙, 等. 基于移动设备的野外地质大数据智能采集和可视化技术[J]. 地质科技通报, 2020, 39(4): 21-28.
[19]	李章林, 吴冲龙, 张夏林, 等. 基于三维块体模型的矿体动态构模方法[J]. 矿业研究与开发, 2011, 31(1): 60-63.
[20]	李章林, 吴冲龙, 张夏林, 等. 地质科学大数据背景下的矿体动态建模方法探讨[J]. 地质科技通报, 2020, 39(4): 59-68.
[21]	张夏林, 吴冲龙, 周琦, 等. 基于勘查大数据和数据集市的锰矿床三维地质建模[J]. 地质科技通报, 2020, 39(4): 12-20.
[22]	HE Z W, WU C L, TIAN Y P, et al. Three-dimensional reconstruction of geological solids based on section topology reasoning[J]. Geo-spatial Information Science, 2008, 11(3): 201-208.
[23]	何珍文, 吴冲龙, 刘刚, 等. 地质空间认知与多维动态建模结构研究[J]. 地质科技情报, 2012, 31(6): 46-51.
[24]	田宜平, 吴冲龙, 翁正平, 等. 地质大数据可视化关键技术探讨[J]. 地质科技通报, 2020, 39(4): 29-36.
[25]	陈麒玉. 基于多点地质统计学的三维地质体随机建模方法研究: 以闽江口地区第四纪沉积体系建模为例[D]. 武汉: 中国地质大学, 2018.
[26]	HAN J W, KAMBER M, PEI J. Data mining: concepts and techniques[M]. 3rd ed. Amsterdam: Elsevier/Morgan Kaufmann, 2012.
[27]	陈国旭, 吴冲龙, 张夏林, 等. 支持多金属的矿产资源储量估算方法研究[J]. 中国矿业, 2009, 18(4): 99-101.
[28]	李章林, 王平, 李冬梅. 实验变差函数计算方法的研究与运用[J]. 国土资源信息化, 2008(2): 10-14.
[29]	李章林, 张夏林, 翁正平. 指示克里格法在矿体储量计算方面的研究与应用[J]. 矿业快报, 2008, 24(1): 11-15.
[30]	CARR G R, ANDREW A S, DENTON G J, et al. The “Glass Earth”: Geochemical frontiers in exploration through cover[J]. Australian Institute of Geoscientists Bulletin, 1999, 28: 33-40.
[31]	吴冲龙, 翁正平, 刘刚, 等. 论中国“玻璃国土” 建设[J]. 地质科技情报, 2012, 31(6): 1-8.
[32]	吴冲龙, 何珍文, 翁正平, 等. 地质数据三维可视化的属性、分类和关键技术[J]. 地质通报, 2011, 30(5): 642-649.
[33]	吴冲龙, 刘刚. “玻璃地球” 建设的现状、问题、趋势与对策[J]. 地质通报, 2015, 34(7): 1280-1287.
[34]	唐丙寅, 吴冲龙, 李新川. 一种基于TIN-CPG混合空间数据模型的精细三维地质模型构建方法[J]. 岩土力学, 2017, 38(4): 1218-1225.
[35]	MAYER-SCHÖNBERGER V, CUKIER K. Big data: a revolution that will transform how we live, work, and think[M]. Boston: Houghton Mifflin Harcourt, 2013.
[36]	吴冲龙, 周琦, 徐凯, 等. 用于大数据预测的大塘坡式锰矿找矿过程复盘研究[J]. 贵州地质, 2022, 39(3): 189-204.
[37]	徐凯, 袁良军, 杨炳南, 等. 黔东北伴生—次生矿物遥感数据组合式挖掘与隐伏锰矿信息提取[J]. 地质科技通报, 2020, 39(4): 37-43.
[38]	XU K, WANG X F, KONG C F, et al. Identification of hydrothermal alteration minerals for exploring gold deposits based on SVM and PCA using ASTER data: a case study of gulong[J]. Remote Sensing, 2019, 11(24): 3003.
[39]	XU K, ZHAO S Y, WU C L, et al. Manganese mineral prospectivity based on deep convolutional neural networks in Songtao of northeastern Guizhou[J]. Earth Science Informatics, 2024, 17(2): 1681-1697.
[40]	赵鹏大. “三联式”资源定量预测与评价: 数字找矿理论与实践探讨[J]. 地球科学: 中国地质大学学报, 2002, 27(5): 482-489.
[41]	赵鹏大. 大数据时代呼唤各科学领域的数据科学[J]. 中国科技奖励, 2014(9): 29-30.
[42]	陈毓川. 当代矿产资源勘查评价的理论与方法[M]. 北京: 地震出版社, 1999.
[43]	黄智龙, 陈进, 刘丛强, 等. 峨眉山玄武岩与铅锌矿床成矿关系初探: 以云南会泽铅锌矿床为例[J]. 矿物学报, 2001, 21(4): 681-688.
[44]	ZHOU Q, WU C L, HU X Y, et al. A new metallogenic model for the giant manganese deposits in northeastern Guizhou, China[J]. Ore Geology Reviews, 2022, 149: 105070.
[45]	周琦, 杜远生, 袁良军, 等. 黔湘渝毗邻区南华纪武陵裂谷盆地结构及其对锰矿的控制作用[J]. 地球科学, 2016, 41(2): 177-188.
[46]	朱介寿, 蔡学林, 曹家敏, 等. 中国华南及东海地区岩石圈三维结构及演化[M]. 北京: 地质出版社, 2005.
[47]	邸凯昌, 李德毅, 李德仁. 云理论及其在空间数据发掘和知识发现中的应用[J]. 中国图象图形学报, 1999, 4(11): 32-37.
[48]	李德仁, 王树良, 李德毅. 空间数据挖掘理论与应用[M]. 2版. 北京: 科学出版社, 2013.
[49]	SCHMIDHUBER J. Deep learning in neural networks: an overview[J]. Neural Networks, 2015, 61: 85-117. PMID
[50]	SILVA A A, LIMA NETO I A, MISSÁGIA R M, et al. Artificial neural networks to support petrographic classification of carbonate-siliciclastic rocks using well logs and textural information[J]. Journal of Applied Geophysics, 2015, 117: 118-125.