基于机器学习的埃达克质岩构造背景判别研究

张焕宝, 贺海洋, 杨仕教, 李亚林, 毕文军, 韩世礼, 郭钦鹏, 杜青

PDF(5256 KB)
中国高校科技期刊信息汇聚平台
PDF(5256 KB)
地学前缘 ›› 2024, Vol. 31 ›› Issue (4) : 417-428. DOI: 10.13745/j.esf.sf.2023.9.2
非主题来稿选登：人工智能与地质应用

基于机器学习的埃达克质岩构造背景判别研究

作者信息 +

Machine learning-based approach for adakitic rocks tectonic setting determination

Author information +
History +

摘要

埃达克质岩具有重要的地球动力学和金属成矿意义,其构造背景的准确识别为探讨区域构造-岩浆演化过程提供了重要依据。由于埃达克质岩源区、热源和岩浆产生机制的多样性,传统低维度地球化学手段在识别构造背景时存在局限性。随着地学数据的指数增长和人工智能的发展,机器学习为解决该问题提供了新方法。因此,本文将机器学习与地质大数据相结合,构建高精度埃达克质岩构造背景判别模型和可视化图解。文中收集了1 075条全球埃达克质岩主、微量地球化学数据,使用主成分分析和t分布-随机近邻嵌入等无监督学习方法进行高维数据降维,采用随机森林、支持向量机、人工神经网络和K近邻等机器学习方法进行数据训练,得出准确率为98.5%的高斯核支持向量机埃达克质岩构造背景判别器,并提出Ba-Sr/Nd图解,为汇聚板块边缘、板内火山活动和太古宙克拉通(包括绿岩带)3种构造背景判别提供依据。这项工作将拓展机器学习在埃达克质岩构造背景研究中的应用,为构造-岩浆作用研究带来新的思路。

Abstract

Adakitic rocks hold significant geodynamic and metallogenic implications, and accurately determining their tectonic setting is crucial for understanding regional tectonic-magmatic evolution. However, due to the diverse sources, heat regimes, and magma generation mechanisms of adakitic rocks, conventional low-dimensional geochemical methods face limitations in tectonic setting identification. With the exponential growth of geoscience data and advancements in artificial intelligence, machine learning offers a novel approach to address this challenge. In this study, we integrate machine learning with geological big data to develop a high-precision adakitic tectonic setting discrimination model and visual representation. We compiled major and trace elements geochemical data from 1075 adakitic rocks worldwide and employed unsupervised learning techniques such as principal component analysis and t-distributed stochastic neighbor embedding for high-dimensional data reduction. Various machine learning algorithms including random forest, support vector machine, artificial neural network, and K-nearest neighbor were trained. Consequently, we established a Gaussian kernel support vector machine adakitic rock tectonic setting discriminator with 98.5% accuracy and proposed a Ba versus Sr/Nd diagram to delineate three tectonic settings: convergent margin, intraplate volcanism, and Archean craton (comprising greenstone belts). This study broadens the application of machine learning in adakitic rock tectonic setting analysis, offering fresh insights into tectonic-magmatic processes investigation.

关键词

埃达克质岩 / 构造背景 / 判别图解 / 主、微量元素 / 大数据分析 / 机器学习

Key words

adakitic rock / tectonic setting / discrimination model / major and trace elements / big data analysis / machine learning

中图分类号

P588.122;P588.121;P544;TP18

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
张焕宝 , 贺海洋 , 杨仕教 , 等. 基于机器学习的埃达克质岩构造背景判别研究. 地学前缘. 2024, 31(4): 417-428 https://doi.org/10.13745/j.esf.sf.2023.9.2
Huanbao ZHANG, Haiyang HE, Shijiao YANG, et al. Machine learning-based approach for adakitic rocks tectonic setting determination[J]. Earth Science Frontiers. 2024, 31(4): 417-428 https://doi.org/10.13745/j.esf.sf.2023.9.2

参考文献

列表( 原文顺序 | 文献年度倒序 | 文中引用次数倒序 ) 可视化分析
[1]
DEFANT M J, DRUMMOND M S. Derivation of some modern arc magmas by melting of young subducted lithosphere[J]. Nature, 1990, 347(6294): 662-665.
本文引用 [1]
[2]
HOU Z Q, ZHENG Y C, ZENG L S, et al. Eocene-Oligocene granitoids in southern Tibet: constraints on crustal anatexis and tectonic evolution of the Himalayan Orogen[J]. Earth and Planetary Science Letters, 2012, 349: 38-52.
本文引用 [1]
[3]
LAI S C, QIN J F, LI Y F, et al. Cenozoic volcanic rocks in the Belog Co area, Qiangtang, northern Tibet, China: petrochemical evidence for partial melting of the mantle-crust transition zone[J]. Chinese Journal of Geochemistry, 2007, 26(3): 305-311.
本文引用 [1]
[4]
XU J F, SHINJO R, DEFANT M J, et al. Origin of Mesozoic adakitic intrusive rocks in the Ningzhen area of East China: partial melting of delaminated lower continental crust?[J]. Geology, 2002, 30(12): 1111.
本文引用 [1]
[5]
王强, 郝露露, 张修政, 等. 汇聚板块边缘的埃达克质岩: 成分和成因[J]. 中国科学: 地球科学, 2020, 50(12): 1845-1873.
本文引用 [1]
[6]
CASTILLO P R. 埃达克岩成因回顾[J]. 科学通报, 2006, 51(6): 617-627.
本文引用 [1]
[7]
LE MAITRE R W. Igneous rocks, a classification and glossary of terms[M]. New York: Cambridge University Press, 2002: 1-254.
本文引用 [1]
[8]
孙立强, 凌洪飞, 赵葵东, 等. 华夏地块早白垩世埃达克质岩的岩石成因及地质意义[J]. 中国科学: 地球科学, 2017, 47(7): 783-803.
本文引用 [1]
[9]
ZHANG L Y, LI S C, ZHAO Q Y. A review of research on adakites[J]. International Geology Review, 2021, 63(1): 47-64.
本文引用 [1]
[10]
DOUCET L S, TETLEY M G, LI Z X, et al. Geochemical fingerprinting of continental and oceanic basalts: a machine learning approach[J]. Earth-Science Reviews, 2022, 233: 104192.
本文引用 [4]
[11]
CONDIE K C. Geochemistry and tectonic setting of early Proterozoic supracrustal rocks in the southwestern United States[J]. The Journal of Geology, 1986, 94(6): 845-864.
本文引用 [1]
[12]
HARRIS N B W, PEARCE J A, TINDLE A G. Geochemical characteristics of collision-zone magmatism[M]. London: Geological Society, 1986: 69-81.
本文引用 [1]
[13]
PEARCE J A, HARRIS N B W, TINDLE A G. Trace element discrimination diagrams for the tectonic interpretation of granitic rocks[J]. Journal of Petrology, 1984, 25(4): 956-983.
本文引用 [1]
[14]
PEARCE J A. Geochemical fingerprinting of oceanic basalts with applications to ophiolite classification and the search for Archean oceanic crust[J]. Lithos, 2008, 100(1/2/3/4): 14-48.
本文引用 [1]
[15]
WANG Q, XU J F, JIAN P, et al. Petrogenesis of adakitic porphyries in an extensional tectonic setting, Dexing, South China: implications for the genesis of porphyry copper mineralization[J]. Journal of Petrology, 2006, 47(1): 119-144.
本文引用 [1]
[16]
WOOD D A. The application of a Th-Hf-Ta diagram to problems of tectonomagmatic classification and to establishing the nature of crustal contamination of basaltic lavas of the British Tertiary Volcanic Province[J]. Earth and Planetary Science Letters, 1980, 50(1): 11-30.
本文引用 [1]
[17]
LI C S, ARNDT N T, TANG Q Y, et al. Trace element indiscrimination diagrams[J]. Lithos, 2015, 232: 76-83.
本文引用 [1]
[18]
成秋明. 什么是数学地球科学及其前沿领域?[J]. 地学前缘, 2021, 28(3): 6-25.
本文引用 [1]
[19]
周永章, 王俊, 左仁广, 等. 地质领域机器学习、 深度学习及实现语言[J]. 岩石学报, 2018, 34(11): 3173-3178.
本文引用 [2]
[20]
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.
本文引用 [1]
[21]
周永章, 张良均, 张奥多, 等. 地球科学大数据挖掘与机器学习[M]. 广州: 中山大学出版社, 2018.
本文引用 [5]
[22]
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.
本文引用 [1]
[23]
周永章, 左仁广, 刘刚, 等. 数学地球科学跨越发展的十年: 大数据、 人工智能算法正在改变地质学[J]. 矿物岩石地球化学通报, 2021, 40(3): 556-573, 777.
本文引用 [1]
[24]
肖立志. 机器学习数据驱动与机理模型融合及可解释性问题[J]. 石油物探, 2022, 61(2): 205-212.
本文引用 [1]
[25]
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.
本文引用 [1]
[26]
朱月琴, 谭永杰, 张建通, 等. 基于Hadoop的地质大数据融合与挖掘技术框架[J]. 测绘学报, 2015, 44(增刊1): 152-159.
本文引用 [1]
[27]
ZHAO Y, ZHANG Y G, GENG M, et al. Involvement of slab-derived fluid in the generation of Cenozoic basalts in Northeast China inferred from machine learning[J]. Geophysical Research Letters, 2019, 46(10): 5234-5242.
本文引用 [2]
[28]
焦守涛, 周永章, 张旗, 等. 基于GEOROC数据库的全球辉长岩大数据的大地构造环境智能判别研究[J]. 岩石学报, 2018, 34(11): 3189-3194.
本文引用 [3]
[29]
GUO P, YANG T, XU W L, et al. Machine learning reveals source compositions of intraplate basaltic rocks[J]. Geochemistry, Geophysics, Geosystems, 2021, 22(9): e2021GC009946.
本文引用 [1]
[30]
陈伟雄, 杨华健, 周泽东, 等. 地质矿物的地球化学数据可视化分析与构造背景预测[J]. 世界有色金属, 2019(14): 132-134.
本文引用 [1]
[31]
韩帅, 李明超, 任秋兵, 等. 基于大数据方法的玄武岩大地构造环境智能挖掘判别与分析[J]. 岩石学报, 2018, 34(11): 3207-3216.
本文引用 [1]
[32]
任秋兵, 李明超, 韩帅. 基于改进遗传算法-神经网络的玄武岩构造环境判别及对比实验[J]. 地学前缘, 2019, 26(4): 117-124.
本文引用 [1]
[33]
杜雪亮, 李玉琼, 杜君, 等. 全球大陆板内玄武岩数据挖掘[J]. 矿物岩石地球化学通报, 2017, 36(6): 905-911, 879.
本文引用 [1]
[34]
杨婧, 王金荣, 张旗, 等. 全球岛弧玄武岩数据挖掘: 在玄武岩判别图上的表现及初步解释[J]. 地质通报, 2016, 35(12): 1937-1949.
本文引用 [1]
[35]
ZHONG R C, DENG Y, YU C. Multi-layer perceptron-based tectonic discrimination of basaltic rocks and an application on the Paleoproterozoic Xiong’er volcanic province in the North China Craton[J]. Computers and Geosciences, 2021, 149: 104717.
本文引用 [1]
[36]
GELADI P, ISAKSSON H, LINDQVIST L, et al. Principal component analysis of multivariate images[J]. Chemometrics and Intelligent Laboratory Systems, 1989, 5(3): 209-220.
本文引用 [1]
[37]
WOLD S, GELADI P, ESBENSEN K, et al. Multi-way principal components and PLS-analysis[J]. Journal of Chemometrics, 1987, 1(1): 41-56.
本文引用 [1]
[38]
MAATEN L V D, HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(2): 2579-2605.
本文引用 [1]
[39]
BREIMAN L. Using iterated bagging to debias regressions[J]. Machine Learning, 2001, 45(3): 261-277.
本文引用 [2]
[40]
HSU C W, CHANG C C, LIN C J. A practical guide to support vector classification[J]. BJU International, 2003, 101(1): 1396-1400.
本文引用 [2]
[41]
KOHONEN T. An introduction to neural computing[J]. Neural Networks, 1988, 1(1): 3-16.
本文引用 [2]
[42]
ZHANG M L, ZHOU Z H. ML-KNN: a lazy learning approach to multi-label learning[J]. Pattern Recognition, 2007, 40(7): 2038-2048.
本文引用 [2]
[43]
葛粲, 汪方跃, 李永东, 等. 基于GEOROC大数据分析地壳厚度地球化学指标[J]. 岩石学报, 2018, 34(11): 3179-3188.
本文引用 [1]
[44]
熊佳杰, 李嘉诚, 徐柳林, 等. 基于GEOROC和PetDB全球岩石地球化学数据库的洋内岛弧和陆缘弧构造背景判别研究[J]. 四川地质学报, 2022, 42(2): 321-324.
本文引用 [1]
[45]
周皓. 吉南—辽东地区早白垩世火山岩成因: 来自地球化学和Sr-Nd-Pb同位素的制约[D]. 长春: 吉林大学, 2021.
本文引用 [1]
[46]
章家保, 金翔龙, 高金耀, 等. 断裂和白垩纪岩浆活动对中西太平洋海山区海山形成的影响[J]. 海洋地质与第四纪地质, 2006, 26(1): 67-74.
本文引用 [1]
[47]
ZOU S H, CHEN X L, XU D R, et al. A machine learning approach to tracking crustal thickness variations in the eastern North China Craton[J]. Geoscience Frontiers, 2021, 12(5): 101195.
本文引用 [1]
[48]
PETRELLI M, CARICCHI L, PERUGINI D. Machine learning thermo-barometry: application to clinopyroxene-bearing magmas[J]. Journal of Geophysical Research: Solid Earth, 2020, 125(9): e2020JB020130.
本文引用 [1]
[49]
DENG Y, ZHONG R C, LI D F, et al. Hunting the datable garnet using the LA-ICP-MS U-Pb method: predicting garnet U concentration, based on major and minor elements[J]. Acta Geologica Sinica (English Edition), 2022, 96(6): 2148-2157.
本文引用 [1]
[50]
ROSSITER H E, BOUDRIAS M H, WARD N S. Do movement-related beta oscillations change after stroke?[J]. Journal of Neurophysiology, 2014, 112(9): 2053-2058.
本文引用 [1]
[51]
ZHANG Z J, ZHOU Y Z, ZHANG P. Crucial geochemical signal identification for Cu-fertile magmas in paleo-Tethyan arc based on machine learning[J]. Mathematical Geosciences, 2023, 55(6): 799-828.
本文引用 [1]
[52]
ABDI H, WILLIAMS L J. Principal component analysis[J]. WIREs Computational Statistics, 2010, 2(4): 433-459.
本文引用 [1]
[53]
STRACKE A, WILLIG M, GENSKE F, et al. Chemical geodynamics insights from a machine learning approach[J]. Geochemistry, Geophysics, Geosystems, 2022, 23(10): e2022GC010606.
本文引用 [1]
[54]
LI X M, ZHANG Y X, LI Z K, et al. Discrimination of Pb-Zn deposit types using sphalerite geochemistry: new insights from machine learning algorithm[J]. Geoscience Frontiers, 2023, 14(4): 101580.
本文引用 [1]
[55]
HU B, ZENG L P, LIAO W, et al. The origin and discrimination of high-Ti magnetite in magmatic-hydrothermal systems: insight from machine learning analysis[J]. Economic Geology, 2022, 117(7): 1613-1627.
本文引用 [1]
[56]
朱紫怡, 周飞, 王瑀, 等. 基于机器学习的锆石成因分类研究[J]. 地学前缘, 2022, 29(5): 464-475.
本文引用 [1]
[57]
CRACKNELL M J, READING A M. Geological mapping using remote sensing data: a comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information[J]. Computers and Geosciences, 2014, 63: 22-33.
本文引用 [1]
[58]
RECANATI A, GROZAVU N, BENNANI Y, et al. Apatite (U-Th-Sm)/He date dispersion: first insights from machine learning algorithms[J]. Earth and Planetary Science Letters, 2021, 554: 116655.
本文引用 [1]
[59]
KUWATANI T, NAGATA K, OKADA M, et al. Machine-learning techniques for geochemical discrimination of 2011 Tohoku tsunami deposits[J]. Scientific Reports, 2014, 4: 7077.
本文引用 [1]
[60]
LI X Y, ZHANG C. Machine learning thermobarometry for biotite-bearing magmas[J]. Journal of Geophysical Research: Solid Earth, 2022, 127(9): e2022JB024137.
本文引用 [1]
[61]
PEDREGOSA F, VAROQUAUX G, GRAMFORT A, et al. Scikit-learn: machine learning in Python[J]. Journal of Machine Learning Research, 2011, 12: 2825-2830.
本文引用 [1]
[62]
HASTIE T, TIBSHIRANI R, FRIEDMAN J. The elements of statistical learning: data mining, inference, and prediction[M]. New York: Springer, 2001.
本文引用 [2]
[63]
SOKOLOVA M, LAPALME G. A systematic analysis of performance measures for classification tasks[J]. Information Processing and Management, 2009, 45(4): 427-437.
本文引用 [1]
[64]
UEKI K, HINO H, KUWATANI T. Geochemical discrimination and characteristics of magmatic tectonic settings: a machine-learning-based approach[J]. Geochemistry, Geophysics, Geosystems, 2018, 19(4): 1327-1347.
本文引用 [1]
[65]
ZHONG R C, DENG Y, LI W B, et al. Revealing the multi-stage ore-forming history of a mineral deposit using pyrite geochemistry and machine learning-based data interpretation[J]. Ore Geology Reviews, 2021, 133: 104079.
本文引用 [1]
[66]
PETRELLI M, PERUGINI D. Solving petrological problems through machine learning: the study case of tectonic discrimination using geochemical and isotopic data[J]. Contributions to Mineralogy and Petrology, 2016, 171(10): 81.
本文引用 [1]
[67]
王瑀, 邱昆峰, 侯照亮, 等. 石英Ti/Ge-P: 基于机器学习的矿床类型判别新图解[J]. 岩石学报, 2022, 38(1): 281-290.
本文引用 [1]
[68]
WANG Y, QIU K F, MÜLLER A, et al. Machine learning prediction of quartz forming-environments[J]. Journal of Geophysical Research: Solid Earth, 2021, 126(8): e2021JB021925.
本文引用 [1]
[69]
郭鹏. 机器学习揭示玄武岩构造背景与源区性质[J]. 矿物岩石地球化学通报, 2023, 42(1): 26-33, 6.
本文引用 [1]
[70]
ROUSSEEUW P J. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis[J]. Journal of Computational and Applied Mathematics, 1987, 20: 53-65.
本文引用 [2]
[71]
周统, 邱昆峰, 王瑀, 等. 磷灰石Eu/Y-Ce: 基于大数据的源区类型判别新图解[J]. 岩石学报, 2022, 38(1): 291-299.
本文引用 [1]
[72]
ROBERT C. Machine learning, a probabilistic perspective[J]. Chance, 2014, 27(2): 62-63.
本文引用 [1]

基金

湖南省自然科学基金面上项目(2023JJ30507)
湖南省自然科学基金面上项目(2023JJ30506)
山西省自然科学基金青年项目(202103021223120)
湖南省教育厅科学研究项目(22B0433)

评论

PDF(5256 KB)

Accesses

Citation

Detail
段落导航
相关文章
Copyright 中国高校科技期刊信息汇聚平台 2024-2025
技术支持：北京玛格泰克科技发展有限公司
京ICP备05021913号-19

/

〈 〉