基于卷积神经网络和火山岩大数据的构造源区判别
|
摘要
早先的构造源区判别图由于受时代、研究区域、研究思路以及研究手段、分析技术和样本数量的限制,存在某些不足,导致部分学者在研究中遇到各种困惑和矛盾。在大数据的冲击下,部分传统图解的可靠性正在接受考验。本文提出了一种将地球化学数据二维图像化的方法,将GEOROC数据库中来自11个构造环境的火山岩数据生成了34 468张灰度二维码图像。根据深度学习理论和方法构造了卷积神经网络(CNN)模型,利用其中75%的二维码数据进行自动学习和训练。该模型可以对不同来源的火山岩数据进行有效分类,总体分类准确度可达95%以上。该模型具备较好的泛化能力,可以作为日常工具辅助人工进行火山岩样本的构造源区的判别。
The traditional tectonic discrimination graphs have some shortcomings due to the limitation of available analytical methods and techniques of times.This has led to some confusions and contradictions for scholars using the graphs in their researches.Under the impact of big data,the reliability of some traditional tectonic discrimination graphs is being tested.In this paper,we proposed a method for the two-dimensional visualization of geochemical data.Using this method,we converted the geochemical compositions of volcanic rocks from 11 tectonic environments registered in the GEOROC database into 34468 two-dimensional coded images.Relying on deep learning method,75% of the images were used to learn and train automatically to construct the convolution neural network(CNN)model,which can be employed to classify volcanic rocks into tectonic groups at an overall accuracy of 95%.This model has good generalization capability and can be routinely used to distinguish the tectonic source regions of volcano rock samples.
The traditional tectonic discrimination graphs have some shortcomings due to the limitation of available analytical methods and techniques of times.This has led to some confusions and contradictions for scholars using the graphs in their researches.Under the impact of big data,the reliability of some traditional tectonic discrimination graphs is being tested.In this paper,we proposed a method for the two-dimensional visualization of geochemical data.Using this method,we converted the geochemical compositions of volcanic rocks from 11 tectonic environments registered in the GEOROC database into 34468 two-dimensional coded images.Relying on deep learning method,75% of the images were used to learn and train automatically to construct the convolution neural network(CNN)model,which can be employed to classify volcanic rocks into tectonic groups at an overall accuracy of 95%.This model has good generalization capability and can be routinely used to distinguish the tectonic source regions of volcano rock samples.
引文
[1]韩宝福.后碰撞花岗岩类的多样性及其构造环境判别的复杂性[J].地学前缘,2007,14(3):64-72.
[2]吴泰然.玄武岩的构造环境判别[J].岩石学报,1991,7(3):83-89.
[3]颜耀阳.玄武岩的构造环境判别及其多解性分析[J].地质调查与研究,1994(4):71-75.
[4]赵振华.关于岩石微量元素构造环境判别图解使用的有关问题[J].大地构造与成矿学,2007,31(1):92-103.
[5] PEARCE J A.Trace element characteristics of lavas from destructive plate boundaries[J].Andesite,1982,8:528-548.
[6] PEARCE J A.Characteristics and tectonic significance of supra subduction zone ophiolites[J].Geological Society of London-Special Publications,1984,16(1):77-94.
[7] PEARCE J A,NORRY M J.Petrogenetic implications of Ti,Zr,Y,and Nb variations in volcanic rocks[J].Contributions to Mineralogy and Petrology,1979,69(1):33-47.
[8] SHERVAIS J W.Ti-V plots and the petrogenesis of modern and ophiolitic lavas[J].Earth and Planetary Science Letters,1982,59(1):101-118.
[9] VERMA S P,AGRAWAL S,SALIL P.New tectonic discrimination diagrams for basic and ultrabasic volcanic rocks through log-transformed ratios of high field strength elements and implications for petrogenetic processes[J].Revista Mexicana De Ciencias Geológicas,2011,28(1):24-44.
[10] VERMA S P,GUEVARA M,AGRAWAL S.Discriminating four tectonic settings:five new geochemical diagrams for basic and ultrabasic volcanic rocks based on log-ratio transformation of major-element data[J].Journal of Earth System Science,2006,115(5):485-528.
[11] VERMEESCH P.Tectonic discrimination of basalts with classification trees[J].Geochimica et Cosmochimica Acta,2006,70(7):1839-1848.
[12] VERMEESCH P.Tectonic discrimination diagrams revisited[J].Geochemistry,Geophysics,Geosystems,2013,7(6):466-480.
[13] 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.
[14]杜雪亮,张旗,王金荣,等.全球海山玄武岩数据挖掘研究[J].地质科学,2017,52(3):668-692.
[15]王金荣,潘振杰,张旗,等.大陆板内玄武岩数据挖掘:成分多样性及在判别图中的表现[J].岩石学报,2016,32(7):1919-1933.
[16]杨婧,王金荣,张旗,等.弧后盆地玄武岩(BABB)数据挖掘:与MORB及IAB的对比[J].地球科学进展,2016,31(1):66-77.
[17]刘欣雨,张旗,张成立.全球新生代安山岩构造环境有关问题探讨[J].地质科学,2017,52(3):649-667.
[18]刘欣雨,张旗,张成立,等.中新世全球重要事件及其意义:数据挖掘的启示[J].科学通报,2017,(15):1645-1654.
[19]张泽军,周鼎武,何瑞芳.玄武岩的地球化学型式与构造环境的判别[J].矿物岩石地球化学通报,1993,12(4):209-211.
[20]张旗,周永章.大数据正在引发地球科学领域一场深刻的革命:《地质科学》2017年大数据专题代序[J].地质科学,2017,52(3):637-648.
[21]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.
[22]郭华东.大数据大科学大发现:大数据与科学发现国际研讨会综述[J].中国科学院院刊,2014(4):500-506.
[23]郭华东,王力哲,陈方,等.科学大数据与数字地球[J].科学通报,2014,59(12):1047-1054.
[24] SILVER D,HUANG A,MADDISON C J,et al.Mastering the game of Go with deep neural networks and tree search[J].Nature,2016,529(7587):484-489.
[25] SILVER D,SCHRITTWIESER J,SIMONYAN K,et al.Mastering the game of Go without human knowledge[J].Nature,2017,550(7676):354-359.
[26] BENGIO Y.Learning deep architectures for AI[J].Foundations&Trends in Machine Learning,2009,2(1):1-127.
[27] HINTON G E,OSINDERO S,TEH Y W.A fast learning algorithm for aeep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[28] HUBEL D H,WIESEL T N.Receptive fields,binocular interaction and functional architecture in the cat's visual cortex[J].Journal of Physiology,1962,160(1):106-154.
[29] LECUN Y L,BOSER B,DENKER J S,et al.Handwritten digit recognition with a back-propagation network[J].Advances in Neural Information Processing Systems,1990,2(2):396-404.
[30] 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.
[31] FUKUSHIMA K,MIYAKE S.Neocognitron:a new algorithm for pattern recognition tolerant of deformations and shifts in position[J].Pattern Recognition,1982,15(6):455-469.
[32] NAIR V,HINTON G E.Rectified linear units improve restricted boltzmann machines[C]∥Proceedings of the 27th International Conference on Machine Learning.Haifa,Israel:ICML,2010:807-814.
[33]刘建伟,刘媛,罗雄麟.深度学习研究进展[J].计算机应用研究,2014,31(7):1921-1930.
[34]孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810.
[35] LECUN Y,KAVUKCUOGLU K,FARABET C,et al.Convolutional networks and applications in vision[C]∥Proceedings of IEEE International Symposium on Circuits and Systems.Geneva,Switzerland:ISCS,2010:253-256.
[36] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image net classification with deep convolutional neural networks[J].Neural Information Processing Systems,2012,141(5):1097-1105.
[37] NGUYEN A,DOSOVITSKIY A,YOSINSKI J,et al.Synthesizing the preferred inputs for neurons in neural networks via deep generator networks[C]∥29th Conference on Neural Information Processing Systems.Barcelona,Spain:NIPS,2016,3387-3395.
[38] ZHANG Q,WU Y N,ZHU S C.Interpretable Convolutional Neural Networks[C]∥2018IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT:CVPR,2018:8827-8836.
[2]吴泰然.玄武岩的构造环境判别[J].岩石学报,1991,7(3):83-89.
[3]颜耀阳.玄武岩的构造环境判别及其多解性分析[J].地质调查与研究,1994(4):71-75.
[4]赵振华.关于岩石微量元素构造环境判别图解使用的有关问题[J].大地构造与成矿学,2007,31(1):92-103.
[5] PEARCE J A.Trace element characteristics of lavas from destructive plate boundaries[J].Andesite,1982,8:528-548.
[6] PEARCE J A.Characteristics and tectonic significance of supra subduction zone ophiolites[J].Geological Society of London-Special Publications,1984,16(1):77-94.
[7] PEARCE J A,NORRY M J.Petrogenetic implications of Ti,Zr,Y,and Nb variations in volcanic rocks[J].Contributions to Mineralogy and Petrology,1979,69(1):33-47.
[8] SHERVAIS J W.Ti-V plots and the petrogenesis of modern and ophiolitic lavas[J].Earth and Planetary Science Letters,1982,59(1):101-118.
[9] VERMA S P,AGRAWAL S,SALIL P.New tectonic discrimination diagrams for basic and ultrabasic volcanic rocks through log-transformed ratios of high field strength elements and implications for petrogenetic processes[J].Revista Mexicana De Ciencias Geológicas,2011,28(1):24-44.
[10] VERMA S P,GUEVARA M,AGRAWAL S.Discriminating four tectonic settings:five new geochemical diagrams for basic and ultrabasic volcanic rocks based on log-ratio transformation of major-element data[J].Journal of Earth System Science,2006,115(5):485-528.
[11] VERMEESCH P.Tectonic discrimination of basalts with classification trees[J].Geochimica et Cosmochimica Acta,2006,70(7):1839-1848.
[12] VERMEESCH P.Tectonic discrimination diagrams revisited[J].Geochemistry,Geophysics,Geosystems,2013,7(6):466-480.
[13] 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.
[14]杜雪亮,张旗,王金荣,等.全球海山玄武岩数据挖掘研究[J].地质科学,2017,52(3):668-692.
[15]王金荣,潘振杰,张旗,等.大陆板内玄武岩数据挖掘:成分多样性及在判别图中的表现[J].岩石学报,2016,32(7):1919-1933.
[16]杨婧,王金荣,张旗,等.弧后盆地玄武岩(BABB)数据挖掘:与MORB及IAB的对比[J].地球科学进展,2016,31(1):66-77.
[17]刘欣雨,张旗,张成立.全球新生代安山岩构造环境有关问题探讨[J].地质科学,2017,52(3):649-667.
[18]刘欣雨,张旗,张成立,等.中新世全球重要事件及其意义:数据挖掘的启示[J].科学通报,2017,(15):1645-1654.
[19]张泽军,周鼎武,何瑞芳.玄武岩的地球化学型式与构造环境的判别[J].矿物岩石地球化学通报,1993,12(4):209-211.
[20]张旗,周永章.大数据正在引发地球科学领域一场深刻的革命:《地质科学》2017年大数据专题代序[J].地质科学,2017,52(3):637-648.
[21]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.
[22]郭华东.大数据大科学大发现:大数据与科学发现国际研讨会综述[J].中国科学院院刊,2014(4):500-506.
[23]郭华东,王力哲,陈方,等.科学大数据与数字地球[J].科学通报,2014,59(12):1047-1054.
[24] SILVER D,HUANG A,MADDISON C J,et al.Mastering the game of Go with deep neural networks and tree search[J].Nature,2016,529(7587):484-489.
[25] SILVER D,SCHRITTWIESER J,SIMONYAN K,et al.Mastering the game of Go without human knowledge[J].Nature,2017,550(7676):354-359.
[26] BENGIO Y.Learning deep architectures for AI[J].Foundations&Trends in Machine Learning,2009,2(1):1-127.
[27] HINTON G E,OSINDERO S,TEH Y W.A fast learning algorithm for aeep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[28] HUBEL D H,WIESEL T N.Receptive fields,binocular interaction and functional architecture in the cat's visual cortex[J].Journal of Physiology,1962,160(1):106-154.
[29] LECUN Y L,BOSER B,DENKER J S,et al.Handwritten digit recognition with a back-propagation network[J].Advances in Neural Information Processing Systems,1990,2(2):396-404.
[30] 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.
[31] FUKUSHIMA K,MIYAKE S.Neocognitron:a new algorithm for pattern recognition tolerant of deformations and shifts in position[J].Pattern Recognition,1982,15(6):455-469.
[32] NAIR V,HINTON G E.Rectified linear units improve restricted boltzmann machines[C]∥Proceedings of the 27th International Conference on Machine Learning.Haifa,Israel:ICML,2010:807-814.
[33]刘建伟,刘媛,罗雄麟.深度学习研究进展[J].计算机应用研究,2014,31(7):1921-1930.
[34]孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810.
[35] LECUN Y,KAVUKCUOGLU K,FARABET C,et al.Convolutional networks and applications in vision[C]∥Proceedings of IEEE International Symposium on Circuits and Systems.Geneva,Switzerland:ISCS,2010:253-256.
[36] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image net classification with deep convolutional neural networks[J].Neural Information Processing Systems,2012,141(5):1097-1105.
[37] NGUYEN A,DOSOVITSKIY A,YOSINSKI J,et al.Synthesizing the preferred inputs for neurons in neural networks via deep generator networks[C]∥29th Conference on Neural Information Processing Systems.Barcelona,Spain:NIPS,2016,3387-3395.
[38] ZHANG Q,WU Y N,ZHU S C.Interpretable Convolutional Neural Networks[C]∥2018IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT:CVPR,2018:8827-8836.