深度学习在活动构造与地貌研究中的应用

doi:10.3969/j.issn.0253-4967.2024.02.003

地震地质 ›› 2024, Vol. 46 ›› Issue (2): 277-296.DOI: 10.3969/j.issn.0253-4967.2024.02.003

深度学习在活动构造与地貌研究中的应用

刘鑫¹^,²⁾(), 王诗柔¹⁾(), 石许华¹^,²⁾^,^*(), 苏程¹⁾^,^*(), 鲁晨妍¹⁾, 钱晓园¹⁾, 孙侨阳¹^,²⁾, 邓洪旦¹^,²⁾, 杨蓉¹^,²⁾, 程晓敢¹^,²⁾

¹⁾ 浙江省地学大数据与地球深部资源重点实验室, 浙江大学, 地球科学学院, 杭州 310058
²⁾ 教育部含油气盆地构造研究中心, 杭州 310058

收稿日期:2023-09-01 修回日期:2023-11-08 出版日期:2024-04-20 发布日期:2024-05-29
通讯作者: *石许华, 男, 1982年生, 研究员, 博士生导师, 主要从事构造地貌、活动构造和地震地质究, E-mail: shixuhua@zju.edu.cn。苏程, 男, 1985年生, 副教授, 硕士生导师, 主要从事遥感方向, 数字图像处理研究, E-mail: sc20184@zju.edu.cn。
作者简介:
刘鑫, 男, 1998年生, 现为浙江大学构造地质学专业在读博士研究生, 主要从事活动构造与地震地质研究, E-mail: xinliu0628@zju.edu.cn。
共同第一作者: 王诗柔, 女, 1999年生, 现为浙江大遥感与地理信息系统专业在读学博士研究生, 主要从事遥感方向深度学习研究, E-mail: wangshirou@zju.edu.cn。
基金资助:
国家自然科学基金(41972227); 国家自然科学基金(41941016); 国家自然科学基金(51988101); 浙江省钱江人才计划项目(QJD190202); 浙江大学百人计划项目

APPLICATION OF DEEP LEARNING IN ACTIVE TECTONICS AND GEOMORPHOLOGY

LIU Xin¹^,²⁾(), WANG Shi-rou¹⁾(), SHI Xu-hua¹^,²⁾^,^*(), SU Cheng¹⁾^,^*(), LU Chen-yan¹⁾, QIAN Xiao-yuan¹⁾, SUN Qiao-yang¹^,²⁾, DENG Hong-dan¹^,²⁾, YANG Rong¹^,²⁾, CHENG Xiao-gan¹^,²⁾

¹⁾ Key Laboratory of Geoscience Big Data and Deep Resource of Zhejiang Province, School of Earth Sciences, Zhejiang University, Hangzhou 310058, China
²⁾ Structural Research Centre of Oil and Gas Bearing Basin of Ministry of Education, Hangzhou 310058, China

Received:2023-09-01 Revised:2023-11-08 Online:2024-04-20 Published:2024-05-29

摘要/Abstract

摘要：

活动构造与地貌学主要涉及活动构造的运动学、地貌的演化过程及其相关动力机制, 该研究方向是近几十年来地球系统科学交叉研究的热点之一。随着大数据与机器学习研究的发展, 活动构造与地貌学的研究和深度学习的结合已成为该领域中受到广泛关注的新兴研究方向, 并产出了大量优秀成果。文中总结并综述了现今深度学习在活动构造与地貌研究中的数据来源, 以及利用深度学习的方法定量化解决活动构造与地貌中的重要科学问题(包括冰川识别、火山活动与地貌、水系分析、滑坡监测和地表形变等)。基于对上述实例的探索, 文中运用深度学习中的卷积神经网络, 对华南东南部福建地区的花岗岩岩石构造裂缝开展了基于高精度无人机航拍影像的深度学习自动识别。所搭建的卷积网络模型在55min的运行时间内自动识别出人工需消耗近一周才可识别的9 000余条裂缝, 并获得了85%的查准率与89%的查全率, 表明该模型在准确识别构造裂缝的同时显著提升了工作效率。文中最后讨论并展望了未来深度学习方法在活动构造与地貌学领域的发展前景。

关键词: 机器学习, 深度学习, 活动构造, 地貌, 自动识别

Abstract:

The research on active tectonics and geomorphology involves extensive sub-topics, including the kinematics of crustal movements, the processes underlying the evolution of landforms, and the associated dynamic mechanisms. These sub-topics are intricately connected with the interactions between the Earth’s endogenic and exogenic processes. In the contemporary realm of the Earth system science, research in active tectonics and geomorphology has become a hot topic for interdisciplinary study. The advancement in big data research coupled with the progressive developments in deep learning technologies has furnished this field of study with a voluminous array of data sources and the requisite analytical tools for technical analysis. In recent years, the application of big data and deep learning technologies in this research field has yielded a series of outstanding results, fostering new research directions, and ushering the discipline into a new phase. In this paper we synthesize existing research to outline the data sources pertinent to the study of active tectonics and geomorphology, including field geological survey, unmanned aerial vehicle (UAV)-based photography, aerial photography, and remote sensing observations. Then, we discuss in-depth examination of the recent innovations progresses in deep learning algorithms, including but not limited to convolutional neural networks(CNNs), deep Gaussian processes, and autoencoders. This article further elaborates on innovative applications of deep learning in the study of active tectonics and geomorphology. These include the identification of changes in glacier extent, monitoring volcanic activity and deformation, recognizing river systems, precise surveillance of landslide events, as well as observations of lithospheric deformation co-seismic surface ruptures.

Based on the summary of prior studies, this paper showcases a distinct application instance. By employing convolutional neural networks(CNNs)within the realm of deep learning image analysis and utilizing UAV-obtained high-resolution images, we undertake the automated detection of structural fractures in granite rocks in Meizhou island, in the southeast of Fujian province, China. In fault damage zones, structural rock fractures are widely developed, and the study of their orientation, system, and secondary characteristics is of great importance for determining their mechanisms of development and the multi-phase tectonic activity events in the region. Under conventional methodologies, the study of structural fractures in rocks is time-consuming and requires considerable manual effort in conducting exhaustive field surveys and detailed interpretation of cartographic representations. However, the application of deep learning can greatly enhance the efficiency of cartographic work. This application case has improved the classic deep learning framework by developing a CNN model specifically designed for the extraction of complex features and multi-scale rock fractures. This model achieved rapid identification of over 9 000 fractures with varied shapes and complex distributions within 55 minutes, attaining an accuracy of 85% and a recall rate of 89%. These findings demonstrate that deep learning significantly enhances operational efficiency in comparison to manual statistical methods for the automated identification of rock structural fractures, while also maintaining exceptional accuracy in fracture detection. Based on the results identified by deep learning, it can be clearly observed that two sets of fractures, oriented NE and NW, develop on the granite outcrops in the study area. According to previous research and the cross-cutting relationships of the fractures, it is known that NE-oriented fractures formed earlier than NW-oriented fractures, corresponding respectively to the Indosinian Movement and the expansion movement of the South China Sea in the tectonic history of South China. Through the automated extraction of deep learning models, the workload of manual mapping can be greatly reduced, yielding results consistent with actual geomorphological phenomena.

Key words: machine learning, deep learning, active tectonics, geomorphology, automatic identification

刘鑫, 王诗柔, 石许华, 苏程, 鲁晨妍, 钱晓园, 孙侨阳, 邓洪旦, 杨蓉, 程晓敢. 深度学习在活动构造与地貌研究中的应用[J]. 地震地质, 2024, 46(2): 277-296.

LIU Xin, WANG Shi-rou, SHI Xu-hua, SU Cheng, LU Chen-yan, QIAN Xiao-yuan, SUN Qiao-yang, DENG Hong-dan, YANG Rong, CHENG Xiao-gan. APPLICATION OF DEEP LEARNING IN ACTIVE TECTONICS AND GEOMORPHOLOGY[J]. SEISMOLOGY AND GEOLOGY, 2024, 46(2): 277-296.

图/表 8

图1 用于深度学习的地质数据来源(改自Ma et al., 2021) a 野外地质调查; b 无人机调查; c 航空影像; d 遥感观测

Fig. 1 Source of geological data for deep learning(modified from Ma et al., 2021).

图2 U-Net模型示意图(改自Ronneberger et al., 2015) 图例中, 第1类向右箭头为通过卷积过程进行特征提取, 第2类向右箭头为拼贴图像过程; 向下箭头为池化过程, 以防出现过拟合; 向上箭头为上采样过程, 对原图像进行放大; 重叠双箭头为输出最终结果

Fig. 2 Schematic diagram of U-Net model(modified from Ronneberger et al., 2015).

图3 自编码器示意图(改自Skansi, 2018) 输入层接受数据并进行降维; 隐藏层发现数据特征; 输出层还原数据原始本构

Fig. 3 Schematic diagram of Autoencoder(modified from Skansi, 2018).

图4 训练和试验提取的南极不同地点的海岸线(Baumhoer et al., 2019) 红线和蓝线分别指示人工及CNN自动识别出的海岸线

Fig. 4 Training and testing extracted shorelines at different locations in Antarctica(Baumhoer et al., 2019).

图5 基于USGS数据样品的水系识别结果(Yu et al., 2022) 显示的数字代表识别概率

Fig. 5 Drainage pattern recognition results based on data samples from USGS(Yu et al., 2022).

图6 大屿山地区的测试分区结果(Shi et al., 2020) a 滑坡事件前的航空正射像; b 滑坡事件后的航空正射像; c 参考地图; d 数字信号输入; e Shi等(2020)的CNN模型; f CDCNN模型分类后的二进制结果; g 将后期处理叠加在事件后图像上的最终结果; h 滑坡的径迹及源头

Fig. 6 Results of the testing zonation of Lantau district(Shi et al., 2020).

图7 基于多尺度特征提取的岩石裂缝提取卷积神经网络模型

Fig. 7 Convolutional neural network model for rock fracture extraction based on multi-scale feature extraction.

图8 岩石构造裂缝的识别 a 岩石构造裂缝正射影像; b 人工破裂填图; c 深度学习输出结果; d 图像后处理的提取结果

Fig. 8 Rock fracture identification.

参考文献 70

[1]	邓起东. 2002. 中国活动构造研究的进展与展望[J]. 地质论评, 48(2): 168—177.
	DENG Qi-dong. 2002. Advances and overview on researches of active tectonics in China[J]. Geological Review, 48(2): 168—177(in Chinese).
[2]	邓起东, 闻学泽. 2008. 活动构造研究: 历史, 进展与建议[J]. 地震地质, 30(1): 1—30.
	DENG Qi-dong, WEN Xue-ze. 2008. A review on the research of active tectonics history, progress and suggestions[J]. Seismology and Geology, 30(1): 1—30(in Chinese).
[3]	邓起东, 张培震, 冉勇康, 等. 2003. 中国活动构造与地震活动[J]. 地学前缘, 10(S1): 66—73.
	DENG Qi-dong, ZHANG Pei-zhen, RAN Yong-kang, et al. 2003. Active tectonics and earthquake activities in China[J]. Earth Science Frontiers, 10(S1): 66—73(in Chinese).
[4]	董传万, 周超, 顾虹艳, 等. 2011. 福建湄州岛镁铁质岩墙群与寄主花岗岩的形成时差、地球化学及成因[J]. 吉林大学学报(地球科学版), 41(3): 735—744.
	DONG Chuan-wan, ZHOU Chao, GU Hong-yan, et al. 2011. The age difference, geochemistry and petrogenesis of mafic dikes and host granites from Meizhou island in Fujian Province[J]. Journal of Jilin University(Earth Science Edition), 41(3): 735—744(in Chinese).
[5]	冯艳芳, 刘江涛, 刘勇, 等. 2022. 国内外基础地质数据更新现状与思考[J]. 地学前缘, 29(2): 370—377. DOI
	FENG Yan-fang, LIU Jiang-tao, LIU Yong, et al. 2022. Updating basic geological data; Current status at home and abroad and suggestions for future improvements[J]. Earth Science Frontiers, 29(2): 370—377(in Chinese).
[6]	舒远海, 石许华, 陈汉林, 等. 2022. 地壳均衡理论及其在构造地貌研究中的应用[J]. 地质论评, 68(4): 1171—1190.
	SHU Yuan-hai, SHI Xu-hua, CHEN Han-lin, et al. 2022. Isostasy and its application in tectonic geomorphology research[J]. Geological Review, 68(4): 1171—1190(in Chinese).
[7]	王锦涵, 石许华, 陈汉林, 等. 2023. “V” 型共轭走滑断裂: 特征, 形成机制及其对青藏高原东南缘晚新生代变形的启示[J]. 地球科学, 48(4): 1421—1440.
	WANG Jin-han, SHI Xu-hua, CHEN Han-lin, et al. 2023. V-shaped conjugate strike-slip faults: Characteristics, formation mechanisms and implications for the late Cenozoic deformation in the southeastern Tibetan plateau[J]. Earth Science, 48(4): 1421—1440(in Chinese).
[8]	叶青, 施和生, 梅廉夫, 等. 2017. 珠江口盆地珠一坳陷裂后期断裂作用: 迁移、转换及其动力学[J]. 地球科学, 42(1): 105—118.
	YE Qing, SHI He-sheng, MEI Lian-fu, et al. 2017. Post-rift faulting migration, transition and dynamics in Zhu Ⅰdepression, pearl river mouth basin[J]. Earth Science, 42(1): 105—118(in Chinese).
[9]	曾宪阳, 刘静, 王伟, 等. 2023. 基于机器学习的地表破裂自动识别和填图: 以2021年青海玛多 M_W7.4 地震为例[J]. 地球物理学报, 66(3): 1098—1112.
	ZENG Xian-yang, LIU Jing, WANG Wei, et al. 2023. Machine learning in identifying and mapping the surface rupture of the 2021 M_W7.4 Madoi earthquake, Qinghai[J]. Chinese Journal of Geophysics, 66(3): 1098—1112(in Chinese).
[10]	张敏, 旷健, 肖志才, 等. 2021. 广东惠州燕山期以来地质构造演化: 对华南构造的新启示[J]. 地球科学, 46(1): 242—258.
	ZHANG Min, KUANG Jian, XIAO Zhi-cai, et al. 2021. Geological evolution since the Yanshanian in Huizhou, Guangdong Province: New implications for the tectonics of south China[J]. Earth Science, 46(1): 242—258(in Chinese).
[11]	周永章, 左仁广, 刘刚, 等. 2021. 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, 40(3): 556—573, 777.
	ZHOU Yong-zhang, ZUO Ren-guang, LIU Gang, et al. 2021. The great-leap-forward development of mathematical geoscience during 2010-2019: Big data and artificial intelligence algorithm are changing mathematical geoscience[J]. Bulletin of Mineralogy, Petrology and Geochemistry, 40(3): 556—573, 777(in Chinese).
[12]	左仁广, 彭勇, 李童, 等. 2021. 基于深度学习的地质找矿大数据挖掘与集成的挑战[J]. 地球科学, 46(1): 350—358.
	ZUO Ren-guang, PENG Yong, LI Tong, et al. 2021. Challenges of geological prospecting big data mining and integration using deep learning algorithms[J]. Earth Science, 46(1): 350—358(in Chinese).
[13]	Allen R M, Ziv A. 2011. Application of real-time GPS to earthquake early warning[J]. Geophysical Research Letters, 38(16): L16310.
[14]	Anantrasirichai N, Biggs J, Albino F, et al. 2018. Application of machine learning to classification of volcanic deformation in routinely generated InSAR data[J]. Journal of Geophysical Research: Solid Earth, 123(8): 6592—6606.
[15]	Anantrasirichai N, Biggs J, Albino F, et al. 2019. A deep learning approach to detecting volcano deformation from satellite imagery using synthetic datasets[J]. Remote Sensing of Environment, 230:111179.
[16]	Baumhoer C A, Dietz A J, Kneisel C, et al. 2019. Automated extraction of antarctic glacier and ice shelf fronts from sentinel -1 imagery using deep learning[J]. Remote Sensing, 11(21): 2529.
[17]	Bemis S P, Micklethwaite S, Turner D, et al. 2014. Ground-based and UAV-Based photogrammetry: A multi-scale, high-resolution mapping tool for structural geology and paleoseismology[J]. Journal of Structural Geology, 69: 163—178.
[18]	Burbank D W, Anderson R S. 2011. Tectonic Geomorphology[M]. John Wiley and Sons, Hoboken.
[19]	Cao T, Xiao A, Wu L, et al. 2017. Automatic fracture detection based on Terrestrial Laser Scanning data: A new method and case study[J]. Computers & Geosciences, 16: 209—216.
[20]	Chaipornkaew L, Elston H, Cooke M, et al. 2022. Predicting off-fault deformation from experimental strike-slip fault images using convolutional neural networks[J]. Geophysical Research Letters, 49(2): e2021GL096854.
[21]	Chen X, Hu G, Liu X. 2022. Recognition of earthquake surface ruptures using deep learning[J]. Applied Sciences, 12(22): 11638.
[22]	Choi Y, Choi J H, Choi Y. 2023. Fit-for-Purpose approach for the detection and analysis of earthquake surface ruptures using satellite images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16: 9574—9589.
[23]	Colomina I, Molina P. 2014. Unmanned aerial systems for photogrammetry and remote sensing: A review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 92: 79—97.
[24]	Cremen G, Galasso C. 2020. Earthquake early warning: Recent advances and perspectives[J]. Earth-Science Reviews, 205(5): 103184.
[25]	Daily M I, Farr T, Elachi C, et al. 1979. Geologic interpretation from composited radar and Landsat imagery[J]. Photogrammetric Engineering and Remote Sensing, 45(8): 1109—1116.
[26]	Damianou A, Lawrence N D. 2013. Deep Gaussian processes[C]. Proceedings of the 16th International Conference on Artificial Intelligence and Statistics(AISTATS), Scottsdale, AZ, USA(PMLR, 2013), 31: 207—215.
[27]	Del Pezzo E, Esposito A, Giudicepietro F, et al. 2003. Discrimination of earthquakes and underwater explosions using neural networks[J]. Bulletin of the Seismological Society of America, 93(1): 215—223.
[28]	Del Soldato M, Confuorto P, Bianchini S, et al. 2021. Review of works combining GNSS and InSAR in Europe[J]. Remote Sensing, 13(9): 1684.
[29]	Dunai T J. 2010. Cosmogenic Nuclides: Principles, Concepts and Applications in the Earth Surface Sciences[M]. Cambridge University Press, Cambridge.
[30]	Elliott J R. 2020. Earth observation for the assessment of earthquake hazard, risk and disaster management[J]. Surveys in Geophysics, 41(6): 1323—1354.
[31]	Elliott J R, Walters R J, Wright T J. 2016. The role of space-based observation in understanding and responding to active tectonics and earthquakes[J]. Nature Communications, 7(1): 1—16.
[32]	Fiorucci F, Giordan D, Santangelo M, et al. 2018. Criteria for the optimal selection of remote sensing optical images to map event landslides[J]. Natural Hazards and Earth System Sciences, 18(1): 405—417.
[33]	Fleming Z, Pavlis T. 2018. An orientation based correction method for SfM-MVS point clouds: Implications for field geology[J]. Journal of Structural Geology, 113: 76—89.
[34]	Guzzetti F, Mondini A C, Cardinali M, et al. 2012. Landslide inventory maps: New tools for an old problem[J]. Earth-Science Reviews, 112(1-2): 42—66.
[35]	Hinton G E, Salakhutdinov R R. 2006. Reducing the dimensionality of data with neural networks[J]. Science, 313(5786): 504—507. DOI PMID
[36]	Im J, Rhee J, Jensen J R, et al. 2007. An automated binary change detection model using a calibration approach[J]. Remote Sensing of Environment, 106(1): 89—105.
[37]	James M R, Robson S. 2012. Straightforward reconstruction of 3D surfaces and topography with a camera: Accuracy and geoscience application[J]. Journal of Geophysical Research: Earth Surface, 117(F3): F03017.
[38]	Kidner D B, Smith D H. 2003. Advances in the data compression of digital elevation models[J]. Computers & Geosciences, 29(8): 985—1002.
[39]	Kim Y S, Peacock D C P, Sanderson D J. 2004. Fault damage zones[J]. Journal of Structural Geology, 26(3): 503—517.
[40]	Klinger Y, Xu X, Tapponnier P, et al. 2005. High-resolution satellite imagery mapping of the surface rupture and slip distribution of the M_W-7.8, 14 November 2001 Kokoxili earthquake, Kunlun Fault, northern Tibet, China[J]. Bulletin of the Seismological Society of America, 95(5): 1970—1987.
[41]	Lei J, Ren Z, Oguchi T, et al. 2021. Topographic evolution involving co-seismic landslide, deformation, long-term folding and isostatic rebound: A case study on the 2004 Chuetsu earthquake[J]. Remote Sensing, 13(6): 1073.
[42]	Li R, Xu Z, Su C, et al. 2022. Automatic identification of semi-tracks on apatite and mica using a deep learning method[J]. Computers & Geosciences, 162:105081.
[43]	Li D, Ren J. 2023. EASRAPP: An open-source semiautomatic Python GUI-Based application for extraction and analysis of surface ruptures in a large earthquake[J]. Seismological Research Letters, 94(4): 2014—2029.
[44]	Li Y E, O’Malley D, Beroza G, et al. 2023. Machine learning developments and applications in solid-earth geosciences: Fad or future?[J]. Journal of Geophysical Research: Solid Earth, 128: e2022JB026310.
[45]	López-Pérez M, García L, Benítez C, et al. 2020. A contribution to deep learning approaches for automatic classification of volcano-seismic events: deep gaussian processes[J]. IEEE Transactions on Geoscience and Remote Sensing, 59(5): 3875—3890.
[46]	Lü Z Y, Shi W, Zhang X, et al. 2018. Landslide inventory mapping from bitemporal high-resolution remote sensing images using change detection and multiscale segmentation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(5): 1520—1532.
[47]	Ma Z, Mei G. 2021. Deep learning for geological hazards analysis: Data, models, applications, and opportunities[J]. Earth-Science Reviews, 223: 103858.
[48]	Martha T R, Kerle N, Jetten V, et al. 2010. Characterising spectral, spatial and morphometric properties of landslides for semi-automatic detection using object-oriented methods[J]. Geomorphology, 116(1-2): 24—36.
[49]	Parker A L, Biggs J, Walters R J, et al. 2015. Systematic assessment of atmospheric uncertainties for InSAR data at volcanic arcs using large-scale atmospheric models: Application to the Cascade volcanoes, United States[J]. Remote Sensing of Environment, 170: 102—114.
[50]	Pavlis T L, Langford R, Hurtado J, et al. 2010. Computer-based data acquisition and visualization systems in field geology: Results from 12 years of experimentation and future potential[J]. Geosphere, 6(3): 275—294.
[51]	Periyasamy M, Davari A, Seehaus T, et al. 2022. How to get the most out of U-Net for glacier calving front segmentation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15: 1712—1723.
[52]	Price P B, Walker R M. 1963. Fossil tracks of charged particles in mica and the age of minerals[J]. Journal of Geophysical Research, 68(16): 4847—4862.
[53]	Rao G, Lin A, Yan B, et al. 2011. Co-seismic Riedel shear structures produced by the 2010 M_W6.9 Yushu earthquake, central Tibetan plateau, China[J]. Tectonophysics, 507(1-4): 86—94.
[54]	Ronneberger O, Fischer P, Brox T. 2015. U-net: Convolutional networks for biomedical image segmentation[C]. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015:18th International Conference, Munich, Germany, October 5-9, Proceedings, Part III 18. Springer International Publishing, Berlin: 234—241.
[55]	Rumelhart D E, Hinton G E, Williams R J. 1986. Learning representations by back-propagating errors[J]. Nature, 323(6088): 533—536.
[56]	Scholz C H. 2019. The Mechanics of Earthquakes and Faulting[M]. Cambridge University Press, Cambridge.
[57]	Shi W, Zhang M, Ke H, et al. 2020. Landslide recognition by deep convolutional neural network and change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 59(6): 4654—4672.
[58]	Shi X, Furlong K P, Kirby E, et al. 2017. Evaluating the size and extent of paleolakes in central Tibet during the late Pleistocene[J]. Geophysical Research Letters, 44(11): 5476—5485.
[59]	Shi X, Kirby E, Furlong K P, et al. 2015. Crustal strength in central Tibet determined from Holocene shoreline deflection around Siling Co[J]. Earth and Planetary Science Letters, 423: 145—154.
[60]	Simonyan K, Zisserman A. 2014. Very deep convolutional networks for large-scale image recognition[J/OL]. arXiv preprint arXiv: 1409.1556.
[61]	Skansi S. 2018. Introduction to Deep Learning: from Logical Calculus to Artificial Intelligence[M]. Springer, Berlin.
[62]	Su N, Zou L, Shen X, et al. 2014. Fracture patterns in successive folding in the western Sichuan Basin, China[J]. Journal of Asian Earth Sciences, 81: 65—76.
[63]	Tavani S, Billi A, Corradetti A, et al. 2022. Smartphone assisted fieldwork: Towards the digital transition of geoscience fieldwork using LiDAR-equipped iPhones[J]. Earth-Science Reviews, 227: 103969.
[64]	Walters R J, Holley R J, Parsons B, et al. 2011. Interseismic strain accumulation across the North Anatolian Fault from Envisat InSAR measurements[J]. Geophysical Research Letters, 38(5): L05303.
[65]	Wang K, Johnson C W, Bennett K C, et al. 2021. Predicting fault slip via transfer learning[J]. Nature Communications, 12(1): 1—11.
[66]	Whipple K X. 2004. Bedrock rivers and the geomorphology of active orogens[J]. Annual Review of Earth and Planetary Sciences, 32: 151—185.
[67]	Whipple K X, Tucker G E. 1999. Dynamics of the stream-power river incision model: Implications for height limits of mountain ranges, landscape response timescales, and research needs[J]. Journal of Geophysical Research: Solid Earth, 104(B8): 17661—17674.
[68]	Xu C, Deng Y, Barnes C G, et al. 2023. Offshore-onshore tectonomagmatic correlations: Towards a Late Mesozoic non-Andean-type Cathaysian continental margin[J]. Earth Science Reviews, 240:104382.
[69]	Yu H, Ai T, Yang M, et al. 2022. A recognition method for drainage patterns using a graph convolutional network[J]. International Journal of Applied Earth Observation and Geoinformation, 107:102696.
[70]	Zhang H, Chen N, Gao B, et al. 2020. Semi-automatic mapping of dyke and dyke-related fractures using UAV-based photogrammetric data: A case study from Sijiao Island, coastal Southeastern China[J]. Journal of Structural Geology, 132: 103971.

深度学习在活动构造与地貌研究中的应用

APPLICATION OF DEEP LEARNING IN ACTIVE TECTONICS AND GEOMORPHOLOGY

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 70

相关文章 15

编辑推荐

Metrics

本文评价

[1]	庞桢辉, 徐皓婷, 石许华, 葛进, 李丰. 陡坎地貌定年理论及其在活动构造与地貌学研究中的应用[J]. 地震地质, 2024, 46(2): 251-276.
[2]	张玲, 苗树清, 杨晓平. 基于ArcGIS平台的天山北麓活动逆断层智能化提取方法的研究与实现[J]. 地震地质, 2023, 45(2): 422-434.
[3]	张苏祥, 盛书中, 席彪, 房立华, 吕坚, 王甘娇, 张潇. 基于改进的DBSCAN算法自动识别断层方法研究及其在唐山地区的应用[J]. 地震地质, 2022, 44(6): 1615-1633.
[4]	徐伟, 刘志成, 王继, 高战武, 尹金辉. 西藏阿里地区喀喇昆仑断裂断错地貌及最近强震活动时代的初步研究[J]. 地震地质, 2022, 44(4): 925-943.
[5]	卢本添, 李志刚, 梁浩, 杨敬钧, 郑文俊. 中条山北麓河流地貌特征及其对断裂构造演化的响应[J]. 地震地质, 2022, 44(4): 961-975.
[6]	叶雨晖, 吴磊, 王依平, 楼谦谦, 陈力琦, 高石宝, 林秀斌, 程晓敢, 陈汉林. 北阿尔金断裂晚第四纪活动构造特征[J]. 地震地质, 2022, 44(2): 297-312.
[7]	周少辉, 蒋海昆, 李健, 曲均浩, 郑晨晨, 李亚军, 张志慧, 郭宗斌. 基于深度学习的地震事件分类识别——以山东地震台网记录为例[J]. 地震地质, 2021, 43(3): 663-676.
[8]	陈晓利, 刘春国, 传一健, 兰剑, 魏延坤. 鲁甸地震的滑坡物质运移规律与地形特征[J]. 地震地质, 2021, 43(1): 92-104.
[9]	周朝, 何宏林, 魏占玉, 苏鹏, 任光雪. 地貌参数方法在小尺度地貌研究中的应用——以北天山独山子背斜为例[J]. 地震地质, 2020, 42(6): 1492-1508.
[10]	唐清, 郑文俊, 石霖, 张冬丽, 黄荣. 基于高精度LiDAR数据的断裂活动习性精细定量——以香山-天景山断裂景泰小红山段为例[J]. 地震地质, 2020, 42(2): 366-381.
[11]	苏强, 任俊杰, 梁欧博, 郭菲. 基于ALOS PALSAR影像的莫勒切河洪积扇地貌面定量分期[J]. 地震地质, 2020, 42(1): 79-94.
[12]	魏聪敏, 葛伟鹏, 张波. 利用地貌形态估算西秦岭-松潘构造结及邻区的下地壳黏滞系数[J]. 地震地质, 2020, 42(1): 163-181.
[13]	孙稳, 何宏林, 魏占玉, 高伟, 孙浩越, 邹俊杰. 基于无人机航测获取高分辨率DEM数据的断层几何结构精细解译与分析——以海原断裂唐家坡为例[J]. 地震地质, 2019, 41(6): 1350-1365.
[14]	刘睿, 姜大伟, 李安, 郭长辉, 张世民. 利用沉积物粒度特征区分不同级地貌面的方法对比——以青衣江流域地貌面为例[J]. 地震地质, 2019, 41(4): 837-855.
[15]	任光雪, 李传友, 吴传勇, 汪思妤, 张会平, 任治坤, 李新男. 东天山包尔图断裂带晚第四纪运动性质及形成机制[J]. 地震地质, 2019, 41(4): 856-871.