基于目标检测的震源逆时成像方法研究

微地震监测广泛应用于水力压裂、碳封存、地热资源开发等人类活动中，开发 活动的安全进行、开发策略的制定、地震研究等都需要微地震监测支持，其定位 精度以及事件目录的完备性对于正确研究和认识区域地震活动规律及其影响因素 具有重要意义。

相比于天然地震，微地震事件数量多但信号微弱。对于时间上存在重叠的微 震事件，基于走时信息的定位方法由于台站记录上波形发生重叠，而无法拾取后 抵达的 P 波到时；基于偏移叠加类的定位方法需要施加成像条件后搜索每个时刻 的最大能量值获取具体的发震时刻和震源位置，这种最大能量值条件将四维的成 像结果压缩到时间维，因此无法区分多个高能量值的情况而发生漏拾。

本文发展了一种基于深度学习 (Deep Learning, DL) 的目标检测 (Object Detection) 算法, 用于检测震源逆时成像结果中的辐射花样。本文设计了一种基于 You Only Look Once (YOLO) 网络的神经网络模型，通过震源逆时成像获得在空间上分 散开的辐射花样后，将 3D 的逆时成像结果取绝对值沿深度叠加来获得包含震源 水平位置信息的二维辐射花样，并将其以类似图像的方式输入神经网络进行识别。 该方法能够有效地预测出单个或多个辐射花样的中心位置和大小。通过预测辐射 花样的中心位置作为震源的水平位置，该方法减小了由于辐射花样不聚焦导致的 的最大能量值成像条件定位的不准确性，相比于极性矫正等传统方法具有计算迅 速的特点；同时凭借目标检测适用于多个物体的特性，空间上分离了时窗上有重 叠的地震事件，且不需要进行全空间的扫描。

由于辐射花样的特征主要受震源参数影响，使用不同偏移叠加方法、不同台 站分布所得到的结果具有相似性，且该网络可以处理不同大小的输入数据，训练 好的模型具有良好的泛化能力，在观测条件符合的情况下可以适用于各类震群事 件的检测和水平定位，三维震源位置的获取则需要进一步结合成像条件等方法。

Microseismic monitoring is widely employed in anthropogenic activities such as hydraulic fracturing, carbon sequestration, and geothermal resource development. It plays a crucial role in ensuring the safety of development operations, formulating efficient development strategies, and advancing seismic research. The accuracy of microseismic event localization and the completeness of the event catalog are of paramount importance for understanding regional seismic activity patterns and their influencing factors.

Compared to natural earthquakes, microseismic events are more abundant but exhibit weaker signals. When dealing with temporally overlapping microseismic events, traditional localization methods based on arrival time information face challenges due to waveform overlap in station records, making it impossible to pick the arrival time of the P-wave after the fact. Additionally, migration-based methods require imposing imaging conditions to search for the maximum energy value at each moment to provide specific seismic onset times and source locations. However, this maximum energy imaging condition compresses the four-dimensional imaging results into the time dimension, making it difficult to distinguish multiple high-energy situations and resulting in missed detections.

In this study, we propose a novel approach based on Deep Learning (DL) for detecting radiation patterns in reverse time imaging results. Specifically, we design a neural network model based on the You Only Look Once (YOLO) architecture. After obtaining spatially dispersed radiation patterns from time-reversal imaging, we stacke the absolute values of 3D imaging wavefield along depth to obtain the 2D radiation pattern that contains the information of horizontal seismic location. This transformed pattern is then put it into the network to predict the center positions and sizes of these radiation patterns. Our method effectively predicts the center locations and sizes of individual or multiple radiation patterns. By using the predicted center positions as the horizontal source locations, our approach mitigates inaccuracies caused by unfocused radiation patterns in maximum energy value-based localization, offering computational efficiency compared to traditional methods like polarity correction.Furthermore, leveraging the multi-object detection capability inherent in object detection techniques, our method spatially separates seismic events with overlapping time windows without requiring a full-space scan.

The proposed network demonstrates robust generalization capabilities, accommodating different input data sizes. Under suitable observational conditions, it can be applied to detect and locate various seismic clusters horizontally. However, obtaining threedimensional source locations still requires further integration with imaging conditions or other techniques.

[1] MOEIN M J, LANGENBRUCH C, SCHULTZ R, et al. The physical mechanisms of induced earthquakes[J]. Nature Reviews Earth & Environment, 2023, 4(12): 847-863.
[2] HEALY J, RUBEY W, GRIGGS D, et al. The denver earthquakes[J]. Science, 1968, 161(3848):1301-1310.
[3] ELLSWORTH W L. Injection-induced earthquakes[J]. science, 2013, 341(6142): 1225942.
[4] FENG G L, FENG X T, CHEN B R, et al. A microseismic method for dynamic warning of rockburst development processes in tunnels[J]. Rock Mechanics and Rock Engineering, 2015,48: 2061-2076.
[5] 达姝瑾, 李学贵, 董宏丽, 等. 微地震震源定位方法综述[M]. 吉林大学学报 (地球科学版),2020.
[6] KARASÖZEN E, KARASÖZEN B. Earthquake location methods[J]. GEM-International Journal on Geomathematics, 2020, 11: 1-28.
[7] 张青山. 微地震叠加定位的干涉成像和机器学习研究与应用[D]. 中国科学技术大学,2022.
[8] MILNE J. Earthquakes and other earth movements: Vol. 56[M]. Kegan Paul, Trench, & Company, 1886.
[9] REID H F. The mechanism of the earthquake, the California earthquake of April 18, 1906[J]. Report of the Research Senatorial Commission, Carnegie Institution, Washington, DC, 1910, 2: 16-18.
[10] GEIGER L. Probability method for the determination of earthquake epicentres from the arrival time only[J]. Bull. St. Louis Univ., 1912, 8: 60.
[11] FITCH T J. Compressional velocity in source regions of deep earthquakes: an application of the master earthquake technique[J]. Earth and planetary science Letters, 1975, 26(2): 156-166.
[12] ITO A. High resolution relative hypocenters of similar earthquakes by cross-spectral analysis method[J]. Journal of Physics of the Earth, 1985, 33(4): 279-294.
[13] WALDHAUSER F, ELLSWORTH W L. A double-difference earthquake location algorithm: Method and application to the northern Hayward fault, California[J]. Bulletin of the seismological society of America, 2000, 90(6): 1353-1368.
[14] SHELLY D R, BEROZA G C, IDE S. Non-volcanic tremor and low-frequency earthquake swarms[J]. Nature, 2007, 446(7133): 305-307.
[15] PENG Z, ZHAO P. Migration of early aftershocks following the 2004 Parkfield earthquake[J]. Nature Geoscience, 2009, 2(12): 877-881.
[16] ALLEN R. Automatic phase pickers: Their present use and future prospects[J]. Bulletin of the Seismological Society of America, 1982, 72(6B): S225-S242.
[17] ROSS Z E, MEIER M A, HAUKSSON E, et al. Generalized seismic phase detection with deep learningshort note[J]. Bulletin of the Seismological Society of America, 2018, 108(5A):2894-2901.
[18] DREW J, LESLIE D, ARMSTRONG P, et al. Automated microseismic event detection and location by continuous spatial mapping[C]//SPE Annual Technical Conference and Exhibition? SPE, 2005: SPE-95513.
[19] KAO H, SHAN S J. The source-scanning algorithm: Mapping the distribution of seismic sources in time and space[J]. Geophysical Journal International, 2004, 157(2): 589-594.
[20] ZHANG Q, ZHANG W. An efficient diffraction stacking interferometric imaging location method for microseismic events[J]. Geophysics, 2022, 87(3): KS73-KS82.
[21] ARTMAN B, PODLADTCHIKOV I, WITTEN B. Source location using time-reverse imaging [J]. Geophysical Prospecting, 2010, 58(5): 861-873.
[22] MCMECHAN G A. Determination of source parameters by wavefield extrapolation[J]. Geophysical Journal International, 1982, 71(3): 613-628.
[23] ZHOU Y, ZHANG Q, ZHANG W. PS interferometric imaging condition for microseismic source elastic time-reversal imaging[J]. Geophysical Journal International, 2022, 229(1): 505-521.
[24] MCMECHAN G A, LUETGERT J, MOONEY W. Imaging of earthquake sources in Long Valley caldera, California, 1983[J]. Bulletin of the Seismological Society of America, 1985, 75 (4): 1005-1020.
[25] FINK M. Time-reversed acoustics[J]. Scientific American, 1999, 281(5): 91-97.
[26] FINK M, MONTALDO G, TANTER M. Time-reversal acoustics in biomedical engineering[J]. Annual review of biomedical engineering, 2003, 5(1): 465-497.
[27] SAVA P, POLIANNIKOV O. Interferometric imaging condition for wave-equation migration [J]. Geophysics, 2008, 73(2): S47-S61.
[28] MOUSAVI S M, BEROZA G C. Deep-learning seismology[J]. Science, 2022, 377(6607): eabm4470.
[29] PEROL T, GHARBI M, DENOLLE M. Convolutional neural network for earthquake detection and location[J]. Science Advances, 2018, 4(2): e1700578.
[30] ZHU W, BEROZA G C. PhaseNet: a deep-neural-network-based seismic arrival-time picking method[J]. Geophysical Journal International, 2019, 216(1): 261-273.
[31] ZHOU Y, YUE H, KONG Q, et al. Hybrid event detection and phase-picking algorithm using convolutional and recurrent neural networks[J]. Seismological Research Letters, 2019, 90(3): 1079-1087.
[32] MOUSAVI S M, ZHU W, SHENG Y, et al. CRED: A deep residual network of convolutional and recurrent units for earthquake signal detection[J]. Scientific reports, 2019, 9(1): 1-14.
[33] MOUSAVI S M, ELLSWORTH W L, ZHU W, et al. Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking[J]. Nature communications,2020, 11(1): 1-12.
[34] ZHOU Y, YUE H, FANG L, et al. An earthquake detection and location architecture for continuous seismograms: Phase picking, association, location, and matched filter (PALM)[J]. Seismological Society of America, 2022, 93(1): 413-425.
[35] ZHANG M, LIU M, FENG T, et al. LOC-FLOW: An End-to-End Machine Learning-Based High-Precision Earthquake Location Workflow[J]. Seismological Research Letters, 2022.
[36] VAN DEN ENDE M P, AMPUERO J P. Automated seismic source characterization using deep graph neural networks[J]. Geophysical Research Letters, 2020, 47(17): e2020GL088690.
[37] KUANG W, YUAN C, ZOU Z, et al. Autonomous Earthquake Location via Deep Reinforcement Learning[J]. Seismological Research Letters, 2024, 95(1): 367-377.
[38] ZHU W, MOUSAVI S M, BEROZA G C. Seismic signal denoising and decomposition using deep neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(11):9476-9488.
[39] TIAN X, ZHANG W, ZHANG X, et al. Comparison of single-trace and multiple-trace polarity determination for surface microseismic data using deep learning[J]. Seismological Research Letters, 2020, 91(3): 1794-1803.
[40] ZHANG Q, ZHANG W, WU X, et al. Deep Learning for Efficient Microseismic Location Using Source Migration-Based Imaging[J]. Journal of Geophysical Research: Solid Earth, 2022, 127 (3): e2021JB022649.
[41] GUTENBERG B, RICHTER C F. Earthquake magnitude, intensity, energy, and acceleration [J]. Bulletin of the Seismological society of America, 1942, 32(3): 163-191.
[42] GUTENBERG B, RICHTER C F. Earthquake magnitude, intensity, energy, and acceleration: (Second paper)[J]. Bulletin of the seismological society of America, 1956, 46(2): 105-145.
[43] DUNCAN P M. Is there a future for passive seismic?[J]. First Break, 2005, 23(6).
[44] BORCEA L, PAPANICOLAOU G, TSOGKA C. Theory and applications of time reversal and interferometric imaging[J]. Inverse Problems, 2003, 19(6): S139.
[45] 周逸成. 微地震单井观测系统的震源逆时成像方法[D]. 中国科学技术大学, 2018.
[46] ZHOU H W, HU H, ZOU Z, et al. Reverse time migration: A prospect of seismic imaging methodology[J]. Earth-science reviews, 2018, 179: 207-227.
[47] AKI K. Quantitative seismology[J]. Theory and method, 1980: 304-308.
[48] FINK M. Time-reversal acousticsin complex environments[J]. geophysics, 2006, 71(4): SI151-SI164.
[49] GAJEWSKI D, TESSMER E. Reverse modelling for seismic event characterizatio [J]. Geophysical Journal International, 2005, 163(1): 276-284.
[50] LARMAT C, GUYER R,JOHNSON P A. Tremorsource location using time reversal: Selecting the appropriate imaging field[J]. Geophysical Research Letters, 2009, 36(22).
[51] AKI K, RICHARDS P G. Quantitative seismology[M]. 2002.
[52] YAN J, SAVA P. Isotropic angle-domain elastic reverse-time migration[J]. Geophysics, 2008,73(6): S229-S239.
[53] XIAO X, LEANEY W S. Local vertical seismic profiling (VSP) elastic reverse-time migration and migration resolution: Salt-flank imaging with transmitted P-to-S waves[J]. Geophysics, 2010, 75(2): S35-S49.
[54] WANG W, MCMECHAN G A. Vector-based elastic reverse time migration[J]. Geophysics, 2015, 80(6): S245-S258.
[55] LI J, SHEN Y, ZHANG W. Three-dimensional passive-source reverse-time migration of converted waves: The method[J]. Journal of Geophysical Research: Solid Earth, 2018, 123(2):1419-1434.
[56] HU N, ZHANG W, XU J, et al. P-and S-wave energy current density vectors dot product imaging condition of source time-reversal imaging[J]. Geophysical Journal International, 2023, 234(3): 2180-2198.
[57] ZHANG W, ZHANG Z, CHEN X. Three-dimensional elastic wave numerical modelling in the presence of surface topography by a collocated-grid finite-difference method on curvilinear grids[J]. Geophysical Journal International, 2012, 190(1): 358-378.
[58] ZHANG W, CHEN X. Traction image method for irregular free surface boundaries in finite difference seismic wave simulation[J]. Geophysical Journal International, 2006, 167(1): 337-353.
[59] MOCZO P, LUCKÁ M, KRISTEK J, et al. 3D displacement finite differences and a combined memory optimization[J]. Bulletin of the Seismological Society of America, 1999, 89(1): 69-79.
[60] HIXON R, HIXON R. On increasing the accuracy of MacCormack schemes for aeroacoustic applications[C]//3rd AIAA/CEAS Aeroacoustics Conference. 1997: 1586.
[61] GRAVES R W. Simulating seismic wave propagation in 3D elastic media using staggered-grid finite differences[J]. Bulletin of the seismological society of America, 1996, 86(4): 1091-1106.
[62] SUN Y C, ZHANG W, CHEN X. 3D seismic wavefield modeling in generally anisotropic media with a topographic free surface by the curvilinear grid finite-difference method[J]. Bulletin of the Seismological Society of America, 2018, 108(3A): 1287-1301.
[63] LEVANDER A R. Fourth-order finite-difference P-SV seismograms[J]. Geophysics, 1988, 53(11): 1425-1436.
[64] BERENGER J P. A perfectly matched layer for the absorption of electromagnetic waves[J]. Journal of computational physics, 1994, 114(2): 185-200.
[65] BASU U, CHOPRA A K. Perfectly matched layers for transient elastodynamics of unbounded domains[J]. International journal for numerical methods in engineering, 2004, 59(8): 1039-1074.
[66] FESTA G, DELAVAUD E, VILOTTE J P. Interaction between surface waves and absorbing boundaries for wave propagation in geological basins: 2D numerical simulations[J]. Geophysical Research Letters, 2005, 32(20).
[67] DROSSAERT F H, GIANNOPOULOS A. A nonsplit complex frequency-shifted PML based on recursive integration for FDTD modeling of elastic waves[J]. Geophysics, 2007, 72(2):T9-T17.
[68] ZHANG W, SHEN Y. Unsplit complex frequency-shifted PML implementation using auxiliary differential equations for seismic wave modeling[J]. Geophysics, 2010, 75(4): T141-T154.
[69] SAAD O M, CHEN Y. Deep denoising autoencoder for seismic random noise attenuation[J]. Geophysics, 2020, 85(4): V367-V376.
[70] KAUR H, FOMEL S, PHAM N. Seismic ground-roll noise attenuation using deep learning[J]. Geophysical Prospecting, 2020, 68(7): 2064-2077.
[71] QIAN F, YIN M, LIU X Y, et al. Unsupervised seismic facies analysis via deep convolutional autoencoders[J]. Geophysics, 2018, 83(3): A39-A43.
[72] LIU M, JERVIS M, LI W, et al. Seismic facies classification using supervised convolutional neural networks and semisupervised generative adversarial networks[J]. Geophysics, 2020, 85 (4): O47-O58.
[73] GENG Z, WANG Y. Automated design of a convolutional neural network with multi-scale filters for cost-efficient seismic data classification[J]. Nature communications, 2020, 11(1):3311.
[74] MOSELEY B, MARKHAM A, NISSEN-MEYER T. Solving the wave equation with physicsinformed deep learning[A]. 2020.
[75] SONG C, ALKHALIFAH T, WAHEED U B. Solving the frequency-domain acoustic VTI wave equation using physics-informed neural networks[J]. Geophysical Journal International, 2021, 225(2): 846-859.
[76] GATTI F, CLOUTEAU D. Towards blending Physics-Based numerical simulations and seismic databases using Generative Adversarial Network[J]. Computer Methods in Applied Mechanics and Engineering, 2020, 372: 113421.
[77] MÜNCHMEYER J, BINDI D, LESER U, et al. The transformer earthquake alerting model: A new versatile approach to earthquake early warning[J]. Geophysical Journal International, 2021, 225(1): 646-656.
[78] KHOSRAVIKIA F, CLAYTON P, NAGY Z. Artificial neural network-based framework for developing ground-motion models for natural and induced earthquakes in Oklahoma, Kansas, and Texas[J]. Seismological Research Letters, 2019, 90(2A): 604-613.
[79] JOZINOVIĆ D, LOMAX A, ŠTAJDUHAR I, et al. Transfer learning: Improving neural network based prediction of earthquake ground shaking for an area with insufficient training data[J]. Geophysical Journal International, 2022, 229(1): 704-718.
[80] BEROZA G C, SEGOU M, MOSTAFA MOUSAVI S. Machine learning and earthquake forecasting—next steps[J]. Nature communications, 2021, 12(1): 4761.
[81] MIGNAN A, BROCCARDO M. Neural network applications in earthquake prediction (1994–2019): Meta-analytic and statistical insights on their limitations[J]. Seismological Research Letters, 2020, 91(4): 2330-2342.
[82] JOHNSON P A, ROUET-LEDUC B, PYRAK-NOLTE L J, et al. Laboratory earthquake forecasting:A machine learning competition[J]. Proceedings of the national academy of sciences, 2021, 118(5): e2011362118.
[83] ARAYA-POLO M, JENNINGS J, ADLER A, et al. Deep-learning tomography[J]. The Leading Edge, 2018, 37(1): 58-66.
[84] DAS V, POLLACK A, WOLLNER U, et al. Convolutional neural network for seismicimpedance inversion[J]. Geophysics, 2019, 84(6): R869-R880.
[85] DAS V, MUKERJI T. Petrophysical properties prediction from prestack seismic data using convolutional neural networks[J]. Geophysics, 2020, 85(5): N41-N55.
[86] MÜNCHMEYER J, BINDI D, LESER U, et al. Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network[J]. Geophysical Journal International, 2021, 226(2): 1086-1104.
[87] MOUSAVI S M, BEROZA G C. Bayesian-deep-learning estimation of earthquake location from single-station observations[A]. 2019.
[88] SMITH J D, ROSS Z E, AZIZZADENESHELI K, et al. HypoSVI: Hypocentre inversion with Stein variational inference and physics informed neural networks[J]. Geophysical Journal International, 2022, 228(1): 698-710.
[89] SEYDOUX L, BALESTRIERO R, POLI P, et al. Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning[J]. Nature communications, 2020, 11(1): 3972.
[90] MIN E, GUO X, LIU Q, et al. A survey of clustering with deep learning: From the perspective of network architecture[J]. IEEE Access, 2018, 6: 39501-39514.
[91] BARKAOUI S, LOGNONNÉ P, KAWAMURA T, et al. Anatomy of continuous Mars SEIS and pressure data from unsupervised learning[J]. Bulletin of the Seismological Society of America, 2021, 111(6): 2964-2981.
[92] 张 ZhangAston, 李沐, 美立顿 LiptonZachary C., 等. 动手学深度学习[M]. 动手学深度学习, 2019.
[93] ZHANG A, LIPTON Z C, LI M, et al. Dive into Deep Learning[M/OL]. Cambridge University Press, 2023. https://D2L.ai.
[94] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by backpropagating errors[J]. nature, 1986, 323(6088): 533-536.
[95] HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural computation, 2006, 18(7): 1527-1554.
[96] GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]//Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 2011: 315-323.
[97] MAAS A L, HANNUN A Y, NG A Y, et al. Rectifier nonlinearities improve neural network acoustic models[C]//Proc. icml: Vol. 30. Atlanta, GA, 2013: 3.
[98] BRIDLE J. Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters[J]. Advances in neural information processing systems, 1989, 2.
[99] 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.
[100] BOSER B E, GUYON I M, VAPNIK V N. A training algorithm for optimal margin classifiers[C]//Proceedings of the fifth annual workshop on Computational learning theory. 1992: 144- 152.
[101] BROMLEY J, GUYON I, LECUN Y, et al. Signature verification using a” siamese” time delay neural network[J]. Advances in neural information processing systems, 1993, 6.
[102] SCHOLKOPF B, SUNG K K, BURGES C J, et al. Comparing support vector machines with Gaussian kernels to radial basis function classifiers[J]. IEEE transactions on Signal Processing, 1997, 45(11): 2758-2765.
[103] MORGAN J N, SONQUIST J A. Problems in the analysis of survey data, and a proposal[J].Journal of the American statistical association, 1963, 58(302): 415-434.
[104] BREIMAN L. Random forests[J]. Machine learning, 2001, 45: 5-32.
[105] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25.
[106] HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37 (9): 1904-1916.
[107] LECUN Y, BOTTOU L, ORR G B, et al. Efficient backprop[M]//Neural networks: Tricks of the trade. Springer, 2002: 9-50.
[108] KROGH A, HERTZ J. A simple weight decay can improve generalization[J]. Advances in neural information processing systems, 1991, 4.
[109] IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]//International conference on machine learning. pmlr, 2015: 448-456.
[110] HINTON G E, SRIVASTAVA N, KRIZHEVSKY A, et al. Improving neural networks by preventing co-adaptation of feature detectors[A]. 2012.
[111] SRIVASTAVA N. Improving neural networks with dropout[J]. University of Toronto, 2013, 182(566): 7.
[112] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. The journal of machine learning research, 2014, 15(1): 1929-1958.
[113] BOUTHILLIER X, KONDA K, VINCENT P, et al. Dropout as data augmentation[A]. 2015.
[114] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587.
[115] GIRSHICK R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.
[116] REN S, HE K, GIRSHICK R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28.
[117] LIU W, ANGUELOV D, ERHAN D, et al. Ssd: Single shot multibox detector[C]//Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14,2016, Proceedings, Part I 14. Springer, 2016: 21-37.
[118] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2016: 779-788.
[119] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7263-7271.
[120] REDMON J, FARHADI A. Yolov3: An incremental improvement[A]. 2018.
[121] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: Optimal speed and accuracy of object detection[A]. 2020.
[122] GE Z, LIU S, WANG F, et al. Yolox: Exceeding yolo series in 2021[A]. 2021.
[123] LI C, LI L, JIANG H, et al. YOLOv6: A single-stage object detection framework for industrial applications[A]. 2022.
[124] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 7464-7475.
[125] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9.
[126] NEUBECK A, VAN GOOL L. Efficient non-maximum suppression[C]//18th international conference on pattern recognition (ICPR’06): Vol. 3. IEEE, 2006: 850-855.
[127] BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS–improving object detection with one line of code[C]//Proceedings of the IEEE international conference on computer vision. 2017:5561-5569.
[128] JIANG B, LUO R, MAO J, et al. Acquisition of localization confidence for accurate object detection[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 784-799.
[129] LIU S, HUANG D, WANG Y. Adaptive nms: Refining pedestrian detection in a crowd[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019:6459-6468.
[130] DENG J, DONG W, SOCHER R, et al. Imagenet: A large-scale hierarchical image database [C]//2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009: 248-255.
[131] ZHEBEL O, EISNER L. Simultaneous microseismic event localization and source mechanism determination[J]. Geophysics, 2015, 80(1): KS1-KS9.
[132] ZHEBEL O, EISNER L. Simultaneous microseismic event localization and source mechanism determination: 82nd Annual International Meeting, SEG[J]. Expanded Abstracts, doi, 2012,10: 1190.
[133] ANIKIEV D, VALENTA J, STANĚK F, et al. Joint location and source mechanism inversion of microseismic events: Benchmarking on seismicity induced by hydraulic fracturing[J]. Geophysical Journal International, 2014, 198(1): 249-258.
[134] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[A]. 2014.
[135] 李庶林. 试论微震监测技术在地下工程中的应用[J]. 地下空间与工程学报, 2009, 1.
[136] XU J, ZHANG W, LIANG X, et al. Joint microseismic moment-tensor inversion and location using P-and S-wave diffraction stacking[J]. Geophysics, 2021, 86(6): KS137-KS150.
[137] FARR T G, ROSEN P A, CARO E, et al. The shuttle radar topography mission[J]. Reviews of geophysics, 2007, 45(2).
[138] LI Z, YONG P, HUANG J, et al. Elastic wave reverse time migration based on vector wavefield seperation[J]. Journal of China University of Petroleum (in Chinese), 2016, 40(1): 42-48.
[139] ATKINSON G M, EATON D W, IGONIN N. Developments in understanding seismicity triggered by hydraulic fracturing[J]. Nature Reviews Earth & Environment, 2020, 1(5): 264-277.
[140] YANG S, HU J, ZHANG H, et al. Simultaneous earthquake detection on multiple stations via a convolutional neural network[J]. Seismological Society of America, 2021, 92(1): 246-260.