Waveform recognition and process interpretation of microseismic monitoring based on an improved LeNet5 convolutional neural network

Abstract

The development of high-precision and interpretable automatic waveform classification algorithms with strong adaptability is becoming increasingly significant under the background of the big data era of microseismicity. Considering the deficiency of the existing network in waveform recognition and classification, an improved model which is suitable for microseismic (MS) monitoring waveform recognition was proposed in this study based on the LeNet framework. The improved model was applied to investigate thirteen kinds of MS monitoring signals that appear within 8 months of the Hanjiang-to-Weihe River Diversion Project. The results show that the accuracy of the best framework in the improved model is 0.98, which is 0.1 higher than original model. The average precision, recall and F₁ values of all improved models increased by 0.11, 0.12 and 0.12, respectively. Meanwhile, the improved model can visualize the entire waveform recognition process. A novel observation is that in some signal categories, the improved model mainly classified by focusing on the background information instead of the waveforms. It provides a reference for the intelligent classification of signals in MS monitoring engineering.

Keywords

microseismic monitoring / waveform classification / improved LeNet / interpretable machine learning

References

[1] ChenS-j, FengF, WangY-j, et al. . Tunnel failure in hard rock with multiple weak planes due to excavation unloading of in situ stress [J]. Journal of Central South University, 2020, 27(10): 2864-2882

[2] LiX-l, ChenS-j, LiuS-m, et al. . AE waveform characteristics of rock mass under uniaxial loading based on Hilbert-Huang transform [J]. Journal of Central South University, 2021, 28(6): 1843-1856

[3] LiX-l, ChenS-j, WangE-y, et al. . Rockburst mechanism in coal rock with structural surface and the microseismic (MS) and electromagnetic radiation (EMR) response [J]. Engineering Failure Analysis, 2021, 124: 105396

[4] LiuJ-p, SiY-t, WeiD-c, et al. . Developments and prospects of microseismic monitoring technology in underground metal mines in China [J]. Journal of Central South University, 2021, 28(10): 3074-3098

[5] GongF-q, WangY-l, LuoSong. Rockburst proneness criteria for rock materials: Review and new insights [J]. Journal of Central South University, 2020, 27(10): 2793-2821

[6] LiP-x, FengX-t, FengG-l, et al. . Rockburst and microseismic characteristics around lithological interfaces under different excavation directions in deep tunnels [J]. Engineering Geology, 2019, 260105209

[7] LiuJ-p, FengX-t, LiY-h, et al. . Studies on temporal and spatial variation of microseismic activities in a deep metal mine [J]. International Journal of Rock Mechanics and Mining Sciences, 2013, 60171-179

[8] TangS-b, DongZ, WangJ-x, et al. . A numerical study of fracture initiation under different loads during hydraulic fracturing [J]. Journal of Central South University, 2020, 27(12): 3875-3887

[9] LiuF, MaT-h, TangC-a, et al. . Prediction of rockburst in tunnels at the Jinping II hydropower station using microseismic monitoring technique [J]. Tunnelling and Underground Space Technology, 2018, 81: 480-493

[10] MaT H, TangC A, TangL X, et al. . Rockburst characteristics and microseismic monitoring of deep-buried tunnels for Jinping II Hydropower Station [J]. Tunnelling and Underground Space Technology, 2015, 49: 345-368

[11] DongL-j, TangZ, LiX-b, et al. . Discrimination of mining microseismic events and blasts using convolutional neural networks and original waveform [J]. Journal of Central South University, 2020, 27(10): 3078-3089

[12] PHOON K K, ZHANG Wen-gang. Future of machine learning in geotechnics [J]. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, 2022: 1–16. DOI: https://doi.org/10.1080/17499518.2022.2087884.

[13] ZhangW-g, GuX, TangL-b, et al. . Application of machine learning, deep learning and optimization algorithms in geoengineering and geoscience: Comprehensive review and future challenge [J]. Gondwana Research, 2022, 109: 1-17

[14] ZhangW-g, LiH-r, LiY-q, et al. . Application of deep learning algorithms in geotechnical engineering: A short critical review [J]. Artificial Intelligence Review, 2021, 54(8): 5633-5673

[15] ZhangW-g, PhoonK K. Editorial for Advances and applications of deep learning and soft computing in geotechnical underground engineering [J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14(3): 671-673

[16] VallejosJ A, MckinnonS D. Logistic regression and neural network classification of seismic records [J]. International Journal of Rock Mechanics and Mining Sciences, 2013, 62: 86-95

[17] DongL-j, WesselooJ, PotvinY, et al. . Discrimination of mine seismic events and blasts using the fisher classifier, naive Bayesian classifier and logistic regression [J]. Rock Mechanics and Rock Engineering, 2016, 49(1): 183-211

[18] MalovichkoDDiscrimination of blasts in mine seismology [C], 2012, Perth, Australian Centre for Geomechanics: 161171

[19] ShangX-y, LiX-b, Morales-EstebanA, et al. . Improving microseismic event and quarry blast classification using artificial neural networks based on principal component analysis [J]. Soil Dynamics and Earthquake Engineering, 2017, 99: 142-149

[20] PuY-y, ApelD B, HallR. Using machine learning approach for microseismic events recognition in underground excavations: Comparison of ten frequently-used models [J]. Engineering Geology, 2020, 268: 105519

[21] FengG-l, ChenB-r, JiangQ, et al. . Excavation-induced microseismicity and rockburst occurrence: Similarities and differences between deep parallel tunnels with alternating soft-hard strata [J]. Journal of Central South University, 2021, 28(2): 582-594

[22] LiX-l, LiZ-h, WangE-y, et al. . Pattern recognition of mine microseismic and blasting events based on wave fractal features [J]. Fractals, 2018, 26(3): 1850029

[23] LiX-l, LiZ-h, WangE-y, et al. . Analysis of natural mineral earthquake and blast based on Hilbert-Huang transform (HHT) [J]. Journal of Applied Geophysics, 2016, 12879-86

[24] MousaviS M, ZhuW-q, ShengY-x, et al. . CRED: A deep residual network of convolutional and recurrent units for earthquake signal detection [J]. Scientific Reports, 2019, 9(1): 1-14

[25] ZhaoG-y, MaJ, DongL-j, et al. . Classification of mine blasts and microseismic events using starting-up features in seismograms [J]. Transactions of Nonferrous Metals Society of China, 2015, 25(10): 3410-3420

[26] ZHAO Zheng-guang, GROSS L. Using supervised machine learning to distinguish microseismic from noise events [C]//SEG Technical Program Expanded Abstracts. Houston, Texas: Society of Exploration Geophysicists, 2017: 2918–2923. DOI: https://doi.org/10.1190/segam2017-17727697.1.

[27] TaryJ B, HerreraR H, HanJ-j, et al. . Spectral estimation-What is new? What is next? [J]. Reviews of Geophysics, 2014, 52(4): 723-749

[28] WilkinsA H, StrangeA, DuanY, et al. . Identifying microseismic events in a mining scenario using a convolutional neural network [J]. Computers & Geosciences, 2020, 137104418

[29] BiL, XieW, ZhaoJ-jie. Automatic recognition and classification of multi-channel microseismic waveform based on DCNN and SVM [J]. Computers & Geosciences, 2019, 123111-120

[30] BiX, ZhangC, HeY, et al. . Explainable time — frequency convolutional neural network for microseismic waveform classification [J]. Information Sciences, 2021, 546: 883-896

[31] WangG, GongJunFacial expression recognition based on improved LeNet-5 CNN [C], 2019, Nanchang, China, IEEE: 56555660

[32] ZhangC-w, YangM-y, ZengH-j, et al. . Pedestrian detection based on improved LeNet-5 convolutional neural network [J]. Journal of Algorithms & Computational Technology, 2019, 13: 174830261987360

[33] LiangZ-z, XueR-x, XuN-w, et al. . Analysis on microseismic characteristics and stability of the access tunnel in the main powerhouse, Shuangjiangkou hydropower station, under high in situ stress [J]. Bulletin of Engineering Geology and the Environment, 2020, 79(6): 3231-3244

[34] LiuZ-h, JiaX-j, XuX-sheng. Study of shrimp recognition methods using smart networks [J]. Computers and Electronics in Agriculture, 2019, 165104926

[35] LiT-h, JinD, DuC-f, et al. . The image-based analysis and classification of urine sediments using a LeNet-5 neural network [J]. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2020, 8(1): 109-114

[36] ZhaoX-z, LiuL-y, QiS-l, et al. . Agile convolutional neural network for pulmonary nodule classification using CT images [J]. International Journal of Computer Assisted Radiology and Surgery, 2018, 13(4): 585-595

[37] DelG V, MuscilloS, WasowskiJ. What we can learn about slope response to earthquakes from ambient noise analysis: An overview [J]. Engineering Geology, 2014, 182182-200

[38] LiJ-m, TangS-b, LiK-y, et al. . Automatic recognition and classification of microseismic waveforms based on computer vision [J]. Tunnelling and Underground Space Technology, 2022, 121: 104327

[39] LecunY, BottouL, BengioY, et al. . Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324

[40] LIN Min, CHEN Qiang, YAN Shui-cheng. Network in network [J]. Computer Science, 2013. DOI: https://doi.org/10.48550/arXiv.1312.4400.

[41] IoffeS, SzegedyCBatch normalization: Accelerating deep network training by reducing internal covariate shift [C], 2015, New York, ACM: 448-456

[42] HuJ, ShenL, AlbanieS, et al. . Squeeze-and-excitation networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023

[43] FabijańskaA, DanekM, BarniakJ. Wood species automatic identification from wood core images with a residual convolutional neural network [J]. Computers and Electronics in Agriculture, 2021, 181105941