机器学习在地震预测中的应用进展

doi:10.12196/j.issn.1000-3274.2021.01.005

Abstract

Abstract: Machine learning (ML), especially deep learning (DL), has developed rapidly in recent years, which has made exciting progress in many applications such as data mining, computer vision, natural language processing, data feature extraction and prediction. Earthquake prediction is a complex, wide-ranging, immature, and controversial scientific issue. Its development is limited by unclear earthquake mechanisms and seismogenic structures, incomplete observation data, and unclear earthquake phenomena. However, machine learning may improve the mining and discovery of complex seismic data and promote the development of earthquake prediction science. This article reviews the application of machine learning in earthquake prediction, including the prediction of big earthquakes, big aftershocks and rock experimental fractures, finally looks forward to the research trends of machine learning in earthquake prediction.

Key words: Earthquake prediction, Earthquake precursor, Machine learning, Deep learning

CLC Number:

P315.7

YUAN Ai-jing, WANG Wei-jun, PENG Fei, YAN Kun, KOU Hua-dong. Recent Progress of Earthquake Prediction with Machine Learning[J]. EARTHQUAKE, 2021, 41(1): 51-66.

References

[1] 陈棋福. 汶川地震引发的中国地震预报探讨[J]. 第四纪研究, 2010, 30(4): 721-735.
CHEN Qi-fu. A discussions about the earthquake prediction in China after the 2008 Wenchuan earthquake[J]. Quaternary Sciences, 2010, 30(4): 721-735 (in Chinese).
[2] Wang K, Chen Q F, Sun S, et al. Predicting the 1975 Haicheng earthquake[J]. Bulletin of the Seismological Society of America, 2006, 96(3): 757-795.
[3] National Research Council. Predicting earthquakes: A scientific and technical evaluation, with implications for society[M]. National Academies, 1976.
[4] 张肇诚, 张炜. 地震预报可行性的科学与实践问题讨论[J]. 地震学报, 2016, 38(4): 564-579.
ZHANG Zhao-cheng, ZHANG Wei. Discussion on scientific and practical problems of feasibility of earthquake prediction[J]. Acta Seismologica Sinica, 2016, 38(4): 564-579 (in Chinese).
[5] 李世煇. 地震预测预报能与不能的争论[J]. 太原师范学院学报(社会科学版), 2012, 11(2): 1-9.
LI Shi-hui. Dispute on capability and incapability for earthquake prediction and forecast[J]. Journal of Taiyuan Normal University (Social Science Edition), 2012, 11(2): 1-9 (in Chinese).
[6] Geller R J, Jackson D D, Kagan Y Y, et al. Earthquakes cannot be predicted[J]. Science, 1997, 275(5306): 1616.
[7] 吴忠良, 蒋长胜. 地震前兆检验的地球动力学问题对地震预测问题争论的评述(之三)[J]. 中国地震, 2006, 22(3): 236-241.
WU Zhong-liang, JIANG Chang-sheng. Performance evaluation and statistical test of candidate earthquake precursors: Revisit in the perspective of geodynamicsCritical review on the recent earthquake prediction debate[J]. Earthquake Research In China, 2006, 22(3): 236-241 (in Chinese).
[8] Wyss M. Evaluation of proposed earthquake precursors[J]. Eos Transactions American Geophysical Union, 1991, 72(38): 411.
[9] Wyss M, Dmowska R. Earthquake prediction-state of the art[J]. Pure and Applied Geophysics, 1997, 149(1).
[10] Wyss M. Second round of evaluations of proposed earthquake precursors[J]. Pure and Applied Geophysics, 1997, 149(1): 3-16.
[11] Trugman D T, Ross Z E. Pervasive foreshock activity across southern California[J]. Geophysical Research Letters, 2019, 46(15): 8772-8781.
[12] Michie D, Spiegelhalter D J, Taylor C. Machine learning[J]. Neural and Statistical Classification, 1994, 13(1994): 1-298.
[13] LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.
[14] Schmidhuber J. Deep learning in neural networks: An overview[J]. Neural networks, 2015, 61: 85-117.
[15] Dramsch J S. Machine learning in 4D seismic data analysis: Deep neural networks in geophysics[D]. Technical University of Denmark, 2019.
[16] Alarifi A S N, Alarifi N S N, Al-Humidan S. Earthquakes magnitude predication using artificial neural network in northern Red Sea area[J]. Journal of King Saud University- Science, 2012, 24(4): 301-313.
[17] Panakkat A, Adeli H. Neural network models for earthquake magnitude prediction using multiple seismicity indicators[J]. International Journal of Neural Systems, 2007, 17(1): 13-33.
[18] Adeli H, Panakkat A. A probabilistic neural network for earthquake magnitude prediction[J]. Neural Networks, 2009, 22(7): 1018-1024.
[19] Asim K M, Adnan I, Talat I, et al. Earthquake prediction model using support vector regressor and hybrid neural networks[J]. Plos One, 2018, 13(7): e0199004.
[20] Asencio-Cortés G, Morales-Esteban A, Shang X, et al. Earthquake prediction in California using regression algorithms and cloud-based big data infrastructure[J]. Computers and Geosciences, 2018, 115: 198-210.
[21] Rouet-Leduc B, Hulbert C, Lubbers N, et al. Machine learning predicts laboratory earthquakes[J]. Geophysical Research Letters, 2017, 44(18): 9276-9282.
[22] Ren C X, Peltier A Ferrazzini V, et al. Machine learning reveals the seismic signature of eruptive behavior at piton de la fournaise volcano[J]. Geophysical Research Letters, 2020, 47(3): e2019GL085523.
[23] 马士振, 刘宏志, 牟磊育. 在地脉动数据上应用分类算法的地震预测实验[J]. 地震, 2020, 40(1): 159-171.
MA Shi-zhen, LIU Hong-zhi, MU Lei-yu. Earthquake forecast experiment with classification algorithm based on microtremor date[J]. Earthquake, 2020, 40(1): 159-171 (in Chinese).
[24] Corbi F, Sandri L, Bedford J, et al. Machine learning can predict the timing and size of analog earthquakes[J]. Geophysical Research Letters, 2019, 46(3): 1303-1311.
[25] Nicolis O, Plaza F, Salas R. Prediction of intensity and location of seismic events using deep learning[J]. Spatial Statistics, 2020, 100442.
[26] DeVries P M R, Viégas F, Wattenberg M, et al. Deep learning of aftershock patterns following large earthquakes[J]. Nature, 2018, 560(7720): 632-634.
[27] 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.
[28] Molchan G M, Dmitrieva O E. Aftershock identification: Methods and new approaches[J]. Geophysical Journal International, 1992, 109(3): 501-516.
[29] King G C P, Stein R S, Lin J. Static stress changes and the triggering of earthquakes[J]. Bulletin of the Seismological Society of America, 1994, 84(3): 935-953.
[30] Alves E I. Earthquake forecasting using neural networks: Results and future work[J]. Nonlinear Dynamics, 2006, 44(1-4): 341-349.
[31] Gutenberg B. Elementary seismology[J]. Engineering and Science, 1958, 22(2): 10-10.
[32] Moustra M, Avraamides M, Christodoulou C. Artificial neural networks for earthquake prediction using time series magnitude data or Seismic Electric Signals[J]. Expert Systems with Applications, 2011, 38(12): 15032-15039.
[33] Asencio-Cortés G, Scitovski S, Scitovski R, et al. Temporal analysis of croatian seismogenic zones to improve earthquake magnitude prediction[J]. Earth Science Informatics, 2017, 10(3): 303-320.
[34] Asencio-Cortés G, Martínez-álvarez F, Troncoso A, et al. Medium-large earthquake magnitude prediction in Tokyo with artificial neural networks[J]. Neural Computing and Applications, 2017, 28(5): 1043-1055.
[35] Li R, Lu X B, Li S W, et al. DLEP: A deep learning model for earthquake prediction[C]. 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020: 1-8.
[36] Reyes J, Morales-Esteban A, Martínez-álvarez F. Neural networks to predict earthquakes in Chile[J]. Applied Soft Computing Journal, 2013, 13(2): 1314-1328.
[37] Asim K M, Martínez-álvarez F, Basit A, et al. Earthquake magnitude prediction in Hindukush region using machine learning techniques[J]. Natural Hazards, 2017, 85(1): 471-486.
[38] Asim K M, Idris A, Iqbal T, et al. Seismic indicators based earthquake predictor system using Genetic Programming and AdaBoost classification[J]. Soil Dynamics and Earthquake Engineering, 2018, 111: 1-7.
[39] Asim K M, Moustafa S S, Niaz I A, et al. Seismicity analysis and machine learning models for short-term low magnitude seismic activity predictions in Cyprus[J]. Soil Dynamics and Earthquake Engineering, 2020, 130: 105932.
[40] Huang J P, Wang X A, Zhao Y, et al. Large earthquake magnitude prediction in Taiwan based on deep learning neural network[J]. Neural Network World, 2018, 28(2): 149-160.
[41] Plaza F, Salas R, Nicolis O. Assessing seismic hazard in chile using deep neural networks[M]∥Natural Hazards-Risk, Exposure, Response, and Resilience. IntechOpen, 2019.
[42] Rundle J B, Donnellan A. Nowcasting earthquakes in southern california with machine learning: Bursts, swarms, and aftershocks may be related to levels of regional tectonic stress[J]. Earth and Space Science, 2020, 7(9): e2020EA001097.
[43] Mignan A, Broccardo M. A Deeper Look into “deep learning of aftershock patterns following large earthquakes”: Illustrating first principles in neural network physical interpretability[C]. International Work-Conference on Artificial Neural Networks. Springer, Cham, 2019: 3-14.
[44] Rouet-Leduc B , Hulbert C, Bolton D C, et al. Estimating fault friction from seismic signals in the laboratory[J]. Geophysical Research Letters, 2018, 45(3): 1321-1329.
[45] Rouet-Leduc B, Hulbert C, McBrearty I W, et al. Probing slow earthquakes with deep learning[J]. Geophysical Research Letters, 2020, 47(4): e2019GL085870.
[46] Rouet-Leduc B, Hulbert C, Johnson P A. Continuous chatter of the Cascadia subduction zone revealed by machine learning[J]. Nature Geoscience, 2019, 12(1): 75-79.
[47] Corbi F, Bedford J, Sandri L, et al. Predicting imminence of analog megathrust earthquakes with Machine Learning: Implications for monitoring subduction zones[J]. Geophysical Research Letters, 2020, 47(7): e2019GL086615.
[48] Hulbert C, Rouet-Leduc B, Johnson P A, et al. Similarity of fast and slow earthquakes illuminated by machine learning[J]. Nature Geoscience, 2019, 12(1): 69-74.
[49] Ren C X, Dorostkar O, Rouet-Leduc B, et al. Machine learning reveals the state of intermittent frictional dynamics in a sheared granular fault[J]. Geophysical Research Letters, 2019, 46(13): 7395-7403.
[50] Biswas S, Castellanos D F, Zaiser M. Prediction of creep failure time using machine learning[J]. arXiv preprint arXiv: 2005.03514, 2020.

Recent Progress of Earthquake Prediction with Machine Learning

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	WANG Xi-long, JIA Xiao-dong, QIAN Rui, FU Cong. Analysis on Anomalous Characteristics and Earthquake Prediction Efficiency of High-frequency Information from Digital Water Level and Water Temperature before 2013 Lushan M7.0 Earthquake in the North-South Seismic Belt of China [J]. EARTHQUAKE, 2020, 40(2): 100-116.
[2]	XU Zhong-huai. In Search of a New Physical Basis for Large Earthquake Prediction [J]. EARTHQUAKE, 2019, 39(2): 11-18.
[3]	LI Yan-e, CHEN Xue-zhong. Coulomb Stress Changes Imparted in the Rupture Zones of the Lushan Earthquake and the Kangding Earthquake by the 2008 Wenchuan M_S8.0 Earthquake [J]. EARTHQUAKE, 2019, 39(1): 136-145.
[4]	SHI Fu-qiang, SHAO Zhi-gang, ZHU Lin, ZHANG Zhu-qi, SHAO Hui-cheng. Earthquake Science on the Western Coast of South American (Chile)and Implications for Earthquake Prediction: An Overview [J]. EARTHQUAKE, 2019, 39(1): 155-170.
[5]	ZHANG Guo-qing, ZHU Yi-qing, LIANG Wei-feng, GUO Shu-song, WEI Shou-chun. Spatial Patterns of Regional Gravity Changes before the 2008 and 2014 Yutian M_S7.3 Earthquakes [J]. EARTHQUAKE, 2018, 38(4): 14-21.
[6]	LI Li, WANG Xia, SONG Mei-qin, WU Hao-yu, LIANG Yan. Earthquake Prediction Effectiveness based on Anomaly Judgement of Datong Window [J]. EARTHQUAKE, 2018, 38(4): 142-150.
[7]	XIANG Yang, SUN Xiao-long, WANG Bo. Earthquake Prediction Efficiency Testing of Observed Fluid Data in Xinjiang using Molchan Diagram Method [J]. EARTHQUAKE, 2018, 38(3): 103-114.
[8]	YANG Si-yu, YI Li, WANG Shuang-jie. Experiment of Hydrochemical Changes in Granite-water Reaction [J]. EARTHQUAKE, 2018, 38(3): 115-122.
[9]	SHAO Zhi-gang, WANG Peng. Reflections on Earthquake Prediction Research Ten Years after the 2008 Wenchuan M_S8.0 Earthquake [J]. EARTHQUAKE, 2018, 38(2): 1-10.
[10]	WANG Xi-long, JIA Xiao-dong, WANG Bo, WANG Yi-xi, WANG Jun, XIANG Yang, JIN Hao, FU Cong. Extracting High-frequency Anomaly from Digital Underground Fluid Data: A Case Study of the 2014 Ludian M_S6.5 Earthquake [J]. EARTHQUAKE, 2018, 38(1): 35-48.
[11]	LIU Yi, ZHOU Chen, ZHAO Zheng-yu, ZHAO Shu-fan, ZHANG Xue-min, KONG Jian. Seismo-ionospheric Disturbance Based on LAIC Electric Field Penetration and SAMI2 Simulation [J]. EARTHQUAKE, 2018, 38(1): 74-83.
[12]	LIAO Xiao-feng, HE Kang, ZHANG Ming-dong, HE Chang, WEI Qiang. Time-frequency Analysis of Geomagnetic Data based on Smooth Pseudo-Wigner-Ville Distribution [J]. EARTHQUAKE, 2018, 38(1): 107-116.
[13]	WANG Yi-xi, LI He, WANG Bo, YANG Peng-tao, WANG Jun, XIANG Yang, WANG Xi-long, LI Yue. Critical Slow Down Phenomena of Radon Concentrations before the 2013 Minxian-Zhangxian M_S6.6 Earthquake [J]. EARTHQUAKE, 2018, 38(1): 128-138.
[14]	WANG Bo, ZHONG Jun, WANG Yi-xi, CHEN Shi. Testing the Forecast Efficiency of Underground Fluid Observation in the North Segment of North-South Seismic Belt [J]. EARTHQUAKE, 2018, 38(1): 147-156.
[15]	ZHANG Zhi-guang, ZHANG Yuan-sheng, WANG Zai-hua, XU Yan-gang. Precursory Anomalies of Thermal Infrared Brightness Temperature before the 2016 Litang M_S5.1 and Zaduo M_S6.2 Earthquakes [J]. EARTHQUAKE, 2018, 38(1): 178-186.