基于VMD-BP神经网络模型的地震三要素预测算法

doi:10.12196/j.issn.1000-3274.2025.01.011

摘要/Abstract

摘要： 地震灾害的发生具有突发性和瞬时性, 可能对人类社会产生巨大的影响, 造成严重的灾难。因此, 发展地震预测的相关理论和方法具有重要意义。本研究利用经典的反向传播(Back Propagation, BP)神经网络, 结合变分模态分解(Variational Mode Decomposition, VMD)技术对地震数据集进行预处理, 建立了一种新的VMD-BP地震预测模型。本研究对于地震目录中震级1.5级以上的每个条目, 都考虑了除震源深度以外的四个特征: 时间差、震级、纬度和经度, 将过去5个时间相邻地震事件的特征作为VMD-BP模型的输入, 并将下一个地震事件的特征作为输出, 通过构建4个VMD-BP模型分别对地震发震时间、震级、震中位置(纬度、经度)进行预测。对该模型在四川和西藏地区进行了实证分析。通过比较模型的性能参数, 我们发现VMD-BP模型比BP模型的预测精度和拟合优度更好。这表明基于VMD-BP的模型能够更为准确地进行地震预测, 为未来地震预测的深入研究提供了有益参考。

关键词: 地震预测, BP神经网络, 变分模态分解, 深度学习

Abstract: The occurrence of an earthquake is instantaneous and destructive, which may cause serious disaster to human society. Therefore, the development of relevant theories and methods for earthquake prediction is of great significance. In this study, classical back propagation (BP) neural network and variational mode decomposition (VMD) technology are combined to develop a new VMD-BP earthquake prediction model. Four VMD-BP models were constructed to predict the time, magnitude, and location (latitude and longitude) of earthquakes. For each entry in the earthquake catalog, four features other than the depth of the earthquake source are considered: time difference, magnitude, latitude, and longitude. The past five adjacent seismic events was used as the input to the VMD-BP model, and the next seismic event was used as the output. The model was empirically analyzed in the Sichuan and Xizang regions. By comparing the prediction performance of the models, it is concluded that the VMD-BP model has better prediction accuracy and goodness of fit than the BP model. It illustrates that the VMD-based model can make more accurate earthquake prediction, which will provide useful references for future in-depth research on earthquake prediction.

Key words: Earthquake prediction, BP neural network, Variational mode decomposition, Deep learning

中图分类号:

P315.7

张家琪, 贺茜君, 王启阅. 基于VMD-BP神经网络模型的地震三要素预测算法[J]. 地震, 2025, 45(1): 161-180.

ZHANG Jia-qi, HE Xi-jun, WANG Qi-yue. Three Elements Earthquake Prediction Method Using VMD-BP Neural Network Model[J]. EARTHQUAKE, 2025, 45(1): 161-180.

参考文献

[1] 王锦红, 蒋海昆. 基于地震观测数据的机器学习地震预测研究综述[J]. 地震研究, 2023, 46(2): 173-187.
WANG Jin-hong, JIANG Hai-kun. Research progress in field of earthquake prediction by machine learning based on seismic data[J]. Journal of Seismological Research, 2023, 46(2): 173-187 (in Chinese).
[2] Moratto L, Orlecka-Sikora B, Costa G, et al. A deterministic seismic hazard analysis for shallow earthquakes in Greece[J]. Tectonophysics, 2007, 442(1-4): 66-82.
[3] 陈棋福, 李乐, 姜金钟. 中国大陆强震孕育深处的变形模式构建[J]. 地震研究, 2020, 43(2): 232-240.
CHEN Qi-fu, LI Le, JIANG Jin-zhong. Deep deformation pattern of strong earthquake in Chinese mainland[J]. Journal of Seismological Research, 2020, 43(2): 232-240 (in Chinese).
[4] 王坦, 李瑜, 张锐, 等. GPS在我国地震监测中的应用现状与发展展望[J]. 地震研究, 2021, 44(2): 192-207.
WANG Tan, LI Yu, ZHANG Rui, et al. GPS in earthquake monitoring in China: Current situation and prospect[J]. Journal of Seismological Research, 2021, 44(2): 192-207 (in Chinese).
[5] Gutenberg B, Richter C F. Frequency of earthquakes in California[J]. Bulletin of the Seismological Society of America, 1944, 34(4): 185-188.
[6] Cornell C A. Engineering seismic risk analysis[J]. Bulletin of the seismological society of America, 1968, 58(5): 1583-1606.
[7] Papanastassiou D, Latoussakis J, Stavrakakis G, et al. The Aegean Sea (Greece) earthquake sequence of 25 March 1986: An application of the v-value method for earthquake prediction[J]. Natural Hazards, 1989, 2: 105-114.
[8] Zhuang J, Ogata Y, Vere-Jones D. Stochastic declustering of space-time earthquake occurrences[J]. Journal of the American Statistical Association, 2011, 97(458): 369-380.
[9] Shebalin P N, Narteau C, Zechar J D, et al. Combining earthquake forecasts using differential probability gains[J]. Earth, Planets and Space, 2014, 66(1): 37.
[10] Shcherbakov R, Zhuang J C, Zöller G, et al. Forecasting the magnitude of the largest expected earthquake[J]. Nature Communications, 2019, 10(1): 4051.
[11] Hashemi S M, Negarestani A, Namvaran M, et al. An analytical algorithm for designing radon monitoring network to predict the location and magnitude of earthquakes[J]. Journal of Radioanalytical and Nuclear Chemistry, 2013, 295(3): 2249-2262.
[12] 赵永红, 谢雨晴, 王航, 等. 地震预测方法Ⅴ: 地下流体方法[J]. 地球物理学进展, 2017, 32(4): 1539-1547.
ZHAO Yong-hong, XIE Yu-qing, WANG Hang, et al. Earthquake prediction V: Subsurface fluid method[J]. Progress in Geophysics, 2017, 32(4): 1539-1547 (in Chinese).
[13] Iwata T, Umeno K. Preseismic ionospheric anomalies detected before the 2016 Kumamoto earthquake[J]. Journal of Geophysical Research: Space Physics, 2017, 122(3): 3602-3616.
[14] Stephens M. Gravitational disturbances could predict earthquake size[J]. Physics World, 2018, 31(1): 5.
[15] Schmidhuber J. Deep learning in neural networks: An overview[J]. Neural Networks, 2015, 61: 85-117.
[16] Mignan A, Broccardo M. One neuron versus deep learning in aftershock prediction[J]. Nature, 2019, 574: E1-E3.
[17] 袁爱璟, 王伟君, 彭菲, 等. 机器学习在地震预测中的应用进展[J]. 地震, 2021, 41(1): 51-66.
YUAN Ai-jing, WANG Wei-jun, PENG Fei, et al. Recent progress of earthquake prediction with machine learning[J]. Earthquake, 2021, 41(1): 51-66 (in Chinese).
[18] 胡琪鑫, 徐亚. 地球物理信号特征识别与解释的机器学习方法及应用综述[J]. 地球物理学进展, 2022, 37(6): 2395-2407.
HU Qi-xin, XU Ya. Review of machine learning and application of geophysical signal feature recognition and interpretation[J]. Progress in Geophysics, 2022, 37(6): 2395-2407 (in Chinese).
[19] 贾漯昭, 孟令媛, 闫睿. 深度学习在地震监测预报中的应用进展[J]. 地震研究, 2024, 47(3): 336-349.
JIA Luo-zhao, MENG Ling-yuan, YAN Rui. Advancements of deep learning in seismic monitoring and prediction[J]. Journal of Seismological Research, 2024, 47(3): 336-349 (in Chinese).
[20] 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.
[21] González J, Yu W, Telesca L. Earthquake magnitude prediction using recurrent neural networks[J]. Multidisciplinary Digital Publishing Institute Proceedings, 2019, 24(1): 22.
[22] Wu H, Zhang B, Lin T F, et al. White noise attenuation of seismic trace by integrating variational mode decomposition with convolutional neural network[J]. Geophysics, 2019, 84(5): V307-V317.
[23] Mousavi S M, Beroza G C. A machine-learning approach for earthquake magnitude estimation[J]. Geophysical Research Letters, 2020, 47(1): e2019GL085976.
[24] 冯德益, 蒋淳, 汪德馨, 等. 神经网络方法在地震预报研究中的初步应用[J]. 地震, 1994, 14(4): 23-29.
FENG De-yi, JIANG Chun, WANG De-xin, et al. Preliminary application of neural network method in earthquake prediction research[J]. Earthquake, 1994, 14(4): 23-29 (in Chinese).
[25] Narayanakumar S, Raja K. A BP artificial neural network model for earthquake magnitude prediction in Himalayas, India[J]. Circuits and Systems, 2016, 7(11): 3456-3468.
[26] 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: 471-486.
[27] Perol T, Gharbi M, Denolle M. Convolutional neural network for earthquake detection and location[J]. Science Advances, 2018, 4(2): e1700578.
[28] 杨黎薇, 林国良, 邱志刚, 等. 基于人工神经元网络和多特征参数的预警震级估算[J]. 地震研究, 2018, 41(2): 302-310.
YANG Li-wei, LIN Guo-liang, QIU Zhi-gang, et al. Study on magnitude estimation of earthquake early warning based on various characteristic parameters and artificial neural networks[J]. Journal of Seismological Research, 2018, 41(2): 302-310 (in Chinese).
[29] Berhich A, Belouadha F Z, Kabbaj M I. LSTM-based models for earthquake prediction[C]//Proceedings of the 3rd International Conference on Networking, Information Systems & Security, 2020: 1-7.
[30] Huang X, Song J Y, Jin H D. The casualty prediction of earthquake disaster based on extreme learning machine method[J]. Natural Hazards, 2020, 102(3): 873-886.
[31] 刘杰, 曹俊兴, 蒋旭东, 等. 基于GRU的汶川地震川西气井压力前兆异常识别研究[J]. 地球物理学进展, 2021, 36(3): 901-907.
LIU Jie, CAO Jun-xing, JIANG Xu-dong, et al. Research on recognition of pressure precursor anomaly of Gas well in western Sichuan before Wenchuan earthquake based on GRU[J]. Progress in Geophysics, 2021, 36(3): 901-907 (in Chinese).
[32] 郭少文, 雷奇果, 周坤. 极震区烈度的ELM预测模型[J]. 华南地震, 2022, 42(1): 140-146.
GUO Shao-wen, LEI Qi-guo, ZHOU Kun. Seismic intensity prediction model in meizoseismal area based on ELM[J]. South China Journal of Seismology, 2022, 42(1): 140-146 (in Chinese).
[33] Dragomiretskiy K, Zosso D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2013, 62(3): 531-544.
[34] 刘长良, 武英杰, 甄成刚. 基于变分模态分解和模糊C均值聚类的滚动轴承故障诊断[J]. 中国电机工程学报, 2015, 35(13): 3358-3365.
LIU Chang-liang, WU Ying-jie, ZHEN Cheng-gang. Rolling bearing fault diagnosis based on variational mode decomposition and fuzzy C means clustering[J]. Proceedings of the CSEE, 2015, 35(13): 3358-3365 (in Chinese).
[35] Ling Q, Zhang Q, Zhang J, et al. Prediction of landslide displacement using multi-kernel extreme learning machine and maximum information coefficient based on variational mode decomposition: A case study in Shaanxi, China[J]. Natural Hazards, 2021, 108: 925-946.
[36] 闫洪波, 沈雅楠, 那毅然. 基于二维变分模态分解与自适应分数阶积分的图像去噪方法[J]. 科学技术与工程, 2022, 22(7): 2800-2805.
YAN Hong-bo, SHEN Ya-nan, NA Yi-ran. Image denoising method based on two-dimensional variational modal decomposition and adaptive fractional integration[J]. Science Technology and Engineering, 2022, 22(7): 2800-2805 (in Chinese).
[37] Tiu E S K, Huang Y F, Ng J L, et al. An evaluation of various data pre-processing techniques with machine learning models for water level prediction[J]. Natural Hazards, 2022, 110: 121-153.
[38] Tripathy R K, Sharma L N, Dandapat S. Detection of shockable ventricular arrhythmia using variational mode decomposition[J]. Journal of Medical Systems, 2016, 40(4): 79.
[39] Xue Y J, Cao J X, Wang D X, et al. Application of the variational-mode decomposition for seismic time-frequency analysis[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(8): 3821-3831.
[40] Proao E, Benítez D S, Lara-Cueva R, et al. On the use of variational mode decomposition for seismic event detection[C]//2018 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC). IEEE, 2018: 1-6.
[41] Paternina M R A, Tripathy R K, Zamora-Mendez A, et al. Identification of electromechanical oscillatory modes based on variational mode decomposition[J]. Electric Power Systems Research, 2019, 167: 71-85.
[42] 华莉, 杨俭, 袁天辰, 等. 基于VMD和BP神经网络的轨道病害诊断方法[J]. 电子科技, 2022, 35(4): 40-46.
HUA Li, YANG Jian, YUAN Tian-chen, et al. Track disease diagnosis method based on VMD and BP neural network[J]. Electronic Science and Technology, 2022, 35(4): 40-46 (in Chinese).
[43] 李媛, 邓嘉瑞, 陈飞, 等. 基于VMD的非平稳地震动信号模拟[J]. 科技通报, 2023, 39(8): 94-99.
LI Yuan, DENG Jia-rui, CHEN Fei, et al. Simulation of non-stationary ground vibration signals based on VMD[J]. Bulletin of Science and Technology, 2023, 39(8): 94-99 (in Chinese).
[44] 王肖, 周怀来, 王元君, 等. 基于MP与GA-VMD结合的地震资料去噪方法研究[J]. 物探化探计算技术, 2023, 45(2): 156-168.
WANG Xiao, ZHOU Huai-lai, WANG Yuan-jun, et al. Research on seismic data denoising method based on MP and GA-VMD[J]. Computing Techniques for Geophysical and Geochemical Exploration, 2023, 45(2): 156-168 (in Chinese).