Abstract
Nowadays, the already-existing earthquake catalogs are abundant, which can be used as the basic statistics for the research and prediction of aftershocks. There is plenty of information on the radiation of earthquake energy and the focal mechanism solution. Moreover, it contains a lot of seismic time and space correlation, most of which is hidden, unprecedented, and very hard to be described by geophysical formulas directly. Firstly, this study proposed a block supported vector regression algorithm in order to artificially study the correlation between main-shock parameters (magnitude, radiation energy, main-shock apparent stress, main-shock seismic moment, earthquake field, etc.) and aftershock parameters (magnitude, time, and space distance). Secondly, an interactive aftershock prediction software has been developed based on the C# language to conduct the research of aftershock prediction and application on real-time level.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Asim KM, Idris A, Iqbal T, Martínez-Álvarez F (2018) Earthquake prediction model using support vector regressor and hybrid neural networks. PLoS One 13(7):e0199004
Basak D, Pal S, Patranabis DC (2007) Support vector regression. Neural Inf Process 11(10):203–224
Bregman Y, Rabin N (2018) Aftershock identification using diffusion maps. Seismol Res Lett 90(2A):539–545
Chang CC, Lin CJ (2002) Training nu-support vector regression: theory and algorithms. Neural Comput 14:1959–1977
Chapelle O, Vapnik V, Bousoquet O (2002) Choosing multiple parameters for support vector machines. Mach Learn 46(1/3):131–159
Choy GL, Boatwrigh JL (1995) Global patterns of radiated seismic energy and apparent stress. J Geophys Res 100:18205–18228
Fu ZX, Lu XJ, Shao HC, D X (2008) Analysis on statistical characteristics of b values of aftershock series in China continent and its sub-regions. Earthquake 28(3):1–7
Guo L (2017) Research of regional correlation based on natural seismic data[D]. China University of Geosciences, Wuhan Shi
Huang FQ, Zhang XD, Cao CX, Li JP, Li SH (2007) The roadmap of numerical earthquake prediction in China. Recent Dev World Seismol 4:4–10
Huang FQ, Li M, Ma YC (2017) Studies on earthquake precursors in China: a review for recent 50 years. Geodesy Geodyn 8(1):1–12
Kaftan I, Salk M, Senol Y (2017) Processing of earthquake catalog data of Western Turkeywith artificial neuralnetworks and adaptive neuro-fuzzy inference system. Arab J Geosci 10(243):1–9
Last M, Rabinowitz N, Leonard G (2016) Predicting the maximum earthquake magnitude from seismic data in Israel and its neighboring countries. PLoS One 11(3):e0151751
Liu Y, Li G, Zhang B, Wu G (2005) Constructive ensemble of RBF neural networks and its application to earthquake prediction. Adv Neural Netw 3496:532–537
Panakkat A, Adeli H (2007) Neural network models for earthquake magnitude prediction using multiple seismicity indicators. Int J Neural Syst 17(01):13–33
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Duchesnay É (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830
Schubnel A, Brunet F, Hilairet N, Gasc J, Wang Y, Green HW (2013) Deep-focus earthquake analogs recorded at high pressure and temperature in the laboratory. Science 341(6152):1377–1380
Slinkard ME, Carr DB, Young CJ (2013) Applying waveform correlation to three aftershock sequences. Bull Seismol Soc Am 103(2A):675–693
Wang MF (2016) Research and software development on seismograph records vectorizing and earthquake catalogs data mining[D]. JiLin University, Changchun
Wang XL, Li ZB (2005) Identifying the parameters of the kernel function in support vector machines based on the grid-search method. J Ocean Univ China 35(5):859–862
Wang MF, Liu QJ, Feng JL, Zhang Z (2013) Energy field filling of NEIC broadband radiated energy catalogue based on method of least squares. Adv Mater Res 1339:760–762
Wiemer S, Wyss M (2000) Minimum magnitude of completeness in earthquake catalogs: examples from Alaska, the western United States, and Japan. Bull Seismol Soc Am 90(4):859–869
Wu ZH, Zhao GM (2013) The earthquake prediction status and related problems: a review. Geol Bull China 32(10):1493–1494
Zhang J, Wu SC, Wang W (2006) Research of data mining method on multivariable time series. Comput Eng Des 27(18):3364–3384
Computer code availability
Name of code: Maximum aftershock prediction, developer: Maofa Wang, telephone: +x8601082426111, email: wangmaofa2008@126.com, year first available: 2016, hardware required: i7 CPU and 2G RAM, software required: win7 or win 10, program language: C#, program size: 200 M, and you can access the software by downloading the software zip file.
Funding
We thank the financial support from National Natural Science Foundation of China (Researches on key algorithms and software development in analogue seismogram records vectorization, No: 41504037), the Supplementary and Supportive Project for Teachers at Beijing Information Science and Technology University (2018-2020) (No:5029011103), and the Key cultivation projects for Promoting the Interior Development of University (No: 5221823904).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Key Points
• Proposed a block SVR model of aftershock prediction based on the analysis of global earthquake catalogs.
• An interactive aftershock prediction software is developed.
• Conducted a predictive research of aftershock in near real-time.
Rights and permissions
About this article
Cite this article
Wang, M., Shen, J., Pan, Z.A. et al. An improved supported vector regression algorithm with application to predict aftershocks. J Seismol 23, 983–993 (2019). https://doi.org/10.1007/s10950-019-09848-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10950-019-09848-9