Application of neural network and ANFIS model for earthquake occurrence in Iran

Abstract

This study examined the spatial-temporal variations in seismicity parameters for the September 10th, 2008 Qeshm earthquake in south Iran. To this aim, artificial neural networks and Adaptive Neural Fuzzy Inference System (ANFIS) were applied. The supervised Radial Basis Function (RBF) network and ANFIS model were implemented because they have shown the efficiency in classification and prediction problems. The eight seismicity parameters were calculated to analyze spatial and temporal seismicity pattern. The data preprocessing that included normalization and Principal Component Analysis (PCA) techniques was led before the data was fed into the RBF network and ANFIS model. Although the accuracy of RBF network and ANFIS model could be evaluated rather similar, the RBF exhibited a higher performance than the ANFIS for prediction of the epicenter area and time of occurrence of the 2008 Qeshm main shock. A proper training on the basis of RBF network and ANFIS model might adopt the physical understanding between seismic data and generate more effective results than conventional prediction approaches. The results of the present study indicated that the RBF neural networks and the ANFIS models could be suitable tools for accurate prediction of epicenteral area as well as time of occurrence of forthcoming strong earthquakes in active seismogenic areas.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

References

  1. Alarifi ASN, Alarifi NSN, Al-Humidan S (2012) Earthquakes magnitude predication using artificial neural network in northern Red Sea area. J K Sa Un 24–4:301–313

    Article  Google Scholar 

  2. Alves EI (2006) Earthquake forecasting using neural networks: results and future work. Nonlinear Dyn 44:341–349

    Article  Google Scholar 

  3. Amutha R, Porchelvan P (2011) Seasonal prediction of groundwater levels using Anfis and Radial basis neural network. Int J Geol Earth Environ Sci 1:98–108

    Google Scholar 

  4. Awad M (2010) Optimization RBFNNs parameters using genetic algorithms: applied on function approximation. I J C S S 4–3:295–307

    Google Scholar 

  5. Bhatt KM, Kumar S (2009) Anomalous b-value in seismogenic layer of Bhuj Region. J Ind Geophys Un 13–3:99–106

    Google Scholar 

  6. Bodri B (2001) A neural-network model for earthquake occurrence. J Geodyn 32:289–310

    Article  Google Scholar 

  7. Cowan EJ, Beatson RK, Ross HJ, Fright WR, Lennan TJ, Mitchell TJ (2002) Rapid geological modelling, Applied Structural Geology for Mineral Exploration and Mining, International Symposium Abstract Volume. Aust Inst Geosci Bull 36:39–41

    Google Scholar 

  8. Ebel JE, Chambers DW, Kafka AL, Baglivo JA (2007) Non-Poissonian earthquake clustering and the hidden Markov model as bases for earthquake forecasting in California. Seismol Res Lett 78:57–65

    Article  Google Scholar 

  9. Enescu B, Ito K (2003) Values of b and p: their variations and relation to physical processes for earthquakes in Japan. Ann Disas Prev Res Inst Kyoto Univ 46B:709–719

    Google Scholar 

  10. Engdahl ER, Bergman EA, Myers S, Ryall F (2006) Improved ground truth in southern Asia using in-country data, analyst waveform review, and advanced algorithms. 28th Seismic Research Review: Gro Nuc Explo Monit Techno 387–396

  11. Farahani JV, Zare M, Lucas C (2012) Adaptive neuro-fuzzy inference systems for semi-automatic discrimination between seismic events: a study in Tehran region. J Seismol 6–2:291–303

    Article  Google Scholar 

  12. Giovanis E (2012) Study of discrete choice models and adaptive neuro-fuzzy inference system in the prediction of economic crisis periods in USA. J Econ Anal Policy 42–1:79–95

    Google Scholar 

  13. Gutenberg B, Richter CF (1944) Frequency of earthquakes in California. Bull Seismol Soc Am 34:185–188

    Google Scholar 

  14. Habermann RE, Wyss M (1987) Reply to “comment on Habermann’s method for detecting seismicity rate changes”, by M.W. Matthews and P. Reasenberg. J Geophys Res 92:9446–9450

    Article  Google Scholar 

  15. Hamadneh N, Sathasivam S, Choon OH (2012) Higher order logic programming in radial basis function neural network. Appl Math Sci 6–3:115–127

    Google Scholar 

  16. Haykin S (1994) Neural networks: a comprehensive foundation. Mac Millan College Publishing Company

  17. Jalalkamali A, Jalalkamali N (2011) Groundwater modeling hybrid of artificial neural network with genetic algorithm. Afr J Agric Res 6–26:5775–5784

    Google Scholar 

  18. Jang JSR (1993) ANFIS: adaptive network based fuzzy inference system. IEEE Trans Syst Man Cybern 23–3:665–685

    Article  Google Scholar 

  19. Jiménez A, Posadas A, Tiampo KF (2008) Describing seismic pattern dynamics by means of Ising cellular automata, nonlinear time series analysis in the geosciences. Lect Notes Earth Sci 273–290

  20. Joelinato E, Widiyantoro S, Ichsan M (2009) Time series estimation on earthquake events using ANFIS with mapping function. Int J Artif Intell 3-A09:0974–0635

    Google Scholar 

  21. Johnson RA, Wichern DW (2003) Applied multivariate statistical analysis, 5th edn. Pearson Education, Upper Saddle River

    Google Scholar 

  22. Kaiser HF (1960) The application of electronic computers to factor analysis. Educ Psychol Meas 20:141–151

    Article  Google Scholar 

  23. Karaboga D, Basturk B (2007) A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. J Glob Optim 39:459–17

    Article  Google Scholar 

  24. Katsumata K (2011) Long term seismic quiescence started 23 years before the 2011 off the pacific coast of Tohoku earthquake (M = 9.0). Earth Plan Sp 63:709–712

    Article  Google Scholar 

  25. Konstantaras A, Vallianatos F, Varley MR, Makris JP (2008) Soft-Computing modelling of seismicity in the southern Hellenic Arc. Geosci Remote Sens Lett 5–3:323–327

    Article  Google Scholar 

  26. Kurban T, Besdok E (2009) A comparison of RBF neural network training algorithms for inertial. Sen Bas Ter Clas 9:6312–6329. doi:10.3390-s90806312

    Article  Google Scholar 

  27. Lee HH, Nguyen NT, Kwon JM (2007) Bearing fault diagnosis using fuzzy inference optimized by neural network and genetic algorithm. J Electr Eng Tec 2–3:353–357

    Google Scholar 

  28. Ma L, Xin K, Liu S (2008) Using radial basis function neural networks to calibrate water quality model. Int J Electr Comput Eng 3:6

    Google Scholar 

  29. Madahizadeh R, Allamehzadeh M (2009) Prediction of aftershocks distribution using artificial neural networks and its application on the May 12, 2008 Sichuan earthquake. J Seismol Earthq Eng 11–3:111–120

    Google Scholar 

  30. Matthews MV, Reasenberg P (1988) Statistical methods for investigating quiescence and other temporal seismicity patterns. Pageoph 126:357–372

    Article  Google Scholar 

  31. Mayilvaganan MK, Naidu KB (2011) ANN and fuzzy logic models for the prediction of groundwater level of a watershed. Int J Comput Sci Eng 3–6:2523–2530

    Google Scholar 

  32. Mignan A, Werner MJ, Wiemer S, Chen CC, Wu YM (2011) Bayesian estimation of the spatially varying completeness magnitude of earthquake catalogs. Bull Seismol Soc Am 101. doi:10.1785/0120100223

  33. Morales-Esteban A, Martínez-Álvarez F, Troncoso A, Justo JL, Rubio-Escudero C (2010) Pattern recognition to forecast seismic time series. Expert Syst Appl 37–12:8333–8342

    Article  Google Scholar 

  34. Motaghi K, Hessami K, Tatar M (2010) Pattern recognition of major asperities using local recurrence time in Alborz Mountains, Northern Iran. J Seismol 14:787–802

    Article  Google Scholar 

  35. Nuannin P, Kulhanek O, Persson L (2005) Spatial and temporal b value anomalies preceding the devastating off coast of NW Sumatra earthquake of December 26, 2004. J Seismol 32:1–4

    Google Scholar 

  36. Oyang YJ, Hwang SC, Ou YY, Chen CY, Chen ZW (2005) Data classification with radial basis function networks based on a novel kernel density estimation algorithm. IEEE Trans Neu Net 16:225–236

    Article  Google Scholar 

  37. Panakkat A, Adeli H (2009) Recurrent neural network for approximate earthquake time and location prediction using multiple sesimicity indicators. Comput Civ Infrastruct Eng 24:280–292

    Article  Google Scholar 

  38. Panakkata A, Adeli H (2007) Neural network models for earthquake magnitude prediction using multiple seismicity indicators. Int J Neural Syst 17–1:13–33

    Article  Google Scholar 

  39. Rani VS, Srivastava K, Srinagesh D, Dimri VP (2011) Spatial and temporal variations of b-value and fractal analysis for the Makran region. Mar Geod 34:77–82

    Article  Google Scholar 

  40. Reasenberg PA (1985) Second-order moment of Central California Seismicity. J Geophys Res 90:5479

    Article  Google Scholar 

  41. Reasenberg PA, Simpson RW (1992) Response of regional seismicity to the static stress change produced by the Loma Prieta earthquake. Science 255:1687–1690

    Article  Google Scholar 

  42. Reyes J, Morales-Esteban A, Martínez-Álvarez F (2013) Neural networks to predict earthquakes in Chile. Appl Soft Comput 13–2:1314–1328

    Article  Google Scholar 

  43. Romeo G (1994) Seismic signals detection and classification using artificial neural networks. Ann Geofis 37:343–353

    Google Scholar 

  44. Samani N, Gohari-Moghadam M, Safavi AA (2007) A simple neural network model for the determination of aquifer parameters. J Hydrol 340:1–11

    Article  Google Scholar 

  45. Schorlemmer D, Wiemer S, Wyss M (2004) Earthquake statistics at Parkfield, Stationarity of b values. J Geophys Res 109, B12307. doi:10.1029/2004JB003234

    Article  Google Scholar 

  46. Shibli M (2011) A novel approach to predict earthquakes using Adaptive Neural Fuzzy Inference System and conservation of energy-angular momentum. Inter J Comp Inf Sys Ind Manag Appli. ISSN 2150-7988 3:371–390

    Google Scholar 

  47. Shih MY, Jheng JW, Lai LF (2010) A two-step method for clustering mixed categroical and numeric data. Tam J Sci Eng 13–1:11–19

    Google Scholar 

  48. Shoorehdeli MA, Teshnehlab M, Khaki Sedigh A (2009) Identification using ANFIS with intelligent hybrid stable learning algorithm approaches. Neu Comput Appl 18–2:157–174

    Article  Google Scholar 

  49. Soleimani M, Salmalian K (2012) Genetic algorithm optimized ANFIS networks for modeling and reduction of energy absorption rate of brass energy absorbers. J Appl Math Is Az Un La 8:29–45

    Google Scholar 

  50. Somasundaram RS, Nedunchezhian R (2011) Evaluation of three simple imputation methods for enhancing preprocessing of data with missing values. Int J Comput Appl 21–10:14–19

    Google Scholar 

  51. Sorbi MR, Nilfouroushan F, Zamani A (2012) Seismicity patterns associated with the September 10th, 2008 Qeshm earthquake, South Iran. Int J Earth Sci 101–8:2215–2223

    Article  Google Scholar 

  52. Spassov E, Sinadinovski C, McCue K (2002) Spatial and temporal variation of seismicity across Australia. J Bal Geophy Soc 5–4:115–122

    Google Scholar 

  53. Sri Lakshmi S, Tiwari RK (2009) Model dissection from earthquake time series: a comparative analysis using modern non-linear forecasting and artificial neural network approach. Comput Geosci 35:191–204

    Article  Google Scholar 

  54. Tahmasbi P, Hezarkhani A (2010) Comparison of optimized neural network with fuzzy logic for ore grade estimation. Aus J Bas Appl Sci 4–5:764–772

    Google Scholar 

  55. Takagi T, Sugeno M (1983) Derivation of fuzzy control rules from human operator’s control actions, Proceedings of IFAC Symposium on Fuzzy Information. Knowl Repres Dec Anal 55–60

  56. Venkataraman S (2010) A grid-based neural network framework for multimodal biometrics world academy of science. Eng Technol 72:298–303

    Google Scholar 

  57. Wang Y, Chen S, Wang H et al (2002) Species analysis of gold in geochemical samples by artificial neural network. Chin J Anal Chem 30:62–65

    Google Scholar 

  58. Wiemer S (2001) A program to analyse seismicity: ZMAP. Geophys Res Lett 72:373–382

    Google Scholar 

  59. Wiemer S, Wyss M (1997) Mapping the frequency-magnitude distribution in asperities: an improved technique to calculate recurrence times? J Geophys Res 102–15:115–128

    Google Scholar 

  60. Wiemer S, Wyss M (2002) Mapping spatial variability of the frequency-magnitude distribution of earthquakes. Adv Geophys 45:259–302

    Article  Google Scholar 

  61. Wu YM, Chen CC, Zhao L, Chang CH (2008) Seismicity characteristics before the 2003 Chengkung, Taiwan, earthquake. Tectonophy 457:177–182

    Article  Google Scholar 

  62. Wyss M, Pacchiani F, Deschamps A, Patau G (2008) Mean magnitude variations of earthquakes as a function of depth: different crustal stress distribution depending on tectonic setting. Geophys Res Let 35, L01307. doi:10.1029/2007GL031057

    Article  Google Scholar 

  63. Yilmaz I, Kaynar O (2011) Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils. Exp Syst Appl 38:5958–5966

    Article  Google Scholar 

  64. Zamani A, Agh-Atabai M (2011) Multifractal analysis of the spatial distribution of earthquake epicenters in the Zagros and Alborz-Kopeh Dagh regions of Iran. J Sci Technol A1:39–51

    Google Scholar 

  65. Zamani A, Nedaei M, Boostani R (2009) Tectonic zoning of iran based on self organizing map. J Appl Sci 9–23:4099–4114

    Google Scholar 

  66. Zhao W (2013) Logistics requirement prediction by a hybrid model of particle swarm optimization algorithm and RBF neural network. J Comput Inform Sys 9–1:41–46

    Google Scholar 

Download references

Acknowledgments

This research was supported by the Center of Excellence for Environmental Geohazards and the Research Council of Shiraz University. The authors express their gratitude to Stefan Wiemer for the ZMAP software. MRS is grateful to B. Rahnama, D. Eberhard, Gh. Nasuhi and A. Khosravani for valuable comments. MRS sincerely thanks Z. Heidari for editing the manuscript. The autors highly appreciate the Referees for their interest in our work and for insightful comments that will greatly improve the manuscript.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Mohammad Reza Sorbi.

Additional information

Communicated by: Hassan Babaie

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Zamani, A., Sorbi, M.R. & Safavi, A.A. Application of neural network and ANFIS model for earthquake occurrence in Iran. Earth Sci Inform 6, 71–85 (2013). https://doi.org/10.1007/s12145-013-0112-8

Download citation

Keywords

  • Seismicity parameters
  • Earthquake occurrence
  • Qeshm earthquake
  • RBF network
  • ANFIS model
  • PCA