Natural Hazards

, Volume 85, Issue 1, pp 471–486 | Cite as

Earthquake magnitude prediction in Hindukush region using machine learning techniques

  • K. M. Asim
  • F. Martínez-Álvarez
  • A. Basit
  • T. Iqbal
Original Paper


Earthquake magnitude prediction for Hindukush region has been carried out in this research using the temporal sequence of historic seismic activities in combination with the machine learning classifiers. Prediction has been made on the basis of mathematically calculated eight seismic indicators using the earthquake catalog of the region. These parameters are based on the well-known geophysical facts of Gutenberg–Richter’s inverse law, distribution of characteristic earthquake magnitudes and seismic quiescence. In this research, four machine learning techniques including pattern recognition neural network, recurrent neural network, random forest and linear programming boost ensemble classifier are separately applied to model relationships between calculated seismic parameters and future earthquake occurrences. The problem is formulated as a binary classification task and predictions are made for earthquakes of magnitude greater than or equal to 5.5 (\(M \ge\) 5.5), for the duration of 1 month. Furthermore, the analysis of earthquake prediction results is carried out for every machine learning classifier in terms of sensitivity, specificity, true and false predictive values. Accuracy is another performance measure considered for analyzing the results. Earthquake magnitude prediction for the Hindukush using these aforementioned techniques show significant and encouraging results, thus constituting a step forward toward the final robust prediction mechanism which is not available so far.


Earthquake prediction Artificial neural networks Time series Machine learning 



The authors would like to thank Centre for Earthquake Studies, for their continuous support and for providing a platform for carrying out this research. Spanish Ministry of Science and Technology, Junta de Andaluca and University Pablo de Olavide under Projects TIN2011-28956-C02, P12-TIC-1728 and APPB813097 are also acknowledged. Finally, authors would also like to thank friends and colleagues for the useful discussion and ideas.


  1. Adeli H, Panakkat A (2009) A probabilistic neural network for earthquake magnitude prediction. Neural Netw 22(7):1018–1024CrossRefGoogle Scholar
  2. Allen CR (1976) Responsibilities in earthquake prediction: to the seismological society of America, delivered in Edmonton, Alberta, may 12, 1976. Bull Seismol Soc Am 66(6):2069–2074Google Scholar
  3. Båth M (1965) Lateral inhomogeneities of the upper mantle. Tectonophysics 2(6):483–514CrossRefGoogle Scholar
  4. Billington S, Isacks BL, Barazangi M (1977) Spatial distribution and focal mechanisms of mantle earthquakes in the Hindu Kush–Pamir region: a contorted Benioff zone. Geology 5(11):699–704CrossRefGoogle Scholar
  5. Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, OxfordGoogle Scholar
  6. Boore DM (2001) Comparisons of ground motions from the 1999 Chi-Chi earthquake with empirical predictions largely based on data from California. Bull Seismol Soc Am 91(5):1212–1217CrossRefGoogle Scholar
  7. Brehm DJ, Braile LW (1998) Intermediate-term earthquake prediction using precursory events in the New Madrid seismic zone. Bull Seismol Soc Am 88(2):564–580Google Scholar
  8. Breiman L (2001) Random forests. Mach Learn 45(1):5–32CrossRefGoogle Scholar
  9. Chatelain J-L, Roecker SW, Hatzfeld D, Molnar P (1980) Microearthquake seismicity and fault plane solutions in the Hindu Kush region and their tectonic implications. J Geophys Res Solid Earth (1978–2012) 85(B3):1365–1387CrossRefGoogle Scholar
  10. Christensen K, Olami Z (1992) Variation of the Gutenberg–Richter b values and nontrivial temporal correlations in a Spring-Block Model for earthquakes. J Geophys Res Solid Earth (1978–2012) 97(B6):8729–8735CrossRefGoogle Scholar
  11. Dahmen K, Erta D, Ben-Zion Y (1998) Gutenberg–Richter and characteristic earthquake behavior in simple mean-field models of heterogeneous faults. Phys Rev E 58(2):1494CrossRefGoogle Scholar
  12. 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(1):57–65CrossRefGoogle Scholar
  13. Ellsworth WL, Matthews MV, Nadeau RM, Nishenko SP, Reasenberg PA, Simpson RW (1999) A physically based earthquake recurrence model for estimation of long-term earthquake probabilities. US Geol Surv Open-File Rep 99(522):23Google Scholar
  14. Farah A, Abbas G, De Jong KA, Lawrence RD (1984) Evolution of the lithosphere in Pakistan. Tectonophysics 105(14):207–227CrossRefGoogle Scholar
  15. Ganatra AP, Kosta YP (2010) Comprehensive evolution and evaluation of boosting. Int J Comput Theory Eng 2(6):931CrossRefGoogle Scholar
  16. Geller RJ, Jackson DD, Kagan YY, Mulargia F (1997) Enhanced: earthquakes cannot be predicted. Science 275(5306):1616–1620CrossRefGoogle Scholar
  17. Grant RA, Raulin JP, Freund FT (2015) Changes in animal activity prior to a major (m = 7) earthquake in the Peruvian Andes. Phys Chem Earth Parts A/B/C 85:69–77CrossRefGoogle Scholar
  18. Graves G, Mohamed A-r, Hinton G (2013) Speech recognition with deep recurrent neural networks. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 6645–6649Google Scholar
  19. Hainzl S, Zller G, Kurths J, Zschau J (2000) Seismic quiescence as an indicator for large earthquakes in a system of self-organized criticality. Geophys Res Lett 27(5):597–600CrossRefGoogle Scholar
  20. Hamburger MW, Sarewitz DR, Pavlis TL, Popandopulo GA (1992) Structural and seismic evidence for intracontinental subduction in the Peter the First Range, central Asia. Geol Soc Am Bull 104(4):397–408CrossRefGoogle Scholar
  21. Hastie T, Tibshirani R, Friedman J, Franklin J (2005) The elements of statistical learning: data mining, inference and prediction. Math Intell 27(2):83–85Google Scholar
  22. Ikram A, Qamar U (2015) Developing an expert system based on association rules and predicate logic for earthquake prediction. Knowl Based Syst 75:87–103CrossRefGoogle Scholar
  23. Kagan YY, Jackson DD, Rong Y (2007) A testable five-year forecast of moderate and large earthquakes in southern California based on smoothed seismicity. Seismol Res Lett 78(1):94–98CrossRefGoogle Scholar
  24. Kirschvink JL (2000) Earthquake prediction by animals: evolution and sensory perception. Bull Seismol Soc Am 90(2):312–323CrossRefGoogle Scholar
  25. Knopoff L (2000) The magnitude distribution of declustered earthquakes in Southern California. Proc Natl Acad Sci 97(22):11880–11884CrossRefGoogle Scholar
  26. Koulakov I, Sobolev SV (2006) A tomographic image of Indian lithosphere break-off beneath the Pamir–Hindukush region. Geophys J Int 164(2):425–440CrossRefGoogle Scholar
  27. Larsen PE, Field D, Gilbert JA (2012) Predicting bacterial community assemblages using an artificial neural network approach. Nat Methods 9(6):621–625CrossRefGoogle Scholar
  28. Liang Z, Thorpe CE (2000) Stereo- and neural network-based pedestrian detection. IEEE Trans Intell Transp Syst 1(3):148–154CrossRefGoogle Scholar
  29. Liu Y, Wang Y, Li Y, Zhang B, Wu G (2004) Earthquake prediction by RBF neural network ensemble. Springer, BerlinCrossRefGoogle Scholar
  30. Martin GL (1995) Inventor; computer technology corp., assignee. Pattern recognition neural network. United States patent US 5,440,651Google Scholar
  31. McGuire JJ, Boettcher MS, Jordan TH (2005) Foreshock sequences and short-term earthquake predictability on East Pacific Rise transform faults. Nature 434(7032):457–461CrossRefGoogle Scholar
  32. Mirrashid M (2014) Earthquake magnitude prediction by adaptive neuro-fuzzy inference system (ANFIS) based on fuzzy C-means algorithm. Nat Hazards 74(3):1577–1593CrossRefGoogle Scholar
  33. Morales-Esteban A, Martínez-Álvarez F, Reyes J (2013) Earthquake prediction in seismogenic areas of the Iberian Peninsula based on computational intelligence. Tectonophysics 593:121–134CrossRefGoogle Scholar
  34. Murtza I, Abdullah D, Khan A, Arif M, Mirza SM (2015) Cortex-inspired multilayer hierarchy based object detection system using phog descriptors and ensemble classification. V Comput 1–14Google Scholar
  35. Negarestani A, Setayeshi S, Mohammad G-M, Akashe B (2002) Layered neural networks based analysis of radon concentration and environmental parameters in earthquake prediction. J Environ Radioact 62(3):225–233CrossRefGoogle Scholar
  36. Panakkat A, Adeli H (2007) Neural network models for earthquake magnitude prediction using multiple seismicity indicators. Int J Neural Syst 17(01):13–33CrossRefGoogle Scholar
  37. Partal T (2015) Comparison of wavelet based hybrid models for daily evapotranspiration estimation using meteorological data. KSCE J Civil Eng 2015:1–9Google Scholar
  38. Pavlis GL, Das S (2000) The Pamir–Hindu Kush seismic zone as a strain marker for flow in the upper mantle. Tectonics 19(1):103–115CrossRefGoogle Scholar
  39. Petersen MD, Cao T, Campbell KW, Frankel AD (2007) Time-independent and time-dependent seismic hazard assessment for the State of California: uniform California Earthquake Rupture Forecast Model 1.0. Seismol Res Lett 78(1):99–109CrossRefGoogle Scholar
  40. Pulinets S, Ouzounov D (2011) Lithosphere-atmosphere-ionosphere coupling (LAIC) model-an unified concept for earthquake precursors validation. J Asian Earth Sci 41(4):371–382CrossRefGoogle Scholar
  41. Reyes J, Morales-Esteban A, Martínez-Álvarez F (2013) Neural networks to predict earthquakes in Chile. Appl Soft Comput 13(2):1314–1328CrossRefGoogle Scholar
  42. Rundle JB (1989) Derivation of the complete Gutenberg–Richter magnitude-frequency relation using the principle of scale invariance. J Geophys Res Solid Earth (1978–2012) 94(B9):12337–12342CrossRefGoogle Scholar
  43. Schapire RE (1990) The strength of weak learnability. Mach Learn 5(2):197–227Google Scholar
  44. Searle M, Hacker BR, Bilham R (2001) The Hindu Kush seismic zone as a paradigm for the creation of ultrahigh-pressure diamond-and coesite-bearing continental rocks. J Geol 109(2):143–153CrossRefGoogle Scholar
  45. Shen Z-K, Jackson DD, Kagan YY (2007) Implications of geodetic strain rate for future earthquakes, with a five-year forecast of m5 earthquakes in southern California. Seismol Res Lett 78(1):116–120CrossRefGoogle Scholar
  46. U.S. Geological Survey (2015) Quaternary fault and fold database for the United StatesGoogle Scholar
  47. Utsu T, Ogata Y (1995) The centenary of the Omori formula for a decay law of aftershock activity. J Phys Earth 43(1):1–33CrossRefGoogle Scholar
  48. Wiemer S, Wyss M (1994) Seismic quiescence before the Landers (M = 7.5) and big bear (M = 6.5) 1992 earthquakes. Bull Seismol Soc Am 84(3):900–916Google Scholar
  49. Zahur A, Majid A, Kausar N (2014) Novel ensemble predictor for gram-positive bacterial protein sequences. In: Proceedings of the IEEE international conference on frontiers of information technology, pp 319–324Google Scholar
  50. Zamani A, Sorbi MR, Safavi AA (2013) Application of neural network and ANFIS model for earthquake occurrence in Iran. Earth Sci Inf 6(2):71–85CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2016

Authors and Affiliations

  • K. M. Asim
    • 1
  • F. Martínez-Álvarez
    • 2
  • A. Basit
    • 3
  • T. Iqbal
    • 1
  1. 1.Centre for Earthquake StudiesNational Centre for PhysicsIslamabadPakistan
  2. 2.Department of Computer SciencePablo de Olavide University of SevilleSevilleSpain
  3. 3.TPD, Pakistan Institute of Nuclear Science and TechnologyIslamabadPakistan

Personalised recommendations