Earthosys—Tsunami Prediction and Warning System Using Machine Learning and IoT

  • Gautham PughazhendhiEmail author
  • Amirthavalli Raja
  • Praveen Ramalingam
  • Dinesh Kumar Elumalai
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 28)


In this paper, the model for predicting tsunami using machine learning classification algorithm and the warning system using IoT has been proposed. The data used for training the model is based on the historical tsunami data comprising tsunami records from 2100 BC. The model has been trained based on the earthquake parameters in the dataset, as earthquakes are the main cause of death-causing tsunamis around the planet. It can classify the earthquake data as Tsunamigenic or Non-Tsunamigenic based on which the warning system is triggered, using the cloud technologies for communication. The model has been tested on the tsunami-causing earthquake records, and it shows an accuracy rate of over 95%. The model and the warning system together can automate the manual tsunami prediction techniques and alert system for the same, to save humankind in a better way than the past.


Tsunami Earthquake Machine learning IoT Cloud 


  1. 1.
    National Oceanic and Atmospheric Administration.
  2. 2.
    Indian Ocean Tsunami Information Center.
  3. 3.
    Truong HV (2012) Wave-propagation velocity, tsunami speed, amplitudes, dynamic water—attenuation factors. In: Proceedings of world conference on earthquake engineering, pp 1–10 (2012)Google Scholar
  4. 4.
    International Tsunami Information Center.
  5. 5.
    Puspito NT, Gunawan I (2005) Tsunami sources in the Sumatra region, Indonesia and simulation of the 26 December 2004 Aceh tsunami. ISET J Earthquake Technol 42:4Google Scholar
  6. 6.
    Zaytsev A, Kostenko I, Kurkin A, Pelinovsky E, Yalciner AC (2016) The depth effect of earthquakes on tsunami heights in the Sea of Okhotsk. Turk J Earth Sci 25(4):289–299CrossRefGoogle Scholar
  7. 7.
  8. 8.
    US Geological Survey.
  9. 9.
    Tayal T, Prema KV (2014) Design and implementation of a fuzzy based tsunami warning system. IJRET: Int J Res Eng Technol (2014)Google Scholar
  10. 10.
    Cherian CM, Jayaraj N (2010) Artificially intelligent tsunami early warning system. In: 12th international conference on computer modelling and simulation. IEEE Press, Cambridge, pp 39–44Google Scholar
  11. 11.
    Casey K, Lim A, Dozier G (2008) A sensor network architecture for tsunami detection and response. Int J Distrib Sens Netw 4(1):27–42CrossRefGoogle Scholar
  12. 12.
    Casey K, Lim A, Dozier G (2006) Evolving general regression neural networks for tsunami detection and response. In: IEEE Congress on Evolutionary Computation. IEEE Press, Vancouver, pp 2451–2458Google Scholar
  13. 13.
    Angove MD, Rabenold CL, Weinstein SA, Eblé MC, Whitmore PM (2015) US tsunami warning system: capabilities, gaps, and future vision. In: OCEANS’15 MTS/IEEE. IEEE Press, Washington, pp 1–5Google Scholar
  14. 14.
    Le Mehaute B, Hwang LS, Van Dorn W (1971) Methods for improving tsunami warning system. In: IEEE 1971 conference on engineering in the ocean environment. IEEE Press, San Diego, pp 329–331Google Scholar
  15. 15.
    USGS Real-time Notifications, Feeds and Web Services.
  16. 16.
    National Geophysical Data Center/World Data Service (NGDC/WDS) (2018) Global historical tsunami database. National Geophysical Data Center, NOAA.
  17. 17.
  18. 18.
  19. 19.
    Rouet-Leduc B, Hulbert C, Lubbers N, Barros K, Humphreys CJ, Johnson PA (2017) Machine learning predicts laboratory earthquakes. Geophys Res Lett 44(18):9276–9282CrossRefGoogle Scholar
  20. 20.
  21. 21.
  22. 22.

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Gautham Pughazhendhi
    • 1
    Email author
  • Amirthavalli Raja
    • 1
  • Praveen Ramalingam
    • 1
  • Dinesh Kumar Elumalai
    • 1
  1. 1.Velammal Engineering CollegeChennaiIndia

Personalised recommendations