Advertisement

Izvestiya, Atmospheric and Oceanic Physics

, Volume 54, Issue 8, pp 898–905 | Cite as

Verification of an Expert System for Forecasting Ice-Block-Formation: The Case of the Northern Dvina River

  • I. M. AleshinEmail author
  • I. V. MalyginEmail author
Article

Abstract

Here we provide a short description of an expert system for predicting the ice-jamming power in the area of the Northern Dvina River and a procedure to verify this system. This expert system is based on hydrological and meteorological data for 1991–2016. The data were processed using a machine learning technique and adjacent mathematics, because there is no mathematical model of the ice-jamming process and time series of observations are too short to apply classical statistics. This expert system was developed in 2012; it was adjusted using data from 1991–2010 seasons obtained at hydrological stations. The current investigation involves additional data on 2011–2016 seasons to repeat learning and estimate system quality. The developed system demonstrates a reliable efficiency: the forecast results coincide with observations for all six added seasons (2011–2016). It should be noted that the additional data do not change forecast accuracy, which remained approximately 85%, like in the previous study. All developed software is cross-platform, written with a C++ language, and is implemented as a command line application. This software can be easily adopted to operate as a part of the Northern Dvina River online monitoring service.

Keywords:

forecast of ice-block formation expert system and machine learning 

Notes

ACKNOWLEDGMENTS

This work was supported by budget projects of the Schmidt Institute of Physics of the Earth, Russian Academy of Sciences, and the Laverov Federal Center for Integrated Arctic Research, Russian Academy of Sciences.

REFERENCES

  1. 1.
    Agafonova, S.A. and Frolova, N.L., Specific features of ice regime in rivers of the Northern Dvina basin, Water Resour., 2007, vol. 34, no. 2, pp. 123–131.CrossRefGoogle Scholar
  2. 2.
    Agafonova, S.A., Frolova, N.L., Krylenko, I.N., Sazonov, A.A., and Golovlyov, P.P., Dangerous ice phenomena on the lowland rivers of European Russia, Nat. Hazards, 2017, vol. 88, no. 1, pp. 171–188.CrossRefGoogle Scholar
  3. 3.
    Berdennikov, V.P., Model studies of the jam formation mechanism to justify the ice-formation scheme on Dnestr River and determine ice loads, Tr. GGI, 1974, no. 219, pp. 31–55.Google Scholar
  4. 4.
    Berdennikov, V.P. and Shmatkov, V.A., Field and laboratory studies of ice jam formation, in Tr. IV Vsesoyuz. gidrologicheskogo s"ezda (Proceedings of the IV All-Union Hydrological Meeting), Leningrad, 1976, vol. 6, pp. 361–370.Google Scholar
  5. 5.
    Buzin, V.A., Conditions and forecast ice motions at freezing of the Neva River, Meteorol. Gidrol., 1997, no. 8, pp. 83–87.Google Scholar
  6. 6.
    Buzin, V.A., Floods caused by ice jams on rivers, Water Resour., 2000, vol. 27, no. 5, pp. 476–481.Google Scholar
  7. 7.
    Buzin, V.A., Zatory l’da i zatornye navodneniya na rekakh (Ice Jams and Jam Floods on Rivers), St. Petersburg: Gidrometeoizdat, 2004.Google Scholar
  8. 8.
    Buzin, V.A. and Zinov’ev, A.T., Ledovye protsessy i yavleniya na rekakh i vodokhranilishchakh: Metody matematicheskogo modelirovaniya i opyt ikh realizatsii dlya prakticheskikh tselei (obzor sovremennogo sostoyaniya problemy) (Ice Processes and Phenomena on Rivers and Water Basins: Mathematical Modeling Methods and History of Their Use in Practice (Review of the Current State of the Problem)), Barnaul: Pyat’ plyus, 2009.Google Scholar
  9. 9.
    Chebotarev, A.I., Gidrologicheskii slovar' (Hydrological Dictionary), Leningrad: Gidrometeoizdat, 1978.Google Scholar
  10. 10.
    Chizhov, A.N., On the mechanism of ice jam formation and their typification, Tr. GGI, 1975, no. 227, pp. 3–17.Google Scholar
  11. 11.
    Deev, Yu.A. and Popov, A.F., Vesennie zatory l’da v ruslovykh potokakh: Fizicheskie osnovy i kolichestvennyi analiz (Spring Ice Jams in River-Bed Flows: Physical Bases and Quantitative Analysis), Leningrad: Gidrometeoizdat, 1978.Google Scholar
  12. 12.
    Frolova, N.L., Kireeva, M.B., Bolgov, M.B., Kopylov, V.N., Hall, J., Semenov, V.A., Kosolapov, A.E., Dorozh-kin, E.V., Korobkina, E.A., Rets, E.P., Akutina, Y., Dzhamalov, R.G., Efremova, N.A., Sazonov, A.A., Agafonova, S.A., and Belyakova, P.A., Hydrological hazards in Russia: Origin, classification, changes and risk assessment, Nat. Hazards, 2017, vol. 88, no. 1, pp. 103–131.CrossRefGoogle Scholar
  13. 13.
    Konstantinov, R.M., Koroleva, Z.E., and Kudryavtsev, V.B., Combinatorial–logical approach to problems of ore-bearing prediction, in Problemy Kibernetiki (Problems in Cybernetics), Moscow: Nauka, 1976, vol. 31, pp. 5–38.Google Scholar
  14. 14.
    Malygin, I.V., A technique for the prediction of ice jam formation on rivers based on the image recognition theory, Vestn. Mosk. Univ., Ser. 5: Geogr., 2014a, no. 3, pp. 43–47.Google Scholar
  15. 15.
    Malygin, I.V., On the problem of the prediction of ice jam formation on rivers, Intellektual’nye Sist. Teor. Prilozh., 2014b, vol. 18, no. 3, pp. 73–80.Google Scholar
  16. 16.
    Malygin, I.V., Logical approach to the creation of expert systems of prediction of hazardous natural phenomena, Estestv. Tekh. Nauki, 2015, no. 2, pp. 102–112.Google Scholar
  17. 17.
    Panfilov, D.F., Regularities in the motion of water and ice in a wide rectangular bed during a continuous ice drift, Meteorol. Gidrol., 1968, no. 8, pp. 41–44.Google Scholar
  18. 18.
    Zhuravlev, Yu.I. and Nikiforov, V.V., Recognition algorithms based on estimates, Kibernetika, 1971, no. 3, pp. 1–11.Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2018

Authors and Affiliations

  1. 1.Schmidt Institute of Physics of the Earth, Russian Academy of SciencesMoscowRussia
  2. 2.Laverov Federal Center for Integrated Arctic Research, Russian Academy of SciencesArkhangelskRussia

Personalised recommendations