Skip to main content
SpringerLink
Log in

Forecasting Ice Jams on the Lena River Using Machine Learning Methods

  • Published:
Izvestiya, Atmospheric and Oceanic Physics Aims and scope Submit manuscript

Abstract

The application of a predictive intellectual system previously developed for the Northern Dvina River is considered for a new region—the basin of the Lena River. The use of this technology under conditions of another region becomes possible due to the similar formulation of the problem of forecasting and publishing new open sets of hydrological and meteorological data for the period of 1985–2019. Based on the results of observations at gauging and meteorological stations, the system makes it possible to form a short-term forecast of the formation of powerful ice jams in river sections under conditions of incompleteness and data gaps. Interpolation methods based on machine learning are used to prepare the initial data and eliminate gaps. Calculations have shown the efficiency of the predictive system. The estimated accuracy of forecasting is 76%. The assessment of the importance of the factors have shown the common influence of groups of factors in different regions on the final result of the ice jamming process.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.

REFERENCES

  1. Agafonova, S.A., Vasilenko, A.N., and Frolova, N.L., The present-day factors of ice jam formation on the rivers of the Severnaya Dvina river basin, Vestn. Mosk. Univ., Ser. 5: Geogr., 2016, no. 2, pp. 82-90.

  2. Agafonova, S., Frolova, N., Krylenko, I., Sazonov, A., and Golovlyov, P., Dangerous ice phenomena on the lowland rivers of European Russia, Nat. Hazards, 2017, vol. 88, no. 1, pp. 171–188.

    Article  Google Scholar 

  3. Aleshin, I.M. and Malygin, I.V., Verification of an expert system for forecasting ice-block formation: The case of the Northern Severnaya Dvina river, Izv., Atmos. Ocean. Phys., 2018, vol. 54, no. 8, pp. 898–905. https://doi.org/10.1134/S0001433818080029

    Article  Google Scholar 

  4. Aleshin, I.M. and Malygin, I.V., Interpretation of the results of radio wave transmission by machine learning methods, Komp’yuternye Issled. Modell., 2019, vol. 11, no. 4, pp. 675-684. https://doi.org/10.20537/2076-7633-2019-11-4-675-684

    Article  Google Scholar 

  5. Ammosov, A.P., Shpakova, R.N., Kusatov, K.I., and Kornilova, Z.G., Change in water surface levels and slopes during jam phenomena on the Lena River, Izv. Irkutsk. Gos. Univ., Ser. Nauki Zemle, 2019, vol. 28, pp. 3–20.

    Google Scholar 

  6. Breiman, L., Random forests, Mach. Learn., 2001, vol. 45, no. 1, pp. 5–32.

    Article  Google Scholar 

  7. Buzin, V.A., Zatory l’da i zatornye navodneniya na rekakh (Ice Jams and Jam Floods on Rivers), St. Petersburg: Gidrometeoizdat, 2004.

  8. Gautier, E., Depret, Th., Costard, F., Virmoux, C., Fedorov, A., Grancher, D., Konstantinov, P., and Brunstein, D., Going with the flow: Hydrologic response of middle Lena River (Siberia) to the climate variability and change, J. Hydrol., 2018, no. 557, pp. 475–488.

  9. Hydrology of the Lena River and its tributaries: Annual characteristics of the state of water objects for 1985–2019 and measures for ice reduction in 2011–2020, Moscow: Roshydromet, 2021. http://data-in.ru/data-catalog/datasets/172/.

  10. Kil’myaninov, V.V., Analysis of conditions for the formation and long-term forecast of jam levels on the Lena river, Meteorol. Gidrol., 1992, no. 4, pp. 82–89.

  11. Kil’myaninov, V.V., The effect of meteorological conditions prior to ice run on the extent of ice jam floods on the Lena River, Russ. Meteorol. Hydrol., 2012, no. 4, pp. 86–89.

  12. Krylenko, I., Alabyan, A., Aleksyuk, A., Belikov, V., Sazonov, A., Zavyalova, E., Pimanov, I., Potryasaev, S., and Zelentsov, V., Modeling ice-jam floods in the frameworks of an intelligent system for river monitoring, Water Resour., 2020, vol. 47, no. 3, pp. 387–398.

    Article  Google Scholar 

  13. Malygin, I.V., A technique for the prediction of ice jam formation on rivers using the pattern recognition theory, Vestn. Mosk. Univ., Ser. 5: Geogr., 2014, no. 3, pp. 43–47.

  14. Malygin, I.V., Logical approach to the creation of expert systems for the prediction of hazardous natural phenomena, Estestv. Tekh. Nauki, 2015, no. 2, pp. 102–112.

  15. Meteorology of the region of Lena river and its tributaries: Monthly, daily, and eight-hour weather characteristics for 1985–2020, Moscow: Roshydromet, 2021. http://data-in.ru/data-catalog/datasets/173/.

  16. Nogovitsyn, D.D. and Kil’myaninov, V.V., On the prediction of jam phenomena on the Lena river, Nauka Tekh Yakutii, 2007, no. 1, pp. 19–24.

  17. Rozhdestvenskii, A.V., Buzin, V.A., and Shalashina, T.L., Forming conditions and probable values of maximum water levels of the Lena River near Yakutsk, Russ. Meteorol. Hydrol., 2010, vol. 35, no. 1, pp. 54–61.

    Article  Google Scholar 

  18. Semenova, N., Sazonov, A., Krylenko, I., and Frolova, N., Use of classification algorithms for the ice jams forecasting problem, E3S Web Conf., 2020, vol. 163, pp. 1–5.

  19. Yang, D., Kane, D., Hinzman, L., Zhang, X., Zhang, T., and Ye, H., Siberian Lena River hydrologic regime and recent change, J. Geophys. Res., 2002, vol. 107, pp. 1–10.

    Google Scholar 

  20. Ye, B., Yang, D., Zhang, Z., and Kane, D., Variation of hydrological regime with permafrost coverage over Lena basin in Siberia, J. Geophys. Res., 2009, vol. 114, pp. 1–12.

    Google Scholar 

Download references

ACKNOWLEDGMENTS

This work was prepared based on the results of the participation of the authors in the Emergency Data Hack geodata analysis hackathon competition organized on the Research Data Infrastructure (RDIS) platform together with the Ministry of Emergency Situations of the Russian Federation in May 2021. Participants were invited to choose to participate in one of the tracks dedicated to forecasting emergencies on rivers and federal highways. Our team took one of the prizes in the first track for predicting the formation of ice jams on the Lena River in the spring.

Funding

This work was supported by the state order of the Schmidt Institute of Physics of the Earth, Russian Academy of Sciences.

Author information

Authors and Affiliations

  1. Sсhmidt Institute of Physics of the Earth, Russian Academy of Sciences, 123995, Moscow, Russia

    I. V. Malygin & I. M. Aleshin

Authors
  1. I. V. Malygin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. I. M. Aleshin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to I. V. Malygin or I. M. Aleshin.

Ethics declarations

The authors declare that they have no conflicts of interest.

Additional information

Translated by E.G. Morozov

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Malygin, I.V., Aleshin, I.M. Forecasting Ice Jams on the Lena River Using Machine Learning Methods. Izv. Atmos. Ocean. Phys. 58, 1218–1225 (2022). https://doi.org/10.1134/S0001433822100061

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S0001433822100061

Keywords:

Search

Navigation