Russian Journal of Earth Sciences Russian Journal of Earth Sciences Russian Journal of Earth Sciences 1681-1208 106642 10.2205/2025ES001072 rtnmvl Special Issue: “Advances in Environmental Studies, from the VIII International Scientific and Practical Conference ‘Fundamental and Applied Aspects of Geology, Geophysics and Geoecology Using Modern Information Technologies’ ” Special Issue: “Advances in Environmental Studies, from the VIII International Scientific and Practical Conference ‘Fundamental and Applied Aspects of Geology, Geophysics and Geoecology Using Modern Information Technologies’ ” Special Issue: “Advances in Environmental Studies, from the VIII International Scientific and Practical Conference ‘Fundamental and Applied Aspects of Geology, Geophysics and Geoecology Using Modern Information Technologies’ ” Comprehensive Analysis of Mudflow Data Using Machine Learning Methods Comprehensive Analysis of Mudflow Data Using Machine Learning Methods https://orcid.org/0000-0002-8131-2908 Гедуева Марьяна Мартиновна Gedueva Maryana Martinovna https://orcid.org/0000-0002-6031-4031 Кюль Елена Владимировна Kyul Elena Vladimirovna https://orcid.org/0000-0003-4941-7854 Лютикова Л. А. Lyutikova L. A. https://orcid.org/0000-0001-9368-1666 Корчагина Елена Александровна Korchagina Elena Aleksandrovna Нирова З. С. Nirova Z. S. Кабардино-Балкарский научный центр РАН Нальчик Россия Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences Nalchik Russian Federation Кабардино-Балкарский научный центр РАН Нальчик Россия Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences Nalchik Russian Federation Институт прикладной математики и автоматики КБНЦ РАН Россия Institute of Applied Mathematics and Automation, KBSC RAS Russian Federation ФНЦ "Кабардино-Балкарский научный центр РАН" Нальчик Россия Federal Scientific Center "Kabardino-Balkarian Scientific Center of the RAS" Nalchik Russian Federation Кабардино-Балкарский научный центр РАН Россия Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences Russian Federation 10 12 2025 10 12 2025 25 6 ES6003 10 09 2025 10 11 2025 https://rjes.ru/en/nauka/article/106642/view

The paper presents a comprehensive analysis of mudflow basin parameters, conducted using machine learning methods. For the northern slope of the Greater Caucasus, data on the main parameters of mudflow basins were analyzed to build models that allow forecasting mudflows with certain characteristics. A set of machine learning methods was used (clustering, search for association rules, logistic regression, etc.). Key factors of mudflows were identified, models were developed for classifying mudflow types and predicting the volume of one-time removal of material, and a number of association rules with high reliability were identified that describe the relationships between factors influencing mudflow processes. The obtained results show great potential in the application of learning in the tasks of analysis and forecasting of mudflow processes. Ultimately, this will allow, based on the addition of mudflow data and updating of existing mudflow maps, to develop more effective measures to reduce the impact of mudflows on the environment to a minimum.

The paper presents a comprehensive analysis of mudflow basin parameters, conducted using machine learning methods. For the northern slope of the Greater Caucasus, data on the main parameters of mudflow basins were analyzed to build models that allow forecasting mudflows with certain characteristics. A set of machine learning methods was used (clustering, search for association rules, logistic regression, etc.). Key factors of mudflows were identified, models were developed for classifying mudflow types and predicting the volume of one-time removal of material, and a number of association rules with high reliability were identified that describe the relationships between factors influencing mudflow processes. The obtained results show great potential in the application of learning in the tasks of analysis and forecasting of mudflow processes. Ultimately, this will allow, based on the addition of mudflow data and updating of existing mudflow maps, to develop more effective measures to reduce the impact of mudflows on the environment to a minimum.

 Mudflow mudflow basin mudflow activity mudflow formation factors machine learning methods analysis models clustering multiparameter regression association discretization rules Mudflow mudflow basin mudflow activity mudflow formation factors machine learning methods analysis models clustering multiparameter regression association discretization rules The work was carried out within the framework of the state assignment of KBSC RAS. The work was carried out within the framework of the state assignment of KBSC RAS.

Flach P. Machine learning: the science and art of building algorithms that extract knowledge from data. — M. : DMK Press, 2015. — 400 p. — (In Russian). Flach P. Machine learning: the science and art of building algorithms that extract knowledge from data. — M. : DMK Press, 2015. — 400 p. — (In Russian). Khvorostov V. V. Extraordinary and ultra-mudflows in the Greater Caucasus // Proceedings of the V International Conference ”Sustainable Development of Mountainous Areas: Problems and Prospects for the Integration of Science and Education”. — 2004. — P. 248–286. — (In Russian). Khvorostov V. V. Extraordinary and ultra-mudflows in the Greater Caucasus // Proceedings of the V International Conference ”Sustainable Development of Mountainous Areas: Problems and Prospects for the Integration of Science and Education”. — 2004. — P. 248–286. — (In Russian). Kondratieva N. V., Adzhiev A. Kh., Bekkiev M. Yu., et al. Mudflow hazard cadastre for the South of European Russia. — M.; Nalchik : Feoriya, 2015. — 148 p. — EDN: VHKUJH ; (in Russian). Kondratieva N. V., Adzhiev A. Kh., Bekkiev M. Yu., et al. Mudflow hazard cadastre for the South of European Russia. — M.; Nalchik : Feoriya, 2015. — 148 p. — EDN: VHKUJH ; (in Russian). Korchagina E. A., Gedueva M. M., Ataev Z. V., et al. Geoecological Research in the Territory of The Northern Slope of the Great Caucasus // News of the Kabardin-Balkar Scientific Center of RAS. — 2021. — Vol. 2, no. 100. — P. 126–138. — https://doi.org/10.35330/1991-6639-2021-2-100-126-138. — (In Russian). Korchagina E. A., Gedueva M. M., Ataev Z. V., et al. Geoecological Research in the Territory of The Northern Slope of the Great Caucasus // News of the Kabardin-Balkar Scientific Center of RAS. — 2021. — Vol. 2, no. 100. — P. 126–138. — https://doi.org/10.35330/1991-6639-2021-2-100-126-138. — (In Russian). Kyul E. V., Ezaov A. K. and Kankulova L. I. The Theoretical Basis of Geo-Environmental Monitoring of the Mountain Geosystems // Sustainable Development of Mountain Territories. — 2019. — Vol. 11, no. 1. — P. 36–43. — https://doi.org/10.21177/1998-4502-2019-11-1-36-43. — (In Russian). Kyul E. V., Ezaov A. K. and Kankulova L. I. The Theoretical Basis of Geo-Environmental Monitoring of the Mountain Geosystems // Sustainable Development of Mountain Territories. — 2019. — Vol. 11, no. 1. — P. 36–43. — https://doi.org/10.21177/1998-4502-2019-11-1-36-43. — (In Russian). Lombardo L. and Mai P. M. Presenting logistic regression-based landslide susceptibility results // Engineering Geology. — 2018. — Vol. 244. — P. 14–24. — https://doi.org/10.1016/j.enggeo.2018.07.019. Lombardo L. and Mai P. M. Presenting logistic regression-based landslide susceptibility results // Engineering Geology. — 2018. — Vol. 244. — P. 14–24. — https://doi.org/10.1016/j.enggeo.2018.07.019. Lyutikova L. A. Methods for Improving the Efficiency of Neural Network Decision-Making // Advances in Automation IV. RusAutoCon 2022. Lecture Notes in Electrical Engineering, vol 986. — Springer International Publishing, 2023. — P. 294–303. — https://doi.org/10.1007/978-3-031-22311-2_29. Lyutikova L. A. Methods for Improving the Efficiency of Neural Network Decision-Making // Advances in Automation IV. RusAutoCon 2022. Lecture Notes in Electrical Engineering, vol 986. — Springer International Publishing, 2023. — P. 294–303. — https://doi.org/10.1007/978-3-031-22311-2_29. Nirova Z. S., Kyul E. V., Baidaeva Z. R., et al. Assessment of the River Basins State in Prielbrusye National Park // Dagestan State Pedagogical University. Journal. Natural and Exact Sciences. — 2024. — Vol. 18, no. 1. — P. 59–69. — https://doi.org/10.31161/1995-0675-2024-18-1-59-69. — EDN: LPPDGN ; (in Russian). Nirova Z. S., Kyul E. V., Baidaeva Z. R., et al. Assessment of the River Basins State in Prielbrusye National Park // Dagestan State Pedagogical University. Journal. Natural and Exact Sciences. — 2024. — Vol. 18, no. 1. — P. 59–69. — https://doi.org/10.31161/1995-0675-2024-18-1-59-69. — EDN: LPPDGN ; (in Russian). Radeev N. A. Avalanches Forecasting Using Machine Learning Methods // Vestnik NSU. Series: Information Technologies. — 2021. — Vol. 19, no. 2. — P. 92–101. — https://doi.org/10.25205/1818-7900-2021-19-2-92-101. — (In Russian). Radeev N. A. Avalanches Forecasting Using Machine Learning Methods // Vestnik NSU. Series: Information Technologies. — 2021. — Vol. 19, no. 2. — P. 92–101. — https://doi.org/10.25205/1818-7900-2021-19-2-92-101. — (In Russian). Rahmati O., Kornejady A., Samadi M., et al. PMT: New analytical framework for automated evaluation of geoenvironmental modelling approaches // Science of The Total Environment. — 2019. — Vol. 664. — P. 296–311. — https://doi.org/10.1016/j.scitotenv.2019.02.017. Rahmati O., Kornejady A., Samadi M., et al. PMT: New analytical framework for automated evaluation of geoenvironmental modelling approaches // Science of The Total Environment. — 2019. — Vol. 664. — P. 296–311. — https://doi.org/10.1016/j.scitotenv.2019.02.017. Zhuravlev Yu. I. On an algebraic approach to solving recognition or classification problems // Problems of Cybernetics. Vol. 33. — Nauka, 1978. — P. 5–68. — (In Russian). Zhuravlev Yu. I. On an algebraic approach to solving recognition or classification problems // Problems of Cybernetics. Vol. 33. — Nauka, 1978. — P. 5–68. — (In Russian).