Experience of a comprehensive typology of mountainous regions in Russia based on heterogeneous parameters using cluster analysis

DOI: 10.35595/2414-9179-2025-1-31-445-462

View or download the article (Rus)

About the Authors

Evgeniy Yu. Kolbovsky

Lomonosov Moscow State University,
1, Leninskie Gory, Moscow, 119991, Russia,
E-mail: kolbowsky@mail.ru

Vladimir A. Dmitriev

Lomonosov Moscow State University,
1, Leninskie Gory, Moscow, 119991, Russia,
E-mail: dmitrieff200@yandex.ru

Abstract

The need to account for the mountainous character of territories within Russia’s legislative framework and regulatory practice highlights two interrelated challenges: the delimitation of mountains as geomorphological objects on one hand, and the identification of their distinctive features as zones of human development on the other. This study presents a methodological approach utilizing global and sectoral datasets to objectively determine the share of mountainous areas within Russia’s administrative-territorial units (ATU) and subsequently classify mountain regions based on cluster analysis across three parameter groups: geomorphological (terrain typology), geoecological (soil cover, land use patterns), and socioeconomic (employment, GRP, infrastructure). A core methodological issue in such typological classification of objects with heterogeneous attributes is determining the optimal number of clusters. We applied and evaluated three prevalent cluster-count validation methods for k-means clustering: elbow plots, silhouette analysis, and pseudo-F-statistics. Our case study demonstrates that combining these metrics reveals hierarchical differentiation across Russia’s mountainous territories—identifying 3 macro-clusters and 13 specialized sub-clusters reflecting regional profiles. Integrated results delineate four key mountain region types: industrial centers, agricultural-tourist regions, remote sparsely populated territories, and the recreational cluster of Crimea. The study confirms the advantages and limitations of each validation method while underscoring the efficacy of their integrated application when coupled with expert assessment.

Keywords

typology of mountainous territories, K-means clustering, spatial analysis, optimal number of clusters, socio-economic indicators, mountainous regions of the Russian Federation

References

  1. Arthur D., Vassilvitskii S. How Slow is the K-Means Method? Proceedings of the 2006 Symposium on Computational Geometry, 2006. DOI: 10.1145/1137856.1137880.
  2. Badarchi Kh.B., Sevek V.K. Analysis of the Border Regions of the Siberian Federal District of Russia by the Level of Socio-Economic Development (On the Example of the Republic of Tyva). Agrarian Bulletin of the Urals, 2019. No. 4 (183). P. 70–85 (in Russian). DOI: 10.32417/article_5cfa02c988b181.53566797.
  3. Bozhenko V., Klyukanov V.K. Application of Machine Learning Algorithms in Classification and Clustering Problems. Processing, Transmission and Protection of Information in Computer Systems 22. Collection of reports of the Second International Scientific Conference, St. Petersburg, April 11–15, 2022. St. Petersburg: Saint Petersburg State University of Aerospace Instrumentation, 2022. P. 28–33 (in Russian).
  4. Buchhorn M., Smets B., Bertels L., De Roo B., Lesiv M., Tsendbazar N.-E., Herold M., Fritz S. Copernicus Global Land Service: Land Cover 100 m. Collection 3. Epoch 2019. Globe (V3.0.1). Zenodo, 2020. DOI: 10.5281/zenodo.3518038. Web resource: https://zenodo.org/records/3518038 (accessed 03.09.2025).
  5. Danielson J.J., Gesch D.B. Global Multi-Resolution Terrain Elevation Data 2010 (GMTED2010). USGS Numbered Series, 2011. 23 p. DOI: 10.3133/ofr20111073.
  6. Dzhioev A.V. Socio-Demographic Aspects of Labor Market Dynamics in the Regions of the North Caucasus Federal District. Bulletin of the K.L. Khetagurov North Ossetian State University, 2019. No. 2. P. 112–121 (in Russian). DOI: 10.29025/1994-7720-2019-2-112-121.
  7. Elvidge D., Baugh K., Zhizhin M., Hsu F.C., Ghosh T. VIIRS Night-Time Lights. International Journal of Remote Sensing, 2017. V. 38. Iss. 21. P. 5860–5879. DOI: 10.1080/01431161.2017.1342050.
  8. Ganeshin G.S. Geomorphological Map of the USSR of scale 1:1 000 000 and Some Issues of Large-Scale Geomorphological Survey. Geomorfologiya I Paleogeografiya (Geomorphology and Paleogeography), 1970. No. 1. P. 53–60 (in Russian).
  9. Gelrud Ya.D., Ugryumov E.A. Analysis of the Competitive Environment and Socio-Economic Indicators of Industrial Production in the Chelyabinsk Region. Bulletin of the South Ural State University. Series “Economics and Management”, 2019. V. 13. No. 1. P. 5–13 (in Russian). DOI: 10.14529/em190101.
  10. Hansen M.C., Potapov P.V., Moore R., Hancher M., Turubanova S.A., Tyukavina A., Thau D., Stehman S.V., Goetz S.J., Loveland T.R., Kommareddy A., Egorov A., Chini L., Justice C.O., Townshend J.R.G. High-Resolution Global Maps of 21st-Century Forest Cover Change. Science, 2013. V. 342. Iss. 6160. P. 850–853. DOI: 10.1126/science.1244693.
  11. Jiang B. Geospatial Analysis Requires a Different Way of Thinking: The Problem of Spatial Heterogeneity. GeoJournal, 2015. V. 80. P. 1–13. DOI: 10.1007/s10708-014-9537-y.
  12. Kapos V., Rhind J., Edwards M., Prince M., Ravilious C. Developing a Map of the World’s Mountain Forests. Rests in Sustainable Mountain Development, IUFRO Research Series, 2000. No. 5. P. 4–19. DOI: 10.1079/9780851994468.0004.
  13. Kolbovsky E.Y. Spatial Analysis in Geoecology. Moscow: Lomonosov Moscow State University, 2022. 820 p. (in Russian).
  14. Kopytov A.I. Optimization of the Coal Industry Development Strategy—A Guarantee of Efficiency, Safety and Stability of the Industrial Potential of the Kuzbass Economy. Bulletin of the Kuzbass State Technical University, 2018. No. 2 (126). P. 5–11 (in Russian). DOI: 10.26730/1999-4125-2018-2-5-11.
  15. Koryachko V.P., Oreshkov V.I. Selection of the Number of Clusters in Clustering Tasks using the Silhouette Method. BIG DATA and Advanced Analytics. Collection of scientific articles of the IX International Scientific and Practical Conference, Minsk, May 17–18, 2023. In 2 parts. Part 1. Minsk: Belarusian State University of Informatics and Radio Electronics, 2023. P. 333–340 (in Russian).
  16. Landscape Map of the USSR, Scale 1:4 000 000. Leningrad: Leningrad State University, 1988. 1 sheet (in Russian).
  17. Lekhtyanskaya L.V., Rimskaya T.G. Tourism is One of the Priorities of the Economic Development of the Far East. Karelian Scientific Journal, 2019. V. 8. No. 2 (27). P. 126–130 (in Russian).
  18. Metzger M.J. The Global Environmental Stratification: A High-Resolution Bioclimate Map of the World. Edinburgh: The University of Edinburgh, 2018. DOI: 10.7488/ds/2354.
  19. Nune R., George B.A., Teluguntla P., Westernet A.W. Relating Trends in Streamflow to Anthropogenic Influences: A Case Study of Himayat Sagar Catchment, India. Water Resources Management, 2014. V. 28. P. 1579–1595. DOI: 10.1007/s11269-014-0567-5.
  20. Pantić M. Delineation of Mountains and Mountain Areas in Europe—A Planning Approach. Journal of the Geographical Institute Jovan Cvijic SASA, 2015. V. 65. Iss. 1. P. 43–58. DOI: 10.2298/IJGI1501043P.
  21. Petrushina M.N., Gunya A.N., Kolbovsky E.Yu., Purehovsky A.Zh. Dynamics of Mountain Landscapes of the North Caucasus under Modern Climate Change and Increased Anthropogenic Impact. Izvestia RAN. Seriya Geograficheskaya (News of the Russian Academy of Sciences. Geographical Series), 2023. V. 87. No. 7. P. 1032–1049 (in Russian). DOI: 10.31857/S2587556623070130.
  22. Samoilova G., Absalomova I. Mountainous Regions of Russia: Morphometric Analysis and Landscape Diversity. Geography Issues, 2014. No. 137. P. 39–62 (in Russian).
  23. Sayre R., Frye C., Karagulle D., Krauer J. Breyer S., Aniello P., Wright D.J., Payne D., Adler C., Warner H., Van Sistine D.P., Cress J. A New High-Resolution Map of World Mountains and an Online Tool for Visualizing and Comparing Characterizations of Global Mountain Distributions. Mountain Research and Development, 2018. V. 38. Iss. 3. P. 240–249. DOI: 10.1659/MRD-JOURNAL-D-17-00107.1.
  24. Selukov D.A., Shilov V.S. Finding the Optimal Number of Clusters using the Elbow Method. Innovative Technologies: Theory, Tools, Practice, 2016. V. 1. P. 107–111 (in Russian).

For citation: Kolbovsky E.Yu., Dmitriev V.A. Experience of a comprehensive typology of mountainous regions in Russia based on heterogeneous parameters using cluster analysis. InterCarto. InterGIS. Moscow: MSU, Faculty of Geography, 2025. V. 31. Part 1. P. 445–462. DOI: 10.35595/2414-9179-2025-1-31-445-462 (in Russian)