Topoclimatic drivers of land cover change in the Mongol Altai Mountains using random forest and eXtreme gradient boosting algorithms
DOI:
https://doi.org/10.5564/mjgg.v62i46.4126Keywords:
Mongol Altai Mountains, Land cover change, Random forest, XGBoost, SHAP, Topoclimatic drivers, Climatic variablesAbstract
Investigating land cover change in mountainous regions is crucial for sustainable land use planning and enhancing climate adaptation strategies. This study examines the spatial and temporal patterns of land cover dynamics in the Mongol Altai Mountains over a 30-year period, and identifies the key climatic and topographic factors, collectively referred topoclimatic drivers, that influencing these changes. Landsat satellite imagery with a 30 m resolution was processed using the Random Forest (RF) algorithm in R to classify land cover types. A change detection matrix was employed to quantify transitions between land cover types, and the results were visualized using a Sankey diagram. To assess the impact of environmental variables, eXtreme Gradient Boosting (XGBoost) algorithm was applied and model interpretability was enhanced using SHAP (Shapley Additive exPlanations) values. The classification demonstrated high accuracy, with overall accuracy values of 92.5% for 1990 and 93.7% for 2020. Over the study period, notable declines were observed in grasslands (−20.08%), tree-covered areas (−22.84%), and glaciers (−43.01%), while shrublands (26.82%) and artificial surfaces (36.28%) experienced substantial increases. XGBoost analysis identified vapor pressure, elevation, and wind speed as the most significant environmental factors driving land cover change. These factors demonstrated complex, non-linear relationships, highlighting the heterogeneous nature of high mountain ecosystems. The findings provide valuable insights for formulating climate-responsive land management and conservation strategies in mountainous regions.
Downloads
101
References
[1] J. A. Foley, et al., “Global consequences of land use,” Science (1979), vol. 309, no. 5734, pp. 570–574, 2005. Available: doi: 10.1126/science.1111772
[2] T. Stoerk, G. Wagner, and R. E. T. Ward, “Policy brief—Recommendations for improving the treatment of risk and uncertainty in economic estimates of climate impacts in the sixth Intergovernmental Panel on Climate Change assessment report,” Rev Environ Econ Policy, 2018. Available: doi: 10.1093/reep/rey005
[3] T. Kohler and D. Maselli, “Mountains and climate change,” From understanding to action. Geographica Bernensia, 2009.
[4] B. Hewitson, et al., “Regional context,” in Climate change 2014: Impacts, adaptation and vulnerability: Part B: Regional aspects: Working Group II Contribution to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change, Cambridge University Press, 2015, pp. 1133–1198.
[5] X. Chen, “Physical Geography of China’s Arid Zones,” 2010, Beijing: Science Press (in Chinese).
[6] E. M. Aizen, V. B. Aizen, J. M. Melack, T. Nakamura, and T. Ohta, “Precipitation and atmospheric circulation patterns at mid‐latitudes of Asia,” Int J Climatol, vol. 21, no. 5, pp. 535–556, 2001. Available: doi: 10.1002/joc.626
[7] J. Tsogtbaatar, S. Khudulmur, N. Mandakh, and S. Amartuvshin, “A Spatial and Temporal Assessment of Forest Cover Changes in Mongolia Using Remotely Sensed Data,” in Salt Lake city, USA, IUFRO 2014 congress, Institute of Geoecology, 2014.
[8] S. Vandandorj, E. Munkhjargal, B. Boldgiv, and B. Gantsetseg, “Changes in event number and duration of rain types over Mongolia from 1981 to 2014,” Environ Earth Sci, vol. 76, no. 2, p. 70, 2017. Available: doi: 10.1007/s12665-016-6380-0
[9] R. Törnqvist, et al., “Evolution of the hydro-climate system in the Lake Baikal basin,” J Hydrol (Amst), vol. 519, pp. 1953–1962, 2014. Available: doi: 10.1016/j.jhydrol.2014.09.074
[10] Y. Zhang, J. Wang, Y. Wang, A. Ochir, and C. Togtokh, “Land Cover Change Analysis to Assess Sustainability of Development in the Mongolian Plateau over 30 Years,” Sustainability (Switzerland), vol. 14, no. 10, May 2022, Available: doi: 10.3390/su14106129.
[11] J. Wang, “Land cover patterns in Mongolia and their spatiotemporal changes from 1990 to 2010,” Arab J Geosci, p. 13, 2019, [Online]. Available: files/202/Wang - 2019 - Land cover patterns in Mongolia and their spatiote.pdf. Available: doi: 10.1007/s12517-019-4893-z
[12] J. Hao et al., “Spatial–Temporal and Driving Factors of Land Use/Cover Change in Mongolia from 1990 to 2021,” Remote Sens (Basel), vol. 15, no. 7, Apr. 2023, Available: doi: 10.3390/rs15071813.
[13] J. Yuan et al., “Land Use Hotspots of the Two Largest Landlocked Countries: Kazakhstan and Mongolia,” Remote Sens (Basel), vol. 14, no. 8, Apr. 2022, Available: doi: 10.3390/rs14081805.
[14] C. Sun, Y. Bao, B. Vandansambuu, and Y. Bao, “Simulation and Prediction of Land Use/Cover Changes Based on CLUE-S and CA-Markov Models: A Case Study of a Typical Pastoral Area in Mongolia,” Sustainability (Switzerland), vol. 14, no. 23, Dec. 2022, Available: doi: 10.3390/su142315707.
[15] S. Dong, Y. Li, Y. Li, and S. Li, “Spatiotemporal patterns and drivers of land use and land cover change in the china-mongolia-russia economic corridor,” Pol J Environ Stud, vol. 30, no. 3, pp. 2527–2541, 2021, Available: doi: 10.15244/pjoes/127419.
[16] N. Dugarsuren, C. Lin, and K. Tsogt, “Land cover change detection in Mongolia in last decade using MODIS imagery,” Proc. Asian Conf. Remote Sens. (ACRS), Taipei, Taiwan, p. 688, 2011.
[17] J. Yuan and J. Chen, “Disproportionate contributions of land cover and changes to ecosystem functions in Kazakhstan and Mongolia,” Sci Rep, vol. 14, no. 1, p. 21922, Dec. 2024, Available: doi: 10.1038/s41598-024-72231-3.
[18] M. Lamchin, et al., “Assessment of land cover change and desertification using remote sensing technology in a local region of Mongolia,” Advances in Space Research, vol. 57, no. 1, pp. 64–77, Jan. 2016, Available: doi: 10.1016/j.asr.2015.10.006.
[19] J. A. Priess, C. Schweitzer, F. Wimmer, O. Batkhishig, and M. Mimler, “The consequences of land-use change and water demands in Central Mongolia,” Land use policy, vol. 28, no. 1, pp. 4–10, Jan. 2011, Available: doi: 10.1016/j.landusepol.2010.03.002.
[20] B. Vandansambuu, T. Davaa, B. Gantumur, M. Purevtseren, O. Lkhagva, and F. Wu, “Spatiotemporal monitoring and prediction of land use/land cover changes using CA-Markov chain model: a case study in Orkhon Province, Mongolia,” SPIE-Intl Soc Optical Eng, Sep. 2020, p. 12. Available: doi: 10.1117/12.2574032.
[21] C. Körner, J. Paulsen, and E. M. Spehn, “A definition of mountains and their bioclimatic belts for global comparisons of biodiversity data,” Alp Bot, vol. 121, no. 2, pp. 73–78, 2011, Available: doi: 10.1007/s00035-011-0094-4.
[22] D. Scherrer and C. Körner, “Topographically controlled thermal-habitat differentiation buffers alpine plant diversity against climate warming,” J Biogeogr, vol. 38, no. 2, pp. 406–416, 2011, Available: doi: 10.1111/j.1365-2699.2010.02407.x.
[23] N. Pepin, et al., “Elevation-dependent warming in mountain regions of the world,” Nat Clim Chang, vol. 5, no. 5, pp. 424–430, 2015, Available: doi: 10.1038/nclimate2563.
[24] E. Palazzi, L. Filippi, and J. Von Hardenberg, “Insights into elevation-dependent warming in the Tibetan Plateau–Himalayas from CMIP5 model simulations,” Clim Dyn, vol. 52, pp. 5833–5849, 2019, Available: doi: 10.1007/s00382-018-4485-6.
[25] G. Chen et al., “Natural world heritage sites are at risk from climate change globally,” Commun Earth Environ, vol. 5, no. 1, 2024. Available: doi: 10.1038/s43247-024-01933-3
[26] S.Jigj, Fundamental Features of the Relief of Mongolia. Ulaanbaatar: Publishing House of the Academy of Sciences, 1975.
[27] NASA, “Earthdata: Data from NASA’s Earth science missions.”
[28] NASA/METI/AIST/Japan Spacesystems and U.S./Japan ASTER Science Team, “ASTER Global Digital Elevation Model V003,” NASA EOSDIS Land Processes DAAC.
[29] J. T. Abatzoglou, S. Z. Dobrowski, S. A. Parks, and K. C. Hegewisch, “TerraClimate, a high-resolution global dataset of monthly climate and climatic water balance from 1958–2015,” Sci Data, vol. 5, no. 1, pp. 1–12, 2018. Available: doi: 10.1038/sdata.2017.191
[30] C. J. Tucker, “Red and photographic infrared linear combinations for monitoring vegetation,” Remote Sens Environ, vol. 8, no. 2, pp. 127–150, 1979. Available: doi: 10.1016/0034-4257(79)90013-0
[31] A. Huete, K. Didan, T. Miura, E. P. Rodriguez, X. Gao, and L. G. Ferreira, “Overview of the radiometric and biophysical performance of the MODIS vegetation indices,” Remote Sens Environ, vol. 83, no. 1–2, pp. 195–213, 2002. Available: doi: 10.1016/S0034-4257(02)00096-2
[32] A. R. Huete, “A soil-adjusted vegetation index (SAVI),” Remote Sens Environ, vol. 25, no. 3, pp. 295–309, 1988. Available: doi: 10.1016/0034-4257(88)90106-X
[33] G. Rondeaux, M. Steven, and F. Baret, “Optimization of soil-adjusted vegetation indices,” Remote Sens Environ, vol. 55, no. 2, pp. 95–107, 1996. Available: doi: 10.1016/0034-4257(95)00186-7
[34] A. J. Richardson and C. L. Wiegand, “Distinguishing vegetation from soil background information,” Photogramm Eng Remote Sensing, vol. 43, no. 12, pp. 1541–1552, 1977.
[35] H. Xu, “Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery,” Int J Remote Sens, vol. 27, no. 14, pp. 3025–3033, 2006. Available: doi: 10.1080/01431160600589179
[36] Y. Zha, J. Gao, and S. Ni, “Use of normalized difference built-up index in automatically mapping urban areas from TM imagery,” Int J Remote Sens, vol. 24, no. 3, pp. 583–594, 2003. Available: doi: 10.1080/01431160304987
[37] D. K. Hall, G. A. Riggs, and V. V Salomonson, “Development of methods for mapping global snow cover using moderate resolution imaging spectroradiometer data,” Remote Sens Environ, vol. 54, no. 2, pp. 127–140, 1995. Available: doi: 10.1016/0034-4257(95)00137-P
[38] G. M. Foody, “Status of land cover classification accuracy assessment,” Remote Sens Environ, vol. 80, no. 1, pp. 185–201, 2002, Available: doi: 10.1016/S0034-4257(01)00295-4.
[39] P. Olofsson, G. M. Foody, M. Herold, S. V Stehman, C. E. Woodcock, and M. A. Wulder, “Good practices for estimating area and assessing accuracy of land change,” Remote Sens Environ, vol. 148, pp. 42–57, 2014, Available: doi: 10.1016/j.rse.2014.02.015.
[40] J. Liu et al., “Spatial patterns and driving forces of land use change in China during the early 21st century,” Journal of Geographical Sciences, vol. 20, pp. 483–494, 2010. Available: doi: 10.1007/s11442-010-0483-4
[41] M. Kuhn, “Building predictive models in R using the caret package,” J Stat Softw, vol. 28, pp. 1–26, 2008. Available: doi: 10.18637/jss.v028.i05
[42] W. Thuiller, B. Lafourcade, R. Engler, and M. B. Araújo, “BIOMOD–a platform for ensemble forecasting of species distributions,” Ecography, vol. 32, no. 3, pp. 369–373, 2009. Available: doi: 10.1111/j.1600-0587.2008.05742.x
[43] P. O. Gislason, J. A. Benediktsson, and J. R. Sveinsson, “Random forests for land cover classification,” Pattern Recognit Lett, vol. 27, no. 4, pp. 294–300, 2006. Available: doi: 10.1016/j.patrec.2005.08.011
[44] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794. Available: doi: 10.1145/2939672.2939785
[45] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” Adv Neural Inf Process Syst, vol. 30, 2017.
[46] “Elevation-dependent warming in mountain regions of the world,” Nat Clim Chang, vol. 5, no. 5, pp. 424–430, 2015. Available: doi: 10.1038/nclimate2563
[47] C. Wang, X. Zhang, and L. Liu, “Land Use Change in the Russian Far East and Its Driving Factors,” Land (Basel), vol. 14, no. 4, p. 804, 2025. Available: doi: 10.3390/land14040804
[48] T. Bolch, et al., “Status and change of the cryosphere in the extended Hindu Kush Himalaya region,” The Hindu Kush Himalaya assessment: Mountains, climate change, sustainability and people, pp. 209–255, 2019. Available: doi: 10.1007/978-3-319-92288-1_7
[49] G. X. He, et al., “Soil carbon, nitrogen and phosphorus stocks and ecological stoichiometry characteristics of different vegetation restorations in degraded mountainous area of central Yunnan, China,” Acta Ecol. Sin, vol. 40, pp. 4425–4435, 2020.
[50] R. Fensholt, et al., “Greenness in semi-arid areas across the globe 1981–2007—an Earth Observing Satellite based analysis of trends and drivers,” Remote Sens Environ, vol. 121, pp. 144–158, 2012. Available: doi: 10.1016/j.rse.2012.01.017
[51] K. Li, Y. Zhang, Z. Zhang, and G. Lai, “A coarse-to-fine registration strategy for multi-sensor images with large resolution differences,” Remote Sens (Basel), vol. 11, no. 4, p. 470, 2019. Available: doi: 10.3390/rs11040470
[52] J. Wang et al., “Land cover patterns in Mongolia and their spatiotemporal changes from 1990 to 2010,” Arabian Journal of Geosciences, vol. 12, pp. 1–13, 2019. Available: doi: 10.1007/s12517-019-4893-z
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Batnyam Tseveengerel, Purevsuren Munkhtur, Renchinmyadag Tovuudorj
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on any research article in the Mongolian Journal of Geography and Geoecology is retained by the author(s).
The authors grant the Mongolian Journal of Geography and Geoecology a license to publish the article and identify itself as the original publisher.
Articles in the Mongolian Journal of Geography and Geoecology are Open Access articles published under a Creative Commons Attribution 4.0 International License CC BY.
This license permits use, distribution and reproduction in any medium, provided the original work is properly cited.
