Digital mapping of soil properties in the high latitudes of Russia using sparse data

被引:5
作者
Suleymanov, Azamat [1 ,2 ]
Abakumov, Evgeny [1 ]
Alekseev, Ivan [1 ]
Nizamutdinov, Timur [1 ]
机构
[1] St Petersburg State Univ, Fac Biol, Dept Appl Ecol, St Petersburg 199034, Russia
[2] Ufa Univ Sci & Technol, Dept Geodesy Cartog & Geog Informat Syst, Ufa 450076, Russia
关键词
Soil organic carbon; pH; Arctic; Digital soil mapping; Machine learning; Cryosols; Leptosol; PERMAFROST-AFFECTED SOILS; MOUNTAINOUS TUNDRA; CALCAREOUS ROCKS; WESTERN SIBERIA; ORGANIC-MATTER; POLAR URALS; IZ MASSIF; TEMPERATURE; CARBON; MAP;
D O I
10.1016/j.geodrs.2024.e00776
中图分类号
S15 [土壤学];
学科分类号
0903 ; 090301 ;
摘要
Understanding the spatial distribution of soil properties in Arctic landscapes can improve our knowledge of carbon storage and the impacts of climate change. This study utilized a range of covariates, including organisms, climate, topography, soil, geology, and land use types, to map and identify key variables responsible for the spatial distribution of soil organic carbon (SOC) and pH values over a 14.000 km2 area in northern Russia. To this end, we employed three machine learning methods: Random Forest (RF), K -Nearest Neighbor (KNN), and Cubist. Our results indicated that the RF outperformed the KNN and Cubist algorithms for both soil parameter predictions and that organisms and climate data (surface temperature and cloud cover) were identified as key variables, with the highest contribution to the models. The generated maps showed that the highest SOC concentrations were associated with alluvial and peat soils, whereas the lowest content was predicted in the mountains. The more acidic soils were concentrated in the flat part of the region, whereas the more alkaline soils were located in the foothills and mountains. This research is important in the context of climate change, as the northern regions are critical for the global carbon cycle and play an essential role in regulating the Earth's climate. The information obtained from this study can aid in predicting future carbon fluxes, mitigating the impact of climate change, and promoting sustainable land management practices.
引用
收藏
页数:9
相关论文
共 66 条
  • [1] Abakumov EV, 2017, EURASIAN SOIL SCI+, V50, P1069, DOI [10.1134/S1064229317090010, 10.1134/s1064229317090010]
  • [2] Digital Mapping of Soil Organic Carbon Contents and Stocks in Denmark
    Adhikari, Kabindra
    Hartemink, Alfred E.
    Minasny, Budiman
    Kheir, Rania Bou
    Greve, Mette B.
    Greve, Mogens H.
    [J]. PLOS ONE, 2014, 9 (08):
  • [3] Alekseev I., 2021, Organic Carbon and Microbiome in Tundra and Forest-Tundra Permafrost Soils, Southern Yamal
  • [4] Soil organic carbon stocks and stability of organic matter in permafrost-affected soils of Yamal region, Russian Arctic
    Alekseev, Ivan
    Abakumov, Evgeny
    [J]. GEODERMA REGIONAL, 2022, 28
  • [5] Arinushkina E. V., 1970, HDB CHEM ANAL SOILS
  • [6] Total carbon and nitrogen in the soils of the world
    Batjes, N. H.
    [J]. EUROPEAN JOURNAL OF SOIL SCIENCE, 2014, 65 (01) : 10 - 21
  • [7] Random forests
    Breiman, L
    [J]. MACHINE LEARNING, 2001, 45 (01) : 5 - 32
  • [8] Digital mapping of the soil thickness of loess deposits over a calcareous bedrock in central France
    Chen, Songchao
    Richer-de-Forges, Anne C.
    Mulder, Vera Leatitia
    Martelet, Guillaume
    Loiseau, Thomas
    Lehmann, Sebastien
    Arrouays, Dominique
    [J]. CATENA, 2021, 198
  • [9] A high-resolution map of soil pH in China made by hybrid modelling of sparse soil data and environmental covariates and its implications for pollution
    Chen, Songchao
    Liang, Zongzheng
    Webster, Richard
    Zhang, Ganlin
    Zhou, Yin
    Teng, Hongfen
    Hu, Bifeng
    Arrouays, Dominique
    Shi, Zhou
    [J]. SCIENCE OF THE TOTAL ENVIRONMENT, 2019, 655 : 273 - 283
  • [10] Dai A, 1999, J CLIMATE, V12, P2451, DOI 10.1175/1520-0442(1999)012<2451:EOCSMP>2.0.CO