Drivers of Soil Organic Carbon Spatial Distribution in the Southern Ural Mountains: a Machine Learning Approach

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

Abstract

This study aims to assess the relationships between SOC content and main soil-forming factors and identify key factors explaining the spatial distribution of SOC. The research was conducted in the Southern Ural Mountains throughout 420 km from north to south in the Republic of Bashkortostan. The predominant soil types are mountainous gray forest (Eutric Retisols (Loamic, Cutanic, Humic)), dark gray forest (Luvic Retic Greyzemic Someric Phaeozems (Loamic)) soils, and gray-humus lithozems (Eutric Leptosols (Loamic, Humic)). Forest stands are mainly composed of birch (Betula pendula), pine (Pinus sylvestris), spruce (Picea obovata Ledeb.), and fir (Abies sibirica Ledeb.). A data set of 306 soil samples taken from the top layer (0–20 cm) was studied using the “random forest” machine learning method. Ninety-four spatial environmental covariates were used as explanatory variables, including remote sensing data, climate (temperature, precipitation, cloudiness, etc.), digital elevation model and its derivatives, land uses, bioclimatic zones, etc. The results showed that the SOC content varied widely from 0.8 to 32%. The random forest predictive model explained 55% of SOC variation (R2) with a root mean squared error (RMSE) of 1.35%. Key variables included surface temperature, absolute elevation, precipitation, and cloudiness, which together reflect the Dokuchaev vertical and horizontal zonality laws. The findings emphasize the importance of considering multiple environmental factors in subsequent research focused on assessing the spatial distribution of SOC.

About the authors

A. R. Suleymanov

Ufa State Petroleum Technological University; Ufa Institute of Biology of the Ufa Federal Research Centre of the Russian Academy of Sciences

Author for correspondence.
Email: filpip@yandex.ru
ORCID iD: 0000-0001-7974-4931
Russian Federation, Ufa, 450064; Ufa, 450054

R. R. Suleymanov

Ufa State Petroleum Technological University; Ufa Institute of Biology of the Ufa Federal Research Centre of the Russian Academy of Sciences; Ufa University of Science and Technology

Email: filpip@yandex.ru
Russian Federation, Ufa, 450064; Ufa, 450054; Ufa, 450076

L. N. Belan

Ufa State Petroleum Technological University

Email: filpip@yandex.ru
Russian Federation, Ufa, 450064

I. G. Asylbaev

Ufa State Petroleum Technological University; Bashkir State Agrarian University

Email: filpip@yandex.ru
Russian Federation, Ufa, 450064; Ufa, 450001

I. O. Tuktarova

Ufa State Petroleum Technological University

Email: filpip@yandex.ru
Russian Federation, Ufa, 450064

R. D. Shagaliev

Ufa State Petroleum Technological University

Email: filpip@yandex.ru
Russian Federation, Ufa, 450064

Е. А. Bogdan

Ufa State Petroleum Technological University

Email: filpip@yandex.ru
Russian Federation, Ufa, 450064

I. I. Fairuzov

Ufa University of Science and Technology

Email: filpip@yandex.ru
Russian Federation, Ufa, 450076

R. R. Mirsayapov

Ufa University of Science and Technology

Email: filpip@yandex.ru
Russian Federation, Ufa, 450076

A. N. Davydychev

Ufa Institute of Biology of the Ufa Federal Research Centre of the Russian Academy of Sciences

Email: filpip@yandex.ru
Russian Federation, Ufa, 450054

References

  1. Агрохимические методы исследования почв. М.: Наука, 1976. 656 с.
  2. Бурангулова М.Н., Мукатанов А.Х., Курчеев П.А. Горные почвы Башкирии // Почвы Башкирии. Уфа, 1973. Т. 1. С. 405–437.
  3. Габбасова И.М., Гарипов Т.Т., Сулейманов Р.Р., Комиссаров М.А., Хабиров И.К., Сидорова Л.В., Назырова Ф.И., Простякова З.Г., Котлугалямова Э.Ю. Влияние низовых пожаров на свойства и эрозию лесных почв Южного Урала (Башкирский государственный природный заповедник) // Почвоведение. 2019. № 4. С. 412–421.
  4. Дымов А.А., Жангуров Е.В. Морфолого-генетические особенности почв кряжа Енганэпэ (Полярный Урал) // Почвоведение. 2011. № 5. С. 515–524.
  5. Жангуров Е.В., Королёв М.А., Дубровский Ю.А., Шамрикова Е.В. Почвы горного хребта Рай-Из (Полярный Урал) // Почвоведение. 2023. № 4. С. 417–432.
  6. Жангуров Е.В., Старцев В.В., Дубровский Ю.А., Дегтева С.В., Дымов А.А. Морфолого-генетические особенности почв горных лиственничных лесов и редколесий Приполярного Урала // Почвоведение. 2019. № 12. С. 1415–1429.
  7. Лукина Н.В., Кузнецова А.И., Гераськина А.П., Смирнов В.Э., Иванова В.Н., Тебенькова Д.Н., Горнов А.В., Шевченко Н.Е., Тихонова Е.В. Неучтенные факторы, определяющие запасы углерода в лесных почвах // Метеорология и гидрология. 2022. № 10. С. 92–110.
  8. Самофалова И.А., Лузянина О.А. Горные почвы Среднего Урала (на примере ГПЗ “Басеги”). Пермь: Прокростъ, 2014. 154 с.
  9. Сморкалов И.А. Изменчивость дыхания почвы: оценка вклада пространства и времени с помощью алгоритма Random Forest // Экология. 2022. № 4. С. 299–311.
  10. Старцев В.В., Мазур А.С., Дымов А.А. Содержание исостав органического вещества почв Приполярного Урала // Почвоведение. 2020. № 12. С. 1478–1488.
  11. Хазиев Ф.Х., Мукатанов А.Х., Хабиров И.К., Кольцова Г.А., Габбасова И.М., Рамазанов Р.Я. Почвы Башкортостана. Эколого-генетическая и агропроизводственная характеристика. Уфа: Гилем, 1995. Т. 1. 384 с.
  12. Халитов Р.М., Абакумов Е.В., Сулейманов Р.Р., Котлугалямова Э.Ю. Горные почвы Южного Урала (на примере Национального парка “Башкирия”) // Известия Самарского НЦ РАН. 2011. Т. 13. № 5-2. С. 128–130.
  13. Халитов Р.М. Перова Е.Н., Абакумов Е.В., Сулейманов Р.Р. Минералогический состав коренной горной породы торфянисто-подзолистой почвы горного массива Иремель, Южный Урал // Почвоведение. 2017. № 8. С. 992–1001.
  14. Чибилев А.А. Природа Оренбургской области. Ч. 1. Физико-географический и историко-географический очерк. Оренбург, 1995. 128 с.
  15. Шамрикова Е.В., Жангуров Е.В., Кулюгина Е.Е., Королев М.А., Кубик О.С., Туманова Е.А. Почвы и почвенный покров горно-тундровых ландшафтов Полярного Урала на карбонатных породах: разнообразие, классификация, распределение углерода и азота // Почвоведение. 2020. № 9. С. 1053–1070.
  16. Adhikari K., Hartemink A.E., Minasny B., Bou Kheir R.M., Greve B., Greve M.H. Digital mapping of soil organic carbon contents and stocks in Denmark // PloS One. 2014. V. 9(8). P. e105519. https://doi.org/10.1371/journal.pone.0105519
  17. Batjes N.H. Total carbon and nitrogen in the soils of the world // Eur. J. Soil Sci. 1996. V. 47(2). P. 151–163. https://doi.org/10.1111/j.1365-2389.1996.tb01386.x
  18. Belan L., Suleymanov A., Bogdan E., Volkov A., Gaysin I., Tuktarova I., Shagaliev R. Assessing and Mapping Changes in Forest Growing Stock Volume over Time in Bashkiriya Nature Reserve, Russia // Forests. 2023. V. 13(11). P. 2251. https://doi.org/10.3390/f14112251
  19. Biau G., Scornet E. A random forest guided tour // TEST. 2016. V. 25(2). P. 197–227. https://doi.org/10.1007/s11749-016-0481-7
  20. Breiman L. Random Forests // Machine Learning. 2001. V. 45(1). P. 5–32.
  21. Chen S., Arrouays D., Leatitia Mulder V., Poggio L., Minasny B., Roudier P., Libohova Z., Lagacherie P., Shi Z., Hannam J., Meersmans J., Richer-de-Forges A.C., Walter C. Digital mapping of GlobalSoilMap soil properties at a broad scale: A review // Geoderma. 2022. V. 409. P. 115567. https://doi.org/10.1016/j.geoderma.2021.115567
  22. Chinilin A., Savin I.Yu. Combining machine learning and environmental covariates for mapping of organic carbon in soils of Russia // The Egypt. J. Remote Sensing Space Sci. 2023. V. 26(3). P. 666–675. https://doi.org/10.1016/j.ejrs.2023.07.007
  23. Dymov A.A., Startsev V.V., Milanovsky E.Y., Valdes-Korovkin I.A., Farkhodov Y.R., Yudina A.V., Donnerhack O., Guggenberger G. Soils and soil organic matter transformations during the two years after a low-intensity surface fire (Subpolar Ural, Russia) // Geoderma. 2021. V. 404. P. 115278. https://doi.org/10.1016/j.geoderma.2021.115278
  24. Guyon I., Weston J., Barnhill S., Vapnik V. Gene Selection for Cancer Classification using Support Vector Machines // Machine Learning. 2022. V. 46(1). P. 389–422. https://doi.org/10.1023/A:1012487302797
  25. Johnson D.W., Curtis P.S. Effects of forest management on soil C and N storage: meta analysis // Forest Ecology and Management. 2001. V. 140(2-3). P. 227–238.
  26. Kuhn M., Johnson K. Applied Predictive Modeling. N.Y.: Springer, 2013.
  27. Kuznetsova A.I., Geraskina A.P., Lukina N.V., Smirnov V.E., Tikhonova E.V., Shevchenko N.E., Gornov A.V., Ruchinskaya E.V., Tebenkova D.N. Linking Vegetation, Soil Carbon Stocks, and Earthworms in Upland Coniferous–Broadleaf Forests // Forests. 2021. V. 12(9). P. 1179. https://doi.org/10.3390/f12091179
  28. McBratney A.B., Mendonça Santos M.L., Minasny B. On digital soil mapping // Geoderma. 2003. V. 117(1–2). P. 3–52. https://doi.org/10.1016/S0016-7061(03)00223-4
  29. Poggio L., de Sousa L.M., Batjes N.H., Heuvelink G.B.M., Kempen B., Ribeiro E., Rossiter D. SoilGrids 2.0: producing soil information for the globe with quantified spatial uncertainty // Soil. 2021. V. 7(1). P. 217–240. https://doi.org/10.5194/soil-7-217-2021
  30. Rodriguez-Galiano V.F., Ghimire B., Rogan J., Chica-Olmo M., Rigol-Sanchez J.P. An assessment of the effectiveness of a random forest classifier for land-cover classification // ISPRS J. Photogrammetry Remote Sensing. 2012. V. 67. P. 93–104. https://doi.org/10.1016/j.isprsjprs.2011.11.002
  31. Suleymanov A., Abakumov E., Alekseev I., Nizamutdinov T. Digital mapping of soil properties in the high latitudes of Russia using sparse data // Geoderma Regional. 2024. V. 36. P. e00776. https://doi.org/10.1016/j.geodrs.2024.e00776
  32. Suleymanov A., Gabbasova I., Suleymanov R., Abakumov E., Polyakov V., Liebelt P. Mapping soil organic carbon under erosion processes using remote sensing // Hungarian Geographical Bulletin. 2021. V. 70(1). P. 49–64. https://doi.org/10.15201/hungeobull.70.1.4
  33. Suleymanov A., Tuktarova I., Belan L., Suleymanov R., Gabbasova I., Araslanova L. Spatial prediction of soil properties using random forest, k-nearest neighbors and cubist approaches in the foothills of the Ural Mountains, Russia // Modeling Earth Systems and Environment. 2023. V. 9(3). P. 3461–3471. https://doi.org/10.1007/s40808-023-01723-4
  34. Wadoux A.M.J.-C., Minasny B., McBratney A.B. Machine learning for digital soil mapping: Applications, challenges and suggested solutions // Earth-Sci. Rev. 2020. V. 210. P. 103359. https://doi.org/10.1016/j.earscirev.2020.103359
  35. Wadoux A.M.J.-C., Saby N.P.A., Martin M.P. Shapley values reveal the drivers of soil organic carbon stock prediction // Soil. 2023. V. 9. P. 21–38. https://doi.org/10.5194/soil-9-21-2023
  36. Wang Q., Zhao X., Chen L., Yang Q., Chen S., Zhang W. Global synthesis of temperature sensitivity of soil organic carbon decomposition: latitudinal patterns and mechanisms // Functional Ecology. 2019. V. 33. P. 514–523. https://doi.org/10.1111/1365- 2435.13256
  37. WMO, World Meteorological Organization (WMO). State of the Global Climate 2022 (WMO-No. 1316). 2023. WMO, Geneva.
  38. Zhou T., Geng Y., Chen J., Pan J., Haase D., Lausch A. High-resolution digital mapping of soil organic carbon and soil total nitrogen using DEM derivatives, Sentinel-1 and Sentinel-2 data based on machine learning algorithms // Sci. Total Environ. 2020. V. 729. P. 138244. https://doi.org/10.1016/j.scitotenv.2020.138244

Supplementary files

Supplementary Files
Action
1. JATS XML
2. Fig. 1. Location of the study area and soil samples (purple dots).

Download (1MB)
3. Fig. 2. Graph of the decrease in RMSE value when using different number of variables in the random forest algorithm.

Download (108KB)
4. Fig. 3. Scatter diagram of measured and predicted Sorg values.

Download (130KB)
5. Fig. 4. Top 15 most important spatial variables in predicting Sorg content.

Download (236KB)

Copyright (c) 2024 Russian Academy of Sciences