Estimation of organic carbon content in Russian soils using ensemble machine learning
https://doi.org/10.55959/MSU0579-9414-5-2022-6-49-63
Abstract
The study presents a modern quantitative assessment of the content of organic carbon in Russian soils, taking into account their huge variety, and reflects the understanding of individual factors regulating and controlling the content of organic carbon in soils of the country. The paper gives the results of three-dimensional modeling of organic carbon content in soils at several standard depths (0–5, 5–15, 15–30, 30–60, 60–100 cm) for the territory of the Russian Federation with 500 m spatial resolution using the ensemble machine learning. Automated predictive mapping was based on 4 961 soil horizons from 863 soil profiles, as well as on the extensive set of spatial information, including bioclimatic variables, digital elevation model and its derivatives, and the long-term averaged time series of MODIS data. An ensemble machine learning algorithm (stacking, stacked generalization and stacked regression) was used to build models of spatial and vertical distribution. The accuracy of obtained cartographic models was assessed using spatial cross-validation. The results of spatial cross-validation show lower accuracy: the coefficient of determination is 0,46, CCC – 0.63, logRMSE – 0,88 (RMSE – 1,41 g/kg) compared to randomize (R2 cv – 0,68, CCC – 0,81, logRMSE – 0,68 (RMSE – 0,97 g/kg)).
The proposed quantitative assessment is fully automated and makes it possible to reproduce the modeling and refine the results as new soil data are obtained.
Supporting agencies: The study was financially supported by the Russian Foundation for Basic Research (project 19-05-50063), and by the RUDN University Strategic Academic Leadership Program.
About the Authors
A. V. Chinilin
FRC “V.V. Dokuchaev Soil Science Institute”, Department of soil genesis, geography and classifi cation
Russian Federation
Russian Federation
Ph.D. in Biology
I. Yu. Savin
FRC “V.V. Dokuchaev Soil Science Institute”, Department of soil genesis, geography and classifi cation; Institute of Environmental Engineering, Peoples Friendship University of Russia (RUDN University), Department of environmental management
Russian Federation
Russian Federation
D.Sc. in Agriculture, Professor, Academician of the RAS
References
1. Biryukova O.N., Biryukov M.V. [Soil organic carbon stocks], Natsional’nyi atlas pochv Rossiiskoi Federatsii [National Atlas of Soils of the Russian Federation], Moscow, Astrel’, AST Publ., 2011b, p. 242–243. (In Russian)
2. Biryukova O.N., Biryukov M.V. [The content of organic carbon in the upper horizons of soils], Natsional’nyi atlas pochv Rossiiskoi Federatsii [National Atlas of Soils of the Russian Federation], Moscow, Astrel’, AST Publ., 2011a, p. 230–231. (In Russian)
3. Breiman L. Stacked regressions, Mach. Learn, 1996, vol. 24, no. 1, р. 49–64. DOI: https://doi.org/10.1007/bf00117832.
4. Brenning A. Spatial prediction models for landslide hazards: review, comparison and evaluation, Nat. Hazards Earth Syst. Sci., 2005, vol. 5, no . 6, р. 853–862, DOI: https:// doi.org/10.5194/nhess-5-853-2005.
5. Chernova O.V., Golozubov O.M., Alyabina I.O., Schepaschenko D.G. Integrated Approach to Spatial Assessment of Soil Organic Carbon in the Russian Federation, Eurasian Soil Sci., 2021, vol. 54, no. 3, р. 325–336, DOI: https://doi.org/10.1134/S1064229321030042.
6. FAO. Global Soil Organic Carbon Map (GSOC map), Technical Report, 2018, FAO, Rome, 162 p.
7. Gomes L.C., Faria R.M., Souza de E., Veloso G.V., Schaefer C.E.G.R., Filho E.I.F. Modelling and mapping soil organic carbon stocks in Brazil, Geoderma, 2019, vol. 340, р. 337–350, DOI: https://doi.org/10.1016/j.geoderma.2019.01.007.
8. Gorelick N., Hancher M., Dixon M., Ilyushchenko S., Thau D., Moore R. Google Earth Engine: Planetary-scale geospatial analysis for everyone, Remote Sens. Environ, 2017, vol. 202, р. 18–27, DOI: https://doi.org/10.1016/j.rse.2017.06.031.
9. Griscom B.W., Adams J., Ellis P.W., Houghton R.A., Lomax G., Miteva D.A., Schlesinger W.H., Shoch D., Siikamäki J.V., Smith P. et al. Natural climate solutions, Proc. Natl. Acad. Sci., U.S.A., 2017, vol. 114, no. 44, р. 11645–11650.
10. Konyushkov D.E., Ananko T.V., Gerasimova M.I., Lebedeva I.I. Actualization of the contents of the soil map of Russian Federation (1 : 2,5 M scale) in the format of the classification system of Russian soils for the development of the new digital map of Russia, Dokuchaev Soil Bull., 2020, no. 102, p. 21–48, DOI: https://doi.org/10.19047/0136-1694-2020-102-21-48.
11. Laan van der M.J., Polley E.C., Hubbard A.E. Super Learner, Stat. Appl. Genet. Mol. Biol., 2007, vol. 6, no. 1, p. 1–23.
12. Liang Z., Chen S., Yang Y., Zhou Y., Shi Z. High-resolution three-dimensional mapping of soil organic carbon in China: Effects of SoilGrids products on national modeling, Sci. Total Environ, 2019, vol. 685, DOI: https://doi.org/10.1016/j.scitotenv.2019.05.332.
13. Malone B.P., McBratney A.B., Minasny B., Laslett G.M. Mapping continuous depth functions of soil carbon storage and available water capacity, Geoderma, 2009, vol. 154, no. 1–2, p. 138–152, DOI: https://doi.org/10.1016/j.geoderma.2009.10.007.
14. McBratney A.B., Mendonça Santos M.L., Minasny B. On digital soil mapping, Geoderma, 2003, vol. 117, no. 1–2, p. 3–52.
15. Meinshausen N. Quantile Regression Forests, J. Mach. Learn. Res., 2006, vol. 7, р. 983–999.
16. Minasny B., Malone B.P., McBratney A.B., Angers D.A., Arrouays D., Chambers A., Chaplot V., Chen Z.S., Cheng K., Das B.S. et al. Soil carbon 4 per mille, Geoderma, 2017, vol. 292, р. 59–86, DOI: https://doi.org/10.1016/j.geoderma.2017.01.002.
17. 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, vol. 7, no. 1, p. 217–240, DOI: https://doi.org/10.5194/soil-7-217-2021.
18. Rozhkov V.A., Wagner V.B., Kogut B.M., Konyushkov D.E., Nilsson S., Sheremet V.B., Shvidenko A.Z. Soil Carbon Estimates and Soil Carbon Map for Russia, Analysis, 1996, р. 1–44.
19. Savin I.Y., Zhogolev A.V., Prudnikova E.Y. Modern Trends and Problems of Soil Mapping, Eurasian Soil Sci., 2019, vol. 52, no. 5, p. 471–480, DOI: https://doi.org/10.1134/S1064229319050107.
20. Scharlemann J.P.W., Tanner E.V.J., Hiederer R., Kapos V. Global soil carbon: understanding and managing the largest terrestrial carbon pool, Carb on Manag., 2014, vol. 5, no. 1, p. 81–91, DOI: 10.4155/cmt.13.77.
21. Schepaschenko D.G., Shvidenko A.Z., Mukhortova L.V., Vedrova E.F. The pool of organic carbon in the soils of Russia, Eurasian Soil Sci., 2013, vol. 46, no. 2, p. 107–116, DOI: 10.1134/S1064229313020129.
22. Stolbovoi V. Carbon in Russian soils, Clim. Change, 2002, vol. 55, no. 1–2, p. 131–156.
23. Szatmári G., Pásztor L., Heuvelink G.B.M. Estimating soil organic carbon stock change at multiple scales using machine learning and multivariate geostatistics, Geoderma, 2021, vol. 403, DOI: https://doi.org/10.1016/j.geoderma.2021.115356.
24. Taghizadeh-Mehrjardi R., Hamzehpour N., Hassanzadeh M., Heung B., Ghebleh Goydaragh M., Schmidt K., Scholten T. Enhancing the accuracy of machine learning models using the super learner technique in digital soil mapping, Geoderma, 2021, vol. 399, р. 115108, DOI: https://doi.org/10.1016/j.geoderma.2021.115108.
25. Zhang Y., Ji W., Saurette D.D., Easher T.H., Li H., Shi Z., Adamchuk V.I., Biswas A. Three-dimensional digital soil mapping of multiple soil properties at a field-scale using regression kriging, Geoderma, 2020, vol. 366, р. 114253, DOI: https://doi.org/10.1016/j.geoderma.2020.114253.
26. Zhou T., Geng Y., Ji C., Xu X., Wang H., Pan J., Bumberger J., Haase D., Lausch A. Prediction of soil organic carbon and the C:N ratio on a national scale using machine learning and satellite data: A comparison between Sentinel-2, Sentinel-3 and Landsat-8 images, Sci. Total Environ, 2021, vol. 755, р. 142661, DOI: https://doi.org/10.1016/j.scitotenv.2020.142661.
27. Web-source Hengl T., MacMillan R.A. Predictive Soil Mapping with R. OpenGeoHub foundation, Wageningen, the Netherlands, 2019, URL: http://www.soilmapper.org (access date 30.10.2021).
Review
For citations:
Chinilin A.V., Savin I.Yu. Estimation of organic carbon content in Russian soils using ensemble machine learning. Vestnik Moskovskogo universiteta. Seriya 5, Geografiya. 2022;(6):49-63. (In Russ.) https://doi.org/10.55959/MSU0579-9414-5-2022-6-49-63
Views:
279
Email this article 
