Mapping of soil organic carbon content using machine learning algorithms in Bayanzurkh soum
DOI:
https://doi.org/10.5564/mjgg.v62i46.4161Keywords:
Soil organic carbon content, Machine learningAbstract
Soil organic carbon (SOC) is the largest carbon reservoir in the terrestrial ecosystem and plays an important role in the global carbon cycle. Consequently, even a slight change in SOC content due to land use, soil management, or rates of soil erosion can considerably increase atmospheric CO2 concentrations. The main purpose of this study is to predict and map SOC content in small area by applying machine learning (ML) algorithms using field measurements and remote sensing data. We used to three different algorithms such as Random Forest (RF), Extreme Gradient Boosting (eXGB), and Gradient Boosted Regression (GBR) of ML. According to field work, 123 soil samples (0–30 cm) were collected from Bayanzurkh soum in Khuvsgul, and 26 variables were used to predict SOC content. As shown the prediction results, the GBR algorithm demonstrated the highest performance, explaining 78% of the variation in soil SOC content, with an RMSE of 42.9 g/kg and an MAE of 33.1 g/kg. The ranking of model performance in terms of prediction accuracy was GBR > eXGB > RF. Therefore, we found a strong relationship (R² = 0.94) between the predicted and measured values based on linear regression analysis. The most influential predictor variables were SILT (13.6%), CLAY (7.8%), NDVI (7.3%), and SOLAR RADIATION (6.3%). These results demonstrate that SOC content can be effectively predicted using machine learning algorithms. However, it is advisable to compare the performance of multiple algorithms and select the most suitable approach for the small area.
Downloads
94
References
[1] R. Lal et al., “The carbon sequestration potential of terrestrial ecosystems,” J. Soil Water Conserv., vol. 73, no. 6, p. 1, Nov. 2018, doi: 10.2489/jswc.73.6.145A.
[2] J. P. Scharlemann, E. V. Tanner, R. Hiederer, and V. Kapos, “Global soil carbon: understanding and managing the largest terrestrial carbon pool,” Carbon Manag., vol. 5, no. 1, pp. 81–91, Feb. 2014, doi: 10.4155/cmt.13.77.
[3] M. Lacoste, B. Minasny, A. McBratney, D. Michot, V. Viaud, and C. Walter, “High resolution 3D mapping of soil organic carbon in a heterogeneous agricultural landscape,” Geoderma, vol. 213, pp. 296–311, Jan. 2014, doi: 10.1016/j.geoderma.2013.07.002.
[4] J. Lin, D. Hui, A. Kumar, Z. Yu, and Y. Huang, “Editorial: Climate change and/or pollution on the carbon cycle in terrestrial ecosystems,” Front. Environ. Sci., vol. 11, p. 1253172, Jul. 2023, doi: 10.3389/fenvs.2023.1253172.
[5] M. Wiesmeier et al., “Soil organic carbon storage as a key function of soils - A review of drivers and indicators at various scales,” Geoderma, vol. 333, pp. 149–162, Jan. 2019, doi: 10.1016/j.geoderma.2018.07.026.
[6] J. Lehmann and M. Kleber, “The contentious nature of soil organic matter,” Nature, vol. 528, no. 7580, pp. 60–68, Dec. 2015, doi: 10.1038/nature16069.
[7] B. Ren, H. Chen, L. Zhang, X. Nie, S. Xing, and X. Fan, “Comparison of machine learning for predicting and mapping soil organic carbon in cultivated land in a subtropical complex geomorphic region.,” Chin. J. Eco-Agric., vol. 29, pp. 1042–1050.
[8] Y. Liu, L. Guo, Q. Jiang, H. Zhang, and Y. Chen, “Comparing geospatial techniques to predict SOC stocks,” Soil Tillage Res., vol. 148, pp. 46–58, May 2015, doi: 10.1016/j.still.2014.12.002.
[9] A. Mondal, D. Khare, S. Kundu, S. Mondal, S. Mukherjee, and A. Mukhopadhyay, “Spatial soil organic carbon (SOC) prediction by regression kriging using remote sensing data,” Egypt. J. Remote Sens. Space Sci., vol. 20, no. 1, pp. 61–70, Jun. 2017, doi: 10.1016/j.ejrs.2016.06.004.
[10] S. Kumar and R. Lal, “Mapping the organic carbon stocks of surface soils using local spatial interpolator,” J. Environ. Monit., vol. 13, no. 11, p. 3128, 2011, doi: 10.1039/c1em10520e.
[11] C. Sothe, A. Gonsamo, J. Arabian, and J. Snider, “Large scale mapping of soil organic carbon concentration with 3D machine learning and satellite observations,” Geoderma, vol. 405, p. 115402, Jan. 2022, doi: 10.1016/j.geoderma.2021.115402.
[12] S. M and P. Ts, “Geospatial modeling approaches for mapping topsoil organic carbon stock in northern part of Mongolia,” Proc. Mong. Acad. Sci., pp. 4–17, Oct. 2019, doi: 10.5564/pmas.v59i2.1215.
[13] M. Emadi, R. Taghizadeh-Mehrjardi, A. Cherati, M. Danesh, A. Mosavi, and T. Scholten, “Predicting and Mapping of Soil Organic Carbon Using Machine Learning Algorithms in Northern Iran,” Remote Sens., vol. 12, no. 14, p. 2234, Jul. 2020, doi: 10.3390/rs12142234.
[14] Q. Chen, Y. Wang, and X. Zhu, “Soil organic carbon estimation using remote sensing data-driven machine learning,” PeerJ, vol. 12, p. e17836, Aug. 2024, doi: 10.7717/peerj.17836.
[15] T. Hengl et al., “SoilGrids250m: Global gridded soil information based on machine learning,” PLOS ONE, vol. 12, no. 2, p. e0169748, Feb. 2017, doi: 10.1371/journal.pone.0169748.
[16] H. Keskin, S. Grunwald, and W. G. Harris, “Digital mapping of soil carbon fractions with machine learning,” Geoderma, vol. 339, pp. 40–58, Apr. 2019, doi: 10.1016/j.geoderma.2018.12.037.
[17] J. L. Speiser, M. E. Miller, J. Tooze, and E. Ip, “A comparison of random forest variable selection methods for classification prediction modeling,” Expert Syst. Appl., vol. 134, pp. 93–101, Nov. 2019, doi: 10.1016/j.eswa.2019.05.028.
[18] Z. Zhang et al., “Exploring the inter-decadal variability of soil organic carbon in China,” CATENA, vol. 230, p. 107242, Sep. 2023, doi: 10.1016/j.catena.2023.107242.
[19] J. H. Friedman, “Greedy function approximation: A gradient boosting machine.,” Ann. Stat., vol. 29, no. 5, Oct. 2001, doi: 10.1214/aos/1013203451.
[20] S. C. Wang, Y. Huo, and X. Mu, “Estimation of surface NO2 concentration in China based on extreme gradient boosted tree and deep learning methods,” Acta Sci Circumstantiae, vol. 43, pp. 298–308, 2023.
[21] T. Chen, J. Jio, and Z. Zhang, “Soil quality evaluation of the alluvial fan in the Lhasa River Basin, Qinghai-Tibet Plateau,” Catena, vol. 209, 2022.
[22] M. Kuhn, M. Campillos, P. González, L. J. Jensen, and P. Bork, “Large‐scale prediction of drug–target relationships,” FEBS Lett., vol. 582, no. 8, pp. 1283–1290, Apr. 2008, doi: 10.1016/j.febslet.2008.02.024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Maralmaa Ariunbold, Saruulzaya Adiya, Purevdulam Yondonrentsen, Dawaadorj Dawaasuren
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.
