Soil & Water Res., 2024, 19(1):32-49 | DOI: 10.17221/119/2023-SWR

Digital soil mapping using machine learning-based methods to predict soil organic carbon in two different districts in the Czech RepublicOriginal Paper

Shahin Nozari1*, Mohammad Reza Pahlavan-Rad2, Colby Brungard3, Brandon Heung4, Luboš Borůvka1
1 Department of Soil Science and Soil Protection, Faculty of Agrobiology, Food, and Natural Resources, Czech University of Life Sciences Prague, Prague, Czech Republic
2 Soil and Water Research Department, Golestan Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Gorgan, Iran
3 Department of Plant and Environmental Sciences, College of Agricultural, Consumer, and Environmental Sciences, New Mexico State University, Las Cruces, USA
4 Department of Plant, Food, and Environmental Sciences, Faculty of Agriculture, Dalhousie University, Truro, Canada

Soil organic carbon (SOC) is an important soil characteristic as well as a way how to mitigate climate change. Information on its content and spatial distribution is thus crucial. Digital soil mapping (DSM) is a suitable way to evaluate spatial distribution of soil properties thanks to its ability to obtain accurate information about soil. This research aims to apply machine learning algorithms using various environmental covariates to generate digital SOC maps for mineral topsoils in the Liberec and Domažlice districts, located in the Czech Republic. The soil class, land cover, and geology maps as well as terrain covariates extracted from the digital elevation model and remote sensing data were used as covariates in modelling. The spatial distribution of SOC was predicted based on its relationships with covariates using random forest (RF), cubist, and quantile random forest (QRF) models. Results of the RF model showed that land cover (vegetation) and elevation were the most important environmental variables in the SOC prediction in both districts. The RF had better efficiency and accuracy than the cubist and QRF to predict SOC in both districts. The greatest R2 value (0.63) was observed in the Domažlice district using the RF model. However, cubist and QRF showed appropriate performance in both districts, too.

Keywords: cubist; DSM; quantile random forest; random forest; SOC

Received: December 12, 2023; Revised: December 29, 2023; Accepted: January 3, 2024; Prepublished online: January 15, 2024; Published: February 15, 2024  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Nozari S, Pahlavan-Rad MR, Brungard C, Heung B, Borůvka L. Digital soil mapping using machine learning-based methods to predict soil organic carbon in two different districts in the Czech Republic. Soil & Water Res. 2024;19(1):32-49. doi: 10.17221/119/2023-SWR.
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. Badia D., Ruiz A., Giona A., Marti C., Casanova J., Ibbara P., Zufiaurre R. (2016): The influence of elevation on soil properties and forest litter in the Siliceous Moncayo Massif, SW Europe. Journal of Mountain Science, 13: 2155-2169. Go to original source...
    2. Borůvka L., Vašát R., Šrámek V., Neudertová Hellebrandová K., Fadrhonsová V., Sáňka M., Pavlů L., Sáňka O., Vacek O., Němeček K., Nozari S., Oppong Sarkodie V.Y. (2022): Predictors for digital mapping of forest soil organic carbon stocks in different types of landscape. Soil and Water Research, 17: 69-79. Go to original source...
    3. Breiman L. (2001): Random forests. Machine Learning, 45: 5-32. Go to original source...
    4. Brevik E.C. (2013): Soil health and productivity. In: Verheye W.H. (ed.): Soils, Plant Growth and Crop Production. Oxford, Encyclopedia of Life Support Systems (EOLSS).
    5. Brewer S., Liaw A., Wiener M., Liaw M.A. (2015): Package Random Forest. Breiman and Cutler's Random Forests for Classification and Regression. R Package Version 4.6-14. Available on https://cran.r-project.org/web/packages/randomForest/index.html
    6. Brungard C., Boettinger J.L., Duniway M.C., Wills S.A., Edwards T.C. (2015): Machine learning for predicting soil classes in three semi-arid landscapes. Geoderma, 239: 68-83. Go to original source...
    7. Conrad O., Bechtel B., Bock M., Dietrich H., Fischer E., Gerlitz L., Wehberg J., Wichmann V., Böhner J. (2015): System for Automated Geoscientific Analyses (SAGA) V. 2.1.4. Geoscientific Model Development, 8: 1991-2007. Go to original source...
    8. EEA (2018): CORINE Land Cover (CLC) 2018, Version 20, European Environment Agency, Kopenhagen, Denmark. Available on https://www.eea.europa.eu/data-and-maps/ data/corine-land-cover-accounting-layers (accessed Jan 23, 2020).
    9. Ellili Y., Walter C., Michot D., Pichelin P., Lemercier B. (2019): Mapping soil organic carbon stock change by soil monitoring and digital soil mapping at the landscape scale. Geoderma, 351: 1-8. Go to original source...
    10. Fathololoumi S., Vaezi A.R., Alavipanah S.K., Ghorbani A., Saurette D., Biswas A. (2020): Improved digital soil mapping with multitemporal remotely sensed satellite data fusion: A case study in Iran. Science of the Total Environment, 721: 137703. Go to original source... Go to PubMed...
    11. Henderson B.L., Bui E.N., Moran C.J., Simon D.A.P. (2005): Australia-wide predictions of soil properties using decision trees. Geoderma, 124: 383-398. Go to original source...
    12. Heung B., Bulmer C.E., Schmidt M.G. (2014): Predictive soil parent material mapping at a regional scale: A random forest approach. Geoderma, 214: 141-154. Go to original source...
    13. IUSS Working Group WRB (2015): World Reference Base for Soil Resources 2014 (Update 2015). International Soil Classification System for Naming Soils and Creating Legends for Soil Maps. World Soil Resources Reports No. 106, Rome, FAO.
    14. James G., Witten D., Hastie T., Tibshirani R. (2014): An Introduction to Statistical Learning: With Applications in R. Springer Publishing Company, Inc. Go to original source...
    15. Kozák J., Němeček J., Jetmar M. (1996): The database of soil information system - PUGIS. Plant Production, 42: 529-534.
    16. Kuhn M. (2012): The Caret Package. R Found. Statistical Computing. Vienna. Available on https//cran. r-project. org/packa-ge= caret.
    17. Kuhn M., Weston S., Keefer C., Coulter N., Quinlan R. (2013): Cubist: Rule-and instance-based regression modeling. R Package Version 0.0.13. Wien, CRAN.
    18. Lagacherie P., McBratney A.B., Voltz M. (eds.) (2006): Digital Soil Mapping - An Introductory Perspective. Developments in Soil Science, Vol. 31, Amsterdam, Hardbound, Elsevier Science.
    19. Lal R., Bouma J., Brevik E., Dawson L., Field D.J., Glaser B., Hatano R., Hartemink A.E., Kosaki T., Lascelles B., Monger C., Muggler C., Martial Ndzana G., Norra S., Pan X., Paradelo R., Reyes-Sánchez L.B., Sandén T., Singh B.R., Spiegel H., Yanai J., Zhang J. (2021): Soils and sustainable development goals of the United Nations: An International Union of Soil Sciences perspective. Geoderma Regional, 25: e00398. Go to original source...
    20. Lamichhane S., Kumar L., Wilson B. (2019): Digital soil mapping algorithms and covariates for soil organic carbon mapping and their implications: A review. Geoderma, 352: 395-413. Go to original source...
    21. Li L., Lu J., Wang S,. Ma Y,. Wei Q,. Li X,. Cong R., Ren T. (2016): Methods for estimating leaf nitrogen concentration of winter oilseed rape (Brassica napus L.) using in situ leaf spectroscopy. Industrial Crops and Products, 91: 194-204. Go to original source...
    22. Lorenzetti R., Barbetti R., Fantappiè M., L'Abate G., Costantini E.A.C. (2015): Comparing data mining and deterministic pedology to assess the frequency of WRB reference soil groups in the legend of small-scale maps. Geoderma, 237-238: 237-245. Go to original source...
    23. McBratney A.B., Mendonça Santos M.L., Minasny B. (2003): On digital soil mapping. Geoderma, 117: 3-52. Go to original source...
    24. Meinshausen N. (2006): Quantile regression forests. Journal of Machine Learning Research, 7: 983-999. Go to original source...
    25. Meinshausen N., Hauser A., Mooij J., Peters J., Versteeg P., Buhlmann P. (2016): Methods for causal inference from gene perturbation experiments and validation. PNAS, 113: 7361-7368. Go to original source... Go to PubMed...
    26. Miko L., Hošek M. (2009): The State of Nature and the Landscape in the Czech Republic. 1st Ed. Prague, Agency for Nature Conservation and Landscape Protection of the Czech Republic.
    27. Minasny B., McBratney A.B. (2016): Digital soil mapping: A brief history and some lessons. Geoderma, 264: 301-311. Go to original source...
    28. Minasny B., McBratney A.B., Salvador-Blanes S. (2008): Quantitative models for pedogenesis - A review. Geoderma, 144: 140-157. Go to original source...
    29. Moore D.S., Notz W.I., Flinger M.A. (2013): The Basic Practice of Statistics. 6th Ed. New York, W.H. Freeman and Company.
    30. Mosleh Z., Salehi M.H., Jafari A., Borujeni I.E., Mehnatkesh A. (2016): The effectiveness of digital soil mapping to predict soil properties over low-relief areas. Environmental Monitoring and Assessment, 188: 1-13. Go to original source... Go to PubMed...
    31. Mulder V.L., de Bruin S., Schaepman M.E., Mayr T.R. (2011): The use of remote sensing in soil and terrain mapping - A review. Geoderma, 162: 1-19. Go to original source...
    32. Němeček J. (2000): The status of soil mapping in the Czech Republic. The European Soil Information System. World Soil Resources Reports, 91: 61-65.
    33. Němeček J., Mühlhanselová M., Macků J., Vokoun J., Vavříček D., Novák P. (2011): Taxonomical classification system of soils of the Czech Republic. 2nd modified Ed. Prague, ČZU, Prague. (in Czech)
    34. Nikou M., Tziachris P. (2022): Prediction and uncertainty capabilities of quantile regression forests in estimating spatial distribution of soil organic matter. ISPRS International Journal of Geo-Information, 11: 130. Go to original source...
    35. Nozari S., Borůvka L. (2020): The effect of landscape slope on soil organic carbon in the Liberec district in the Czech Republic. International Journal of Advanced Science and Technology, 29: 3934-3942.
    36. Nozari S., Borůvka L. (2023): The effects of slope and altitude on soil organic carbon and clay content in different land-uses: A case study in the Czech Republic. Soil and Water Research, 18: 204-218. Go to original source...
    37. Pahlavan-Rad M.R., Akbari Moghaddam A.R. (2018): Spatial variability of soil texture fractions and pH in a flood plain (A case study from eastern Iran). Catena, 160: 275-281. Go to original source...
    38. Pahlavan-Rad M.R., Dahmardeh K.H., Brungard C. (2018): Predicting soil organic carbon concentrations in a low relief landscape, eastern Iran. Geoderma Regional, 15: e00195. Go to original source...
    39. Pahlavan-Rad M.R., Dahmardeh K.H., Hadizadeh M., Keykha G., Mohammadnia N., Gangali M., Keikha M., Davatgare N., Brungard C. (2020): Prediction of soil water infiltration using multiple linear regression and random forest in a dry flod plain, eastern Iran. Catena, 194: 104715. Go to original source...
    40. Panagos P., Meusburger K., Ballabio C., Borrelli P., Alewell C. (2014): Soil erodibility in Europe: A high-resolution dataset based on LUCAS. The Science of the Total Environment, 479: 189-200. Go to original source... Go to PubMed...
    41. Peters J., De Baets B., Verhoest N.E., Samson R., Degroeve S., De Becker P. Huybrechts W. (2007): Random forests as a tool for ecohydrological distribution modeling. Ecological Modeling, 207: 304-318. Go to original source...
    42. Pieri C.J. (1992): The effect of population growth on the soil. In: Fertility of Soils. Springer Series in Physical Environment, Vol. 10, Berlin, Heidelberg, Springer: 84-99. Go to original source...
    43. Pospíšil F. (1964): Fractionation of humus substances of several soil types in Czechoslovakia. Rostlinná Výroba, 10: 567-579.
    44. Prasad A.M., Iverson L.R., Liaw A. (2006): Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems, 9: 181-199. Go to original source...
    45. Pouladi N., Møller A.B. Tabatabai S., Greve M.H. (2019): Mapping soil organic matter contents at field level with cubist, random forest and kriging, Geoderma, 342: 85-92. Go to original source...
    46. Quinlan J. (1993): C4.5: Programs for Empirical Learning. San Francisco, Morgan Kaufmann Publishers, Inc.
    47. R Core Team (2018): R, a Language and Environment for Statistical Computing. Vienna, R Foundation for Statistical Computing.
    48. Selvaradjou S.K., Montanarella L., Carre F., Jones A., Panagos P., Ragunath K., Kumaraperumal R., Natarajan S. (2007): An Innovative Approach for Updating Soil Information based on Digital Soil Mapping Techniques. Official Publication of European Communities. EUR 22545 EN: 1-34.
    49. SPSS (2001): Statistics for Windows, Version 11.0. Chicago, SPSS Inc.
    50. Taghizadeh-Mehrjardi R., Nabiollahi K., Kerry R. (2016): Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran. Geoderma, 266: 98-110. Go to original source...
    51. Tesfahunegn G.B., Tamene L., Vlek P.L.G. (2011): Catchment scale spatial variability of soil properties and implications on site-specific soil management in northern Ethiopia. Soil and Tillage Research, 117: 124-139. Go to original source...
    52. Tziachris P., Aschonitis V., Chatzistathis T. (2019): Assessment of spatial hybrid methods for predicting soil organic matter using DEM derivatives and soil parameters. Catena, 174: 206-216. Go to original source...
    53. USGS (2021): US Geological Survey. Available on https://earthexplorer.usgs.gov/
    54. Vaysse K., Lagacherie P. (2017): Using quantile regression forest to estimate uncertainty of digital soil mapping products. Geoderma, 291: 55-64. Go to original source...
    55. Victoria R., Banwart S., Black H., Ingram J., Joosten H., Milne E., Noellemeyer E. (2012): The Benefits of Soil Organic Carbon. Emerging Issues in Our Global Environment. Nairobi, UNEP Division of Early Warning and Assessment United Nations Environment.
    56. Weier J., Herring D. (2000): Measuring Vegetation (NDVI & EVI). NASA. Available on https://earthobservatory.nasa.gov/Features/MeasuringVegetation/ (accessed Jan 2020).
    57. Wiesmeier M., Urbanski L., Hobley E.; Lang B., von Lützow M., Marin-Spiotta E., van Wesemael B., Rabot E., Ließ M., Garcia-Franco N. (2019): Soil organic carbon storage as a key function of soils - A review of drivers and indicators at various scales. Geoderma, 333: 149-162. Go to original source...
    58. Winowiecki L., Vågen T.G., Massawe B. Jelinski N., Yamchai Ch., Sayula G., Msoka E. (2016): Landscape-scale variability of soil health indicators: effects of cultivation on soil organic carbon in the Usambara Mountains of Tanzania. Nutrient Cycling in the Agroecosystems, 105: 263-274. Go to original source...
    59. Zeraatpisheh M., Ayoubi S., Jafari A., Tajik S., Finke P. (2019): Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran. Geoderma, 338: 445-452. Go to original source...
    60. Zhu H., Hud W., Jing Y., Cao Y. (2018): Soil organic carbon prediction based on scale-specific relationships with environmental factors by discrete wavelet transform, Geoderma, 330: 9-18. Go to original source...
    61. Žížala D., Minařík R., Skála J., Beitlerová H., Juřicová A., Rojas J.R., Penížek V., Zádorová T. (2022): High-resolution agriculture soil property maps from digital soil mapping methods, Czech Republic. Catena, 212: 106024. Go to original source...

    This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY NC 4.0), which permits non-comercial use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content