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

Shahin Nozari, Mohammad Reza Pahlavan-Rad, Colby Brungard, Brandon Heung and Luboš Borůvka
Additional contact information
Mohammad Reza Pahlavan-Rad: Soil and Water Research Department, Golestan Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Gorgan, Iran
Colby Brungard: Department of Plant and Environmental Sciences, College of Agricultural, Consumer, and Environmental Sciences, New Mexico State University, Las Cruces, USA
Brandon Heung: Department of Plant, Food, and Environmental Sciences, Faculty of Agriculture, Dalhousie University, Truro, Canada
Luboš Borůvka: Department of Soil Science and Soil Protection, Faculty of Agrobiology, Food, and Natural Resources, Czech University of Life Sciences Prague, Prague, Czech Republic

Soil and Water Research, 2024, vol. 19, issue 1, 32-49

Abstract: 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 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://swr.agriculturejournals.cz/doi/10.17221/119/2023-SWR.html (text/html)
http://swr.agriculturejournals.cz/doi/10.17221/119/2023-SWR.pdf (application/pdf)
free of charge

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:caa:jnlswr:v:19:y:2024:i:1:id:119-2023-swr

DOI: 10.17221/119/2023-SWR

Access Statistics for this article

Soil and Water Research is currently edited by Ing. Markéta Knížková, (Executive Editor)

More articles in Soil and Water Research from Czech Academy of Agricultural Sciences
Bibliographic data for series maintained by Ivo Andrle ().